Search Results for author: Ping Li

Found 239 papers, 27 papers with code

Toward Faster and Simpler Matrix Normalization via Rank-1 Update

no code implementations ECCV 2020 Tan Yu, Yunfeng Cai, Ping Li

To boost the efficiency in the GPU platform, recent methods rely on Newton-Schulz (NS) iteration to approximate the matrix square-root.

OIE@OIA: an Adaptable and Efficient Open Information Extraction Framework

no code implementations ACL 2022 Xin Wang, Minlong Peng, Mingming Sun, Ping Li

OIE@OIA follows the methodology of Open Information eXpression (OIX): parsing a sentence to an Open Information Annotation (OIA) Graph and then adapting the OIA graph to different OIE tasks with simple rules.

Open Information Extraction

A Deep Decomposable Model for Disentangling Syntax and Semantics in Sentence Representation

no code implementations Findings (EMNLP) 2021 Dingcheng Li, Hongliang Fei, Shaogang Ren, Ping Li

Recently, disentanglement based on a generative adversarial network or a variational autoencoder has significantly advanced the performance of diverse applications in CV and NLP domains.

Disentanglement Semantic Similarity +1

Inflate and Shrink:Enriching and Reducing Interactions for Fast Text-Image Retrieval

no code implementations EMNLP 2021 Haoliang Liu, Tan Yu, Ping Li

Through an inflating operation followed by a shrinking operation, both efficiency and accuracy of a late-interaction model are boosted.

Cross-Modal Retrieval Image Retrieval +1

A Predicate-Function-Argument Annotation of Natural Language for Open-Domain Information eXpression

no code implementations EMNLP 2020 Mingming Sun, Wenyue Hua, Zoey Liu, Xin Wang, Kangjie Zheng, Ping Li

Based on the same platform of OIX, the OIE strategies are reusable, and people can select a set of strategies to assemble their algorithm for a specific task so that the adaptability may be significantly increased.

Open Information Extraction

Optimal Estimator for Unlabeled Linear Regression

no code implementations ICML 2020 Hang Zhang, Ping Li

Unlabeled linear regression, or ``linear regression with an unknown permutation'', has attracted increasing attentions due to its applications in linkage record and de-anonymization.


PromptGen: Automatically Generate Prompts using Generative Models

no code implementations Findings (NAACL) 2022 Yue Zhang, Hongliang Fei, Dingcheng Li, Ping Li

Recently, prompt learning has received significant attention, where the downstream tasks are reformulated to the mask-filling task with the help of a textual prompt.

Knowledge Probing

Multi-Hop Open-Domain Question Answering over Structured and Unstructured Knowledge

no code implementations Findings (NAACL) 2022 Yue Feng, Zhen Han, Mingming Sun, Ping Li

DEHG employs a graph constructor to integrate structured and unstructured information, a context encoder to represent nodes and question, a heterogeneous information reasoning layer to conduct multi-hop reasoning on both information sources, and an answer decoder to generate answers for the question.

Open-Domain Question Answering

Learning to Selectively Learn for Weakly Supervised Paraphrase Generation with Model-based Reinforcement Learning

no code implementations NAACL 2022 Haiyan Yin, Dingcheng Li, Ping Li

In this paper, we propose a new weakly supervised paraphrase generation approach that extends the success of a recent work that leverages reinforcement learning for effective model training with data selection.

Model-based Reinforcement Learning Paraphrase Generation

CoopInit: Initializing Generative Adversarial Networks via Cooperative Learning

no code implementations21 Mar 2023 Yang Zhao, Jianwen Xie, Ping Li

The proposed algorithm consists of two learning stages: (i) Cooperative initialization stage: The discriminator of GAN is treated as an energy-based model (EBM) and is optimized via maximum likelihood estimation (MLE), with the help of the GAN's generator to provide synthetic data to approximate the learning gradients.

Image-to-Image Translation

Sparse Recovery with Shuffled Labels: Statistical Limits and Practical Estimators

no code implementations20 Mar 2023 Hang Zhang, Ping Li

From the statistical aspect, we first establish the minimax lower bounds on the sample number $n$ and the \emph{signal-to-noise ratio} ($\snr$) for the correct recovery of permutation matrix $\bPitrue$ and the support set $\supp(\bbetatrue)$, to be more specific, $n \gtrsim k\log p$ and $\log\snr \gtrsim \log n + \frac{k\log p}{n}$.

AnimeDiffusion: Anime Face Line Drawing Colorization via Diffusion Models

no code implementations20 Mar 2023 Yu Cao, Xiangqiao Meng, P. Y. Mok, Xueting Liu, Tong-Yee Lee, Ping Li

Through multiple quantitative metrics evaluated on our dataset and a user study, we demonstrate AnimeDiffusion outperforms state-of-the-art GANs-based models for anime face line drawing colorization.

Colorization Image Reconstruction

Steering Graph Neural Networks with Pinning Control

no code implementations2 Mar 2023 Acong Zhang, Ping Li, Guanrong Chen

In the semi-supervised setting where labeled data are largely limited, it remains to be a big challenge for message passing based graph neural networks (GNNs) to learn feature representations for the nodes with the same class label that is distributed discontinuously over the graph.

Graph Learning Representation Learning

Building Shortcuts between Distant Nodes with Biaffine Mapping for Graph Convolutional Networks

no code implementations17 Feb 2023 Acong Zhang, Jincheng Huang, Ping Li, Kai Zhang

Multiple recent studies show a paradox in graph convolutional networks (GCNs), that is, shallow architectures limit the capability of learning information from high-order neighbors, while deep architectures suffer from over-smoothing or over-squashing.

Contrastive Learning Node Classification +1

OPORP: One Permutation + One Random Projection

no code implementations7 Feb 2023 Ping Li, Xiaoyun Li

We show that the estimation variance is essentially: $(s-1)A + \frac{D-k}{D-1}\frac{1}{k}\left[ (1-\rho^2)^2 -2A\right]$, where $A\geq 0$ is a function of the data ($u, v$).


A Tale of Two Latent Flows: Learning Latent Space Normalizing Flow with Short-run Langevin Flow for Approximate Inference

no code implementations23 Jan 2023 Jianwen Xie, Yaxuan Zhu, Yifei Xu, Dingcheng Li, Ping Li

We study a normalizing flow in the latent space of a top-down generator model, in which the normalizing flow model plays the role of the informative prior model of the generator.

Anomaly Detection Image Inpainting +1

Sharper Analysis for Minibatch Stochastic Proximal Point Methods: Stability, Smoothness, and Deviation

no code implementations9 Jan 2023 Xiao-Tong Yuan, Ping Li

The stochastic proximal point (SPP) methods have gained recent attention for stochastic optimization, with strong convergence guarantees and superior robustness to the classic stochastic gradient descent (SGD) methods showcased at little to no cost of computational overhead added.

Stochastic Optimization

Exploration in Model-based Reinforcement Learning with Randomized Reward

no code implementations9 Jan 2023 Lingxiao Wang, Ping Li

We further extend our theory to generalized function approximation and identified conditions for reward randomization to attain provably efficient exploration.

Efficient Exploration Model-based Reinforcement Learning +2

Rethinking the Structure of Stochastic Gradients: Empirical and Statistical Evidence

no code implementations5 Dec 2022 Zeke Xie, Qian-Yuan Tang, Zheng He, Mingming Sun, Ping Li

Unfortunately, formal statistical tests for analyzing the structure and heavy tails of stochastic gradients in deep learning are still under-explored.

Stochastic Optimization

Analysis of Error Feedback in Federated Non-Convex Optimization with Biased Compression

no code implementations25 Nov 2022 Xiaoyun Li, Ping Li

Moreover, we develop a new analysis of the EF under partial client participation, which is an important scenario in FL.

Federated Learning

Degenerate Swin to Win: Plain Window-based Transformer without Sophisticated Operations

no code implementations25 Nov 2022 Tan Yu, Ping Li

To bring back the global receptive field, window-based Vision Transformers have devoted a lot of efforts to achieving cross-window communications by developing several sophisticated operations.

object-detection Object Detection +1

R2-MLP: Round-Roll MLP for Multi-View 3D Object Recognition

no code implementations20 Nov 2022 Shuo Chen, Tan Yu, Ping Li

Recently, vision architectures based exclusively on multi-layer perceptrons (MLPs) have gained much attention in the computer vision community.

3D Object Recognition Image Classification +1

On Penalization in Stochastic Multi-armed Bandits

no code implementations15 Nov 2022 Guanhua Fang, Ping Li, Gennady Samorodnitsky

We study an important variant of the stochastic multi-armed bandit (MAB) problem, which takes penalization into consideration.

Fairness Multi-Armed Bandits

Asymmetric Hashing for Fast Ranking via Neural Network Measures

no code implementations1 Nov 2022 Khoa Doan, Shulong Tan, Weijie Zhao, Ping Li

Previous learning-to-hash approaches are also not suitable to solve the fast item ranking problem since they can take a significant amount of time and computation to train the hash functions.

Recommendation Systems

A pruning method based on the dissimilarity of angle among channels and filters

1 code implementation29 Oct 2022 Jiayi Yao, Ping Li, Xiatao Kang, Yuzhe Wang

Firstly, we train a sparse model by GL penalty, and impose an angle dissimilarity constraint on the channels and filters of convolutional network to obtain a more sparse structure.

Network Pruning

Improving the Transferability of Adversarial Attacks on Face Recognition with Beneficial Perturbation Feature Augmentation

no code implementations28 Oct 2022 Fengfan Zhou, Hefei Ling, Yuxuan Shi, Jiazhong Chen, Zongyi Li, Ping Li

Though generating hard samples has shown its effectiveness in improving the generalization of models in training tasks, the effectiveness of utilizing this idea to improve the transferability of adversarial face examples remains unexplored.

Adversarial Attack Face Recognition

Deep Latent Mixture Model for Recommendation

no code implementations27 Oct 2022 Jun Zhang, Ping Li, Wei Wang

Recent advances in neural networks have been successfully applied to many tasks in online recommendation applications.

Constrained Approximate Similarity Search on Proximity Graph

no code implementations26 Oct 2022 Weijie Zhao, Shulong Tan, Ping Li

Typically a three-stage mechanism is employed in those systems: (i) a small collection of items are first retrieved by (e. g.,) approximate near neighbor search algorithms; (ii) then a collection of constraints are applied on the retrieved items; (iii) a fine-grained ranking neural network is employed to determine the final recommendation.

Quantization Recommendation Systems

Prompting through Prototype: A Prototype-based Prompt Learning on Pretrained Vision-Language Models

no code implementations19 Oct 2022 Yue Zhang, Hongliang Fei, Dingcheng Li, Tan Yu, Ping Li

In particular, we focus on few-shot image recognition tasks on pretrained vision-language models (PVLMs) and develop a method of prompting through prototype (PTP), where we define $K$ image prototypes and $K$ prompt prototypes.

Few-Shot Learning

Denoising Enhanced Distantly Supervised Ultrafine Entity Typing

no code implementations18 Oct 2022 Yue Zhang, Hongliang Fei, Ping Li

Specifically, we build a noise model to estimate the unknown labeling noise distribution over input contexts and noisy type labels.

Denoising Entity Typing

Marksman Backdoor: Backdoor Attacks with Arbitrary Target Class

no code implementations17 Oct 2022 Khoa D. Doan, Yingjie Lao, Ping Li

To achieve this goal, we propose to represent the trigger function as a class-conditional generative model and to inject the backdoor in a constrained optimization framework, where the trigger function learns to generate an optimal trigger pattern to attack any target class at will while simultaneously embedding this generative backdoor into the trained model.

Backdoor Attack

Decomposing User-APP Graph into Subgraphs for Effective APP and User Embedding Learning

no code implementations13 Oct 2022 Tan Yu, Jun Zhi, Yufei Zhang, Jian Li, Hongliang Fei, Ping Li

In this paper, we formulate the APP-installation user embedding learning into a bipartite graph embedding problem.

Graph Embedding Graph Learning

CoopHash: Cooperative Learning of Multipurpose Descriptor and Contrastive Pair Generator via Variational MCMC Teaching for Supervised Image Hashing

no code implementations9 Oct 2022 Khoa D. Doan, Jianwen Xie, Yaxuan Zhu, Yang Zhao, Ping Li

Leveraging supervised information can lead to superior retrieval performance in the image hashing domain but the performance degrades significantly without enough labeled data.


Neural Network Panning: Screening the Optimal Sparse Network Before Training

1 code implementation27 Sep 2022 Xiatao Kang, Ping Li, Jiayi Yao, Chengxi Li

Pruning on neural networks before training not only compresses the original models, but also accelerates the network training phase, which has substantial application value.

Network Pruning Scheduling

FeatureBox: Feature Engineering on GPUs for Massive-Scale Ads Systems

no code implementations26 Sep 2022 Weijie Zhao, Xuewu Jiao, Xinsheng Luo, Jingxue Li, Belhal Karimi, Ping Li

In this paper, we propose FeatureBox, a novel end-to-end training framework that pipelines the feature extraction and the training on GPU servers to save the intermediate I/O of the feature extraction.

Feature Engineering Management +1

Boost CTR Prediction for New Advertisements via Modeling Visual Content

no code implementations23 Sep 2022 Tan Yu, Zhipeng Jin, Jie Liu, Yi Yang, Hongliang Fei, Ping Li

To overcome the limitations of behavior ID features in modeling new ads, we exploit the visual content in ads to boost the performance of CTR prediction models.

Click-Through Rate Prediction Quantization

NL2GDPR: Automatically Develop GDPR Compliant Android Application Features from Natural Language

no code implementations29 Aug 2022 Faysal Hossain Shezan, Yingjie Lao, Minlong Peng, Xin Wang, Mingming Sun, Ping Li

At the core, NL2GDPR is a privacy-centric information extraction model, appended with a GDPR policy finder and a policy generator.

Catoni-style Confidence Sequences under Infinite Variance

no code implementations5 Aug 2022 Sujay Bhatt, Guanhua Fang, Ping Li, Gennady Samorodnitsky

In this paper, we provide an extension of confidence sequences for settings where the variance of the data-generating distribution does not exist or is infinite.

Package for Fast ABC-Boost

1 code implementation18 Jul 2022 Ping Li, Weijie Zhao

Although the gain formula in Li (2010) was derived for logistic regression loss, it is a generic formula for loss functions with second-derivatives.

Multi-class Classification regression

pGMM Kernel Regression and Comparisons with Boosted Trees

1 code implementation18 Jul 2022 Ping Li, Weijie Zhao

In recent prior studies, the pGMM kernel has been extensively evaluated for classification tasks, for logistic regression, support vector machines, as well as deep neural networks.


Variational Flow Graphical Model

no code implementations6 Jul 2022 Shaogang Ren, Belhal Karimi, Dingcheng Li, Ping Li

VFGs learn the representation of high dimensional data via a message-passing scheme by integrating flow-based functions through variational inference.

Representation Learning Variational Inference

Best Subset Selection with Efficient Primal-Dual Algorithm

no code implementations5 Jul 2022 Shaogang Ren, Guanhua Fang, Ping Li

Best subset selection is considered the `gold standard' for many sparse learning problems.

Sparse Learning

$k$-Median Clustering via Metric Embedding: Towards Better Initialization with Differential Privacy

no code implementations26 Jun 2022 Chenglin Fan, Ping Li, Xiaoyun Li

When designing clustering algorithms, the choice of initial centers is crucial for the quality of the learned clusters.

Defending Backdoor Attacks on Vision Transformer via Patch Processing

no code implementations24 Jun 2022 Khoa D. Doan, Yingjie Lao, Peng Yang, Ping Li

We first examine the vulnerability of ViTs against various backdoor attacks and find that ViTs are also quite vulnerable to existing attacks.

Backdoor Attack Inductive Bias

CGAR: Critic Guided Action Redistribution in Reinforcement Leaning

1 code implementation23 Jun 2022 Tairan Huang, Xu Li, Hao Li, Mingming Sun, Ping Li

As discussed in this paper, under the settings of the off-policy actor critic algorithms, we demonstrate that the critic can bring more expected discounted rewards than or at least equal to the actor.

Reinforcement Learning (RL)

Proximity Graph Maintenance for Fast Online Nearest Neighbor Search

no code implementations22 Jun 2022 Zhaozhuo Xu, Weijie Zhao, Shulong Tan, Zhixin Zhou, Ping Li

Given a vertex deletion request, we thoroughly investigate solutions to update the connections of the vertex.

Quantization Recommendation Systems

Noisy $\ell^{0}$-Sparse Subspace Clustering on Dimensionality Reduced Data

no code implementations22 Jun 2022 Yingzhen Yang, Ping Li

Our results provide theoretical guarantee on the correctness of noisy $\ell^{0}$-SSC in terms of SDP on noisy data for the first time, which reveals the advantage of noisy $\ell^{0}$-SSC in terms of much less restrictive condition on subspace affinity.

From a few Accurate 2D Correspondences to 3D Point Clouds

no code implementations13 Jun 2022 Trung-Kien Le, Ping Li

This article proposes a new method to estimate the world points and projection matrices from their correspondences.

3D Reconstruction

On Convergence of FedProx: Local Dissimilarity Invariant Bounds, Non-smoothness and Beyond

no code implementations10 Jun 2022 Xiao-Tong Yuan, Ping Li

The FedProx algorithm is a simple yet powerful distributed proximal point optimization method widely used for federated learning (FL) over heterogeneous data.

Federated Learning

Boosting the Confidence of Generalization for $L_2$-Stable Randomized Learning Algorithms

no code implementations8 Jun 2022 Xiao-Tong Yuan, Ping Li

We further substantialize these generic results to stochastic gradient descent (SGD) to derive improved high-probability generalization bounds for convex or non-convex optimization problems with natural time decaying learning rates, which have not been possible to prove with the existing hypothesis stability or uniform stability based results.

Generalization Bounds

One Loss for Quantization: Deep Hashing with Discrete Wasserstein Distributional Matching

1 code implementation CVPR 2022 Khoa D. Doan, Peng Yang, Ping Li

However, in the existing deep supervised hashing methods, coding balance and low-quantization error are difficult to achieve and involve several losses.

Quantization Retrieval

Revisiting the role of heterophily in graph representation learning: An edge classification perspective

no code implementations23 May 2022 Jincheng Huang, Ping Li, Rui Huang, Chen Na, Acong Zhang

Alternatively, it is possible to exploit the information about the presence of heterophilous neighbors for feature learning, so a hybrid message passing approach is devised to aggregate homophilious neighbors and diversify heterophilous neighbors based on edge classification.

Edge Classification Graph Learning +1

Dataset Pruning: Reducing Training Data by Examining Generalization Influence

no code implementations19 May 2022 Shuo Yang, Zeke Xie, Hanyu Peng, Min Xu, Mingming Sun, Ping Li

To answer these, we propose dataset pruning, an optimization-based sample selection method that can (1) examine the influence of removing a particular set of training samples on model's generalization ability with theoretical guarantee, and (2) construct the smallest subset of training data that yields strictly constrained generalization gap.

A Tale of Two Flows: Cooperative Learning of Langevin Flow and Normalizing Flow Toward Energy-Based Model

no code implementations ICLR 2022 Jianwen Xie, Yaxuan Zhu, Jun Li, Ping Li

Under the short-run non-mixing MCMC scenario, the estimation of the energy-based model is shown to follow the perturbation of maximum likelihood, and the short-run Langevin flow and the normalizing flow form a two-flow generator that we call CoopFlow.

On Distributed Adaptive Optimization with Gradient Compression

no code implementations ICLR 2022 Xiaoyun Li, Belhal Karimi, Ping Li

We study COMP-AMS, a distributed optimization framework based on gradient averaging and adaptive AMSGrad algorithm.

Distributed Optimization

Multi-view Geometry: Correspondences Refinement Based on Algebraic Properties

no code implementations3 May 2022 Trung-Kien Le, Ping Li

To our knowledge, there are no theoretical results for multi-view correspondences prior to this paper.

3D Reconstruction

SpaceE: Knowledge Graph Embedding by Relational Linear Transformation in the Entity Space

no code implementations21 Apr 2022 Jinxing Yu, Yunfeng Cai, Mingming Sun, Ping Li

Translation distance based knowledge graph embedding (KGE) methods, such as TransE and RotatE, model the relation in knowledge graphs as translation or rotation in the vector space.

Knowledge Graph Embedding Knowledge Graphs +2

An Energy-Based Prior for Generative Saliency

1 code implementation19 Apr 2022 Jing Zhang, Jianwen Xie, Nick Barnes, Ping Li

With the generative saliency model, we can obtain a pixel-wise uncertainty map from an image, indicating model confidence in the saliency prediction.

object-detection RGB-D Salient Object Detection +2

A Class of Two-Timescale Stochastic EM Algorithms for Nonconvex Latent Variable Models

no code implementations18 Mar 2022 Belhal Karimi, Ping Li

We motivate the choice of a double dynamic by invoking the variance reduction virtue of each stage of the method on both sources of noise: the index sampling for the incremental update and the MC approximation.

Stability and Risk Bounds of Iterative Hard Thresholding

no code implementations17 Mar 2022 Xiao-Tong Yuan, Ping Li

In this paper, we analyze the generalization performance of the Iterative Hard Thresholding (IHT) algorithm widely used for sparse recovery problems.


Label-Smoothed Backdoor Attack

no code implementations19 Feb 2022 Minlong Peng, Zidi Xiong, Mingming Sun, Ping Li

In order to achieve a high attack success rate using as few poisoned training samples as possible, most existing attack methods change the labels of the poisoned samples to the target class.

Backdoor Attack

BOAT: Bilateral Local Attention Vision Transformer

1 code implementation31 Jan 2022 Tan Yu, Gangming Zhao, Ping Li, Yizhou Yu

To improve efficiency, recent Vision Transformers adopt local self-attention mechanisms, where self-attention is computed within local windows.

On the Power-Law Hessian Spectrums in Deep Learning

no code implementations31 Jan 2022 Zeke Xie, Qian-Yuan Tang, Yunfeng Cai, Mingming Sun, Ping Li

It is well-known that the Hessian of deep loss landscape matters to optimization, generalization, and even robustness of deep learning.

GCWSNet: Generalized Consistent Weighted Sampling for Scalable and Accurate Training of Neural Networks

no code implementations7 Jan 2022 Ping Li, Weijie Zhao

For example, one can apply GCWS on the outputs of the last layer to boost the accuracy of trained deep neural networks.

Click-Through Rate Prediction

Communication-Efficient TeraByte-Scale Model Training Framework for Online Advertising

no code implementations5 Jan 2022 Weijie Zhao, Xuewu Jiao, Mingqing Hu, Xiaoyun Li, Xiangyu Zhang, Ping Li

In this paper, we propose a hardware-aware training workflow that couples the hardware topology into the algorithm design.

Click-Through Rate Prediction

Boosting RGB-D Saliency Detection by Leveraging Unlabeled RGB Images

1 code implementation1 Jan 2022 Xiaoqiang Wang, Lei Zhu, Siliang Tang, Huazhu Fu, Ping Li, Fei Wu, Yi Yang, Yueting Zhuang

The depth estimation branch is trained with RGB-D images and then used to estimate the pseudo depth maps for all unlabeled RGB images to form the paired data.

Depth Estimation object-detection +3

Learning Generative Vision Transformer with Energy-Based Latent Space for Saliency Prediction

no code implementations NeurIPS 2021 Jing Zhang, Jianwen Xie, Nick Barnes, Ping Li

In this paper, we take a step further by proposing a novel generative vision transformer with latent variables following an informative energy-based prior for salient object detection.

object-detection RGB-D Salient Object Detection +3

Causal Discovery with Flow-based Conditional Density Estimation

1 code implementation ICDM 21 2021 Shaogang Ren, Haiyan Yin, Mingming Sun, Ping Li

Then we formulate a novel evaluation metric to infer the scores for each potential causal direction based on the variance of the conditional density estimation.

Causal Discovery Density Estimation

Mitigating Forgetting in Online Continual Learning with Neuron Calibration

no code implementations NeurIPS 2021 Haiyan Yin, Peng Yang, Ping Li

Though recent studies have achieved remarkable progress in improving the online continual learning performance empowered by the deep neural networks-based models, many of today's approaches still suffer a lot from catastrophic forgetting, a persistent challenge for continual learning.

Continual Learning

Rate-Optimal Subspace Estimation on Random Graphs

no code implementations NeurIPS 2021 Zhixin Zhou, Fan Zhou, Ping Li, Cun-Hui Zhang

We show that the performance of estimating the connectivity matrix $M$ depends on the sparsity of the graph.

A Comprehensively Tight Analysis of Gradient Descent for PCA

no code implementations NeurIPS 2021 Zhiqiang Xu, Ping Li

We further give the first worst-case analysis that achieves a rate of convergence at $O(\frac{1}{\epsilon}\log\frac{1}{\epsilon})$.

A Note on Sparse Generalized Eigenvalue Problem

no code implementations NeurIPS 2021 Yunfeng Cai, Guanhua Fang, Ping Li

The sparse generalized eigenvalue problem (SGEP) aims to find the leading eigenvector with sparsity structure.

Backdoor Attack with Imperceptible Input and Latent Modification

no code implementations NeurIPS 2021 Khoa Doan, Yingjie Lao, Ping Li

Many existing countermeasures found that backdoor tends to leave tangible footprints in the latent or feature space, which can be utilized to mitigate backdoor attacks. In this paper, we extend the concept of imperceptible backdoor from the input space to the latent representation, which significantly improves the effectiveness against the existing defense mechanisms, especially those relying on the distinguishability between clean inputs and backdoor inputs in latent space.

Backdoor Attack

C-OPH: Improving the Accuracy of One Permutation Hashing (OPH) with Circulant Permutations

no code implementations18 Nov 2021 Xiaoyun Li, Ping Li

Note that C-MinHash is different from the well-known work on "One Permutation Hashing (OPH)" published in NIPS'12.

MVT: Multi-view Vision Transformer for 3D Object Recognition

no code implementations25 Oct 2021 Shuo Chen, Tan Yu, Ping Li

Nevertheless, multi-view CNN models cannot model the communications between patches from different views, limiting its effectiveness in 3D object recognition.

3D Object Recognition Inductive Bias

Layer-wise and Dimension-wise Locally Adaptive Federated Learning

no code implementations1 Oct 2021 Belhal Karimi, Ping Li, Xiaoyun Li

In the emerging paradigm of Federated Learning (FL), large amount of clients such as mobile devices are used to train possibly high-dimensional models on their respective data.

Federated Learning

Causal Discovery via Cholesky Factorization

no code implementations29 Sep 2021 Xu Li, Yunfeng Cai, Mingming Sun, Ping Li

Discovering the causal relationship via recovering the directed acyclic graph (DAG) structure from the observed data is a challenging combinatorial problem.

Causal Discovery

Boosting the Confidence of Near-Tight Generalization Bounds for Uniformly Stable Randomized Algorithms

no code implementations29 Sep 2021 Xiaotong Yuan, Ping Li

We further substantialize these generic results to SGD to derive improved high probability generalization bounds for convex or non-convex optimization with natural time decaying learning rates, which have not been possible to prove with the existing uniform stability results.

Generalization Bounds

A new look at fairness in stochastic multi-armed bandit problems

no code implementations29 Sep 2021 Guanhua Fang, Ping Li, Gennady Samorodnitsky

Under such a framework, we propose a hard-threshold UCB-like algorithm, which enjoys many merits including asymptotic fairness, nearly optimal regret, better tradeoff between reward and fairness.


k-Median Clustering via Metric Embedding: Towards Better Initialization with Privacy

no code implementations29 Sep 2021 Chenglin Fan, Ping Li, Xiaoyun Li

Our method, named the HST initialization, can also be easily extended to the setting of differential privacy (DP) to generate private initial centers.

Revisiting Locality-Sensitive Binary Codes from Random Fourier Features

no code implementations29 Sep 2021 Xiaoyun Li, Ping Li

We show the locality-sensitivity of SignRFF, and propose a new measure, called ranking efficiency, to theoretically compare different Locality-Sensitive Hashing (LSH) methods with practical implications.

Information Retrieval Quantization +1

Constructing Orthogonal Convolutions in an Explicit Manner

no code implementations ICLR 2022 Tan Yu, Jun Li, Yunfeng Cai, Ping Li

A convolution layer with an orthogonal Jacobian matrix is 1-Lipschitz in the 2-norm, making the output robust to the perturbation in input.

Lifting Imbalanced Regression with Self-Supervised Learning

no code implementations29 Sep 2021 Weiguo Pian, Hanyu Peng, Mingming Sun, Ping Li

In this paper, we work on a seamless marriage of imbalanced regression and self-supervised learning.

imbalanced classification regression +1

Practical Adversarial Training with Differential Privacy for Deep Learning

no code implementations29 Sep 2021 Zhiqi Bu, Ping Li, Weijie Zhao

In this work, we propose the practical adversarial training with differential privacy (DP-Adv), to combine the backbones from both communities and deliver robust and private models with high accuracy.

Optimal Transport for Long-Tailed Recognition with Learnable Cost Matrix

no code implementations ICLR 2022 Hanyu Peng, Mingming Sun, Ping Li

It is attracting attention to the long-tailed recognition problem, a burning issue that has become very popular recently.

Long-tail Learning

$f$-Divergence Thermodynamic Variational Objective: a Deformed Geometry Perspective

no code implementations29 Sep 2021 Jun Li, Ping Li

In this paper, we propose a $f$-divergence Thermodynamic Variational Objective ($f$-TVO).

Variational Inference

Unsupervised Contrastive Learning for Signal-Dependent Noise Synthesis

no code implementations29 Sep 2021 Nanqing Dong, Jianwen Xie, Ping Li

We present a simple yet robust noise synthesis framework based on unsupervised contrastive learning.

Contrastive Learning

Fairness-aware Federated Learning

no code implementations29 Sep 2021 Zhuozhuo Tu, Zhiqiang Xu, Tairan Huang, DaCheng Tao, Ping Li

Federated Learning is a machine learning technique where a network of clients collaborates with a server to learn a centralized model while keeping data localized.

Fairness Federated Learning +1

C-MinHash: Improving Minwise Hashing with Circulant Permutation

no code implementations29 Sep 2021 Xiaoyun Li, Ping Li

Minwise hashing (MinHash) is an important and practical algorithm for generating random hashes to approximate the Jaccard (resemblance) similarity in massive binary (0/1) data.

Discriminative Similarity for Data Clustering

no code implementations ICLR 2022 Yingzhen Yang, Ping Li

Similarity-based clustering methods separate data into clusters according to the pairwise similarity between the data, and the pairwise similarity is crucial for their performance.

Toward Communication Efficient Adaptive Gradient Method

no code implementations10 Sep 2021 Xiangyi Chen, Xiaoyun Li, Ping Li

While adaptive gradient methods have been proven effective for training neural nets, the study of adaptive gradient methods in federated learning is scarce.

BIG-bench Machine Learning Distributed Optimization +1

C-MinHash: Practically Reducing Two Permutations to Just One

no code implementations10 Sep 2021 Xiaoyun Li, Ping Li

That is, one single permutation is used for both the initial pre-processing step to break the structures in the data and the circulant hashing step to generate $K$ hashes.

Extreme Bandits using Robust Statistics

no code implementations9 Sep 2021 Sujay Bhatt, Ping Li, Gennady Samorodnitsky

We consider a multi-armed bandit problem motivated by situations where only the extreme values, as opposed to expected values in the classical bandit setting, are of interest.

On the Convergence of Decentralized Adaptive Gradient Methods

no code implementations7 Sep 2021 Xiangyi Chen, Belhal Karimi, Weijie Zhao, Ping Li

Adaptive gradient methods including Adam, AdaGrad, and their variants have been very successful for training deep learning models, such as neural networks.

Distributed Computing Distributed Optimization

C-MinHash: Rigorously Reducing $K$ Permutations to Two

no code implementations7 Sep 2021 Xiaoyun Li, Ping Li

Unlike classical MinHash, these $K$ hashes are obviously correlated, but we are able to provide rigorous proofs that we still obtain an unbiased estimate of the Jaccard similarity and the theoretical variance is uniformly smaller than that of the classical MinHash with $K$ independent permutations.

Non-Local Feature Aggregation on Graphs via Latent Fixed Data Structures

no code implementations16 Aug 2021 Mostafa Rahmani, Rasoul Shafipour, Ping Li

The proposed approach is used to design several novel global feature aggregation methods based on the choice of the LFDS.

Provable Data Clustering via Innovation Search

no code implementations16 Aug 2021 Weiwei Li, Mostafa Rahmani, Ping Li

It is shown that in contrast to most of the existing methods which require the subspaces to be sufficiently incoherent with each other, Innovation Pursuit only requires the innovative components of the subspaces to be sufficiently incoherent with each other.

S$^2$-MLPv2: Improved Spatial-Shift MLP Architecture for Vision

2 code implementations2 Aug 2021 Tan Yu, Xu Li, Yunfeng Cai, Mingming Sun, Ping Li

More recently, using smaller patches with a pyramid structure, Vision Permutator (ViP) and Global Filter Network (GFNet) achieve better performance than S$^2$-MLP.

Inductive Bias

Rethinking Token-Mixing MLP for MLP-based Vision Backbone

no code implementations28 Jun 2021 Tan Yu, Xu Li, Yunfeng Cai, Mingming Sun, Ping Li

By introducing the inductive bias from the image processing, convolution neural network (CNN) has achieved excellent performance in numerous computer vision tasks and has been established as \emph{de facto} backbone.

Inductive Bias

A Systematic Collection of Medical Image Datasets for Deep Learning

1 code implementation24 Jun 2021 Johann Li, Guangming Zhu, Cong Hua, Mingtao Feng, BasheerBennamoun, Ping Li, Xiaoyuan Lu, Juan Song, Peiyi Shen, Xu Xu, Lin Mei, Liang Zhang, Syed Afaq Ali Shah, Mohammed Bennamoun

Thus, as comprehensive as possible, this paper provides a collection of medical image datasets with their associated challenges for deep learning research.

Closed-Form, Provable, and Robust PCA via Leverage Statistics and Innovation Search

no code implementations23 Jun 2021 Mostafa Rahmani, Ping Li

In the application of Innovation Search for outlier detection, the directions of innovation were utilized to measure the innovation of the data points.

Outlier Detection

Learning Deep Latent Variable Models by Short-Run MCMC Inference With Optimal Transport Correction

no code implementations CVPR 2021 Dongsheng An, Jianwen Xie, Ping Li

Learning latent variable models with deep top-down architectures typically requires inferring the latent variables for each training example based on the posterior distribution of these latent variables.

Patchwise Generative ConvNet: Training Energy-Based Models From a Single Natural Image for Internal Learning

no code implementations CVPR 2021 Zilong Zheng, Jianwen Xie, Ping Li

Exploiting internal statistics of a single natural image has long been recognized as a significant research paradigm where the goal is to learn the distribution of patches within the image without relying on external training data.

Image Generation Super-Resolution

S$^2$-MLP: Spatial-Shift MLP Architecture for Vision

1 code implementation14 Jun 2021 Tan Yu, Xu Li, Yunfeng Cai, Mingming Sun, Ping Li

We discover that the token-mixing MLP is a variant of the depthwise convolution with a global reception field and spatial-specific configuration.

Cross-lingual Cross-modal Pretraining for Multimodal Retrieval

no code implementations NAACL 2021 Hongliang Fei, Tan Yu, Ping Li

Recent pretrained vision-language models have achieved impressive performance on cross-modal retrieval tasks in English.

Cross-Modal Retrieval Machine Translation +2

Mitigating Forgetting in Online Continual Learning with Neuron Calibration

no code implementations NeurIPS 2021 Haiyan Yin, Peng Yang, Ping Li

Though recent studies have achieved remarkable progress in improving the online continual learning performance empowered by the deep neural networks-based models, many of today's approaches still suffer a lot from catastrophic forgetting, a persistent challenge for continual learning.

Continual Learning

High-quality Low-dose CT Reconstruction Using Convolutional Neural Networks with Spatial and Channel Squeeze and Excitation

no code implementations1 Apr 2021 Jingfeng Lu, Shuo Wang, Ping Li, Dong Ye

Low-dose computed tomography (CT) allows the reduction of radiation risk in clinical applications at the expense of image quality, which deteriorates the diagnosis accuracy of radiologists.

Computed Tomography (CT) Image Reconstruction

Quantization Algorithms for Random Fourier Features

no code implementations25 Feb 2021 Xiaoyun Li, Ping Li

Closely related to RP, the method of random Fourier features (RFF) has also become popular, for approximating the Gaussian kernel.

Dimensionality Reduction Quantization

Simulation on the Transparency of Electrons and Ion Back Flow for a Time Projection Chamber based on Staggered Multiple THGEMs

no code implementations16 Feb 2021 Mengzhi Wu, Qian Liu, Ping Li, Shi Chen, Binlong Wang, Wenhan Shen, Shiping Chen, Yangheng Zheng, Yigang Xie, Jin Li

The IBF and the transparent rate of electrons are two essential indicators of TPC, which affect the energy resolution and counting rate respectively.

Instrumentation and Detectors High Energy Physics - Experiment

Convergent Adaptive Gradient Methods in Decentralized Optimization

no code implementations1 Jan 2021 Xiangyi Chen, Belhal Karimi, Weijie Zhao, Ping Li

Specifically, we propose a general algorithmic framework that can convert existing adaptive gradient methods to their decentralized counterparts.

Distributed Optimization

Temporal Cue Guided Video Highlight Detection With Low-Rank Audio-Visual Fusion

no code implementations ICCV 2021 Qinghao Ye, Xiyue Shen, Yuan Gao, ZiRui Wang, Qi Bi, Ping Li, Guang Yang

Video highlight detection plays an increasingly important role in social media content filtering, however, it remains highly challenging to develop automated video highlight detection methods because of the lack of temporal annotations (i. e., where the highlight moments are in long videos) for supervised learning.

Association Highlight Detection +1

LIRA: Learnable, Imperceptible and Robust Backdoor Attacks

2 code implementations ICCV 2021 Khoa Doan, Yingjie Lao, Weijie Zhao, Ping Li

Under this optimization framework, the trigger generator function will learn to manipulate the input with imperceptible noise to preserve the model performance on the clean data and maximize the attack success rate on the poisoned data.

Backdoor Attack backdoor defense +1

Robust Watermarking for Deep Neural Networks via Bi-Level Optimization

no code implementations ICCV 2021 Peng Yang, Yingjie Lao, Ping Li

Deep neural networks (DNNs) have become state-of-the-art in many application domains.

Learning Energy-Based Generative Models via Coarse-to-Fine Expanding and Sampling

no code implementations ICLR 2021 Yang Zhao, Jianwen Xie, Ping Li

Energy-based models (EBMs) for generative modeling parametrize a single net and can be directly trained by maximum likelihood estimation.

Translation Unsupervised Image-To-Image Translation

Cross-Probe BERT for Efficient and Effective Cross-Modal Search

no code implementations1 Jan 2021 Tan Yu, Hongliang Fei, Ping Li

Inspired by the great success of BERT in NLP tasks, many text-vision BERT models emerged recently.

Image Retrieval Retrieval

MISSO: Minimization by Incremental Stochastic Surrogate Optimization for Large Scale Nonconvex and Nonsmooth Problems

no code implementations1 Jan 2021 Belhal Karimi, Hoi To Wai, Eric Moulines, Ping Li

Many constrained, nonconvex and nonsmooth optimization problems can be tackled using the majorization-minimization (MM) method which alternates between constructing a surrogate function which upper bounds the objective function, and then minimizing this surrogate.

Variational Inference

Learning Energy-Based Model with Variational Auto-Encoder as Amortized Sampler

no code implementations29 Dec 2020 Jianwen Xie, Zilong Zheng, Ping Li

In this paper, we propose to learn a variational auto-encoder (VAE) to initialize the finite-step MCMC, such as Langevin dynamics that is derived from the energy function, for efficient amortized sampling of the EBM.

Towards Better Generalization of Adaptive Gradient Methods

no code implementations NeurIPS 2020 Yingxue Zhou, Belhal Karimi, Jinxing Yu, Zhiqiang Xu, Ping Li

Adaptive gradient methods such as AdaGrad, RMSprop and Adam have been optimizers of choice for deep learning due to their fast training speed.

RANet: Region Attention Network for Semantic Segmentation

1 code implementation NeurIPS 2020 Dingguo Shen, Yuanfeng Ji, Ping Li, Yi Wang, Di Lin

In contrast to the previous methods, RANet configures the information pathways between the pixels in different regions, enabling the region interaction to exchange the regional context for enhancing all of the pixels in the image.

Semantic Segmentation

Optimal Prediction of the Number of Unseen Species with Multiplicity

no code implementations NeurIPS 2020 Yi Hao, Ping Li

Based on a sample of size $n$, we consider estimating the number of symbols that appear at least $\mu$ times in an independent sample of size $a \cdot n$, where $a$ is a given parameter.

Ratio Trace Formulation of Wasserstein Discriminant Analysis

no code implementations NeurIPS 2020 Hexuan Liu, Yunfeng Cai, You-Lin Chen, Ping Li

We reformulate the Wasserstein Discriminant Analysis (WDA) as a ratio trace problem and present an eigensolver-based algorithm to compute the discriminative subspace of WDA.

HWA: Hyperparameters Weight Averaging in Bayesian Neural Networks

no code implementations pproximateinference AABI Symposium 2021 Belhal Karimi, Ping Li

Bayesian neural networks attempt to combine the strong predictive performance of neural networks with formal quantification of uncertainty of the predicted output in the Bayesian framework.

Identification of Matrix Joint Block Diagonalization

no code implementations2 Nov 2020 Yunfeng Cai, Ping Li

This paper considers the identification problem for BJBDP, that is, under what conditions and by what means, we can identify the diagonalizer $A$ and the block diagonal structure of $\Sigma_i$, especially when there is noise in $C_i$'s.

Tensor Completion via Tensor Networks with a Tucker Wrapper

no code implementations29 Oct 2020 Yunfeng Cai, Ping Li

In this paper, we propose to solve LRTC via tensor networks with a Tucker wrapper.

Tensor Networks Video Inpainting

Exploring global diverse attention via pairwise temporal relation for video summarization

no code implementations23 Sep 2020 Ping Li, Qinghao Ye, Luming Zhang, Li Yuan, Xianghua Xu, Ling Shao

In this paper, we propose an efficient convolutional neural network architecture for video SUMmarization via Global Diverse Attention called SUM-GDA, which adapts attention mechanism in a global perspective to consider pairwise temporal relations of video frames.

Video Summarization

A Framework of Randomized Selection Based Certified Defenses Against Data Poisoning Attacks

no code implementations18 Sep 2020 Ruoxin Chen, Jie Li, Chentao Wu, Bin Sheng, Ping Li

Random selection based defenses can achieve certified robustness by averaging the classifiers' predictions on the sub-datasets sampled from the training set.

Data Poisoning

Understanding and Detecting Convergence for Stochastic Gradient Descent with Momentum

no code implementations27 Aug 2020 Jerry Chee, Ping Li

We construct a statistical diagnostic test for convergence to the stationary phase using the inner product between successive gradients and demonstrate that the proposed diagnostic works well.

Stochastic Optimization

FedSKETCH: Communication-Efficient and Private Federated Learning via Sketching

no code implementations11 Aug 2020 Farzin Haddadpour, Belhal Karimi, Ping Li, Xiaoyun Li

Communication complexity and privacy are the two key challenges in Federated Learning where the goal is to perform a distributed learning through a large volume of devices.

Federated Learning

MeDaS: An open-source platform as service to help break the walls between medicine and informatics

no code implementations12 Jul 2020 Liang Zhang, Johann Li, Ping Li, Xiaoyuan Lu, Peiyi Shen, Guangming Zhu, Syed Afaq Shah, Mohammed Bennarmoun, Kun Qian, Björn W. Schuller

To the best of our knowledge, MeDaS is the first open-source platform proving a collaborative and interactive service for researchers from a medical background easily using DL related toolkits, and at the same time for scientists or engineers from information sciences to understand the medical knowledge side.

Learning Interpretable Relationships between Entities, Relations and Concepts via Bayesian Structure Learning on Open Domain Facts

no code implementations ACL 2020 Jingyuan Zhang, Mingming Sun, Yue Feng, Ping Li

Compared to the state-of-the-art methods, the learned network structures help improving the identification of concepts for entities based on the relations of entities on both datasets.

Cooperative Rate-Splitting for Secrecy Sum-Rate Enhancement in Multi-antenna Broadcast Channels

no code implementations3 Jun 2020 Ping Li, Ming Chen, Yijie Mao, Zhaohui Yang, Bruno Clerckx, Mohammad Shikh-Bahaei

In this paper, we employ Cooperative Rate-Splitting (CRS) technique to enhance the Secrecy Sum Rate (SSR) for the Multiple Input Single Output (MISO) Broadcast Channel (BC), consisting of two legitimate users and one eavesdropper, with perfect Channel State Information (CSI) available at all nodes.

Estimate the Implicit Likelihoods of GANs with Application to Anomaly Detection

1 code implementation20 Apr 2020 Shaogang Ren, Dingcheng Li, Zhixin Zhou, Ping Li

The thriving of deep models and generative models provides approaches to model high dimensional distributions.

Anomaly Detection

Randomized Kernel Multi-view Discriminant Analysis

no code implementations2 Apr 2020 Xiaoyun Li, Jie Gui, Ping Li

In this paper, we propose the kernel version of multi-view discriminant analysis, called kernel multi-view discriminant analysis (KMvDA).

Object Recognition

Distributed Primal-Dual Optimization for Online Multi-Task Learning

no code implementations2 Apr 2020 Peng Yang, Ping Li

Conventional online multi-task learning algorithms suffer from two critical limitations: 1) Heavy communication caused by delivering high velocity of sequential data to a central machine; 2) Expensive runtime complexity for building task relatedness.

Multi-Task Learning

Solving the Robust Matrix Completion Problem via a System of Nonlinear Equations

no code implementations24 Mar 2020 Yunfeng Cai, Ping Li

We consider the problem of robust matrix completion, which aims to recover a low rank matrix $L_*$ and a sparse matrix $S_*$ from incomplete observations of their sum $M=L_*+S_*\in\mathbb{R}^{m\times n}$.

Matrix Completion

An Inverse-free Truncated Rayleigh-Ritz Method for Sparse Generalized Eigenvalue Problem

no code implementations24 Mar 2020 Yunfeng Cai, Ping Li

Particularly, a new truncation strategy is proposed, which is able to find the support set of the leading eigenvector effectively.

Distributed Hierarchical GPU Parameter Server for Massive Scale Deep Learning Ads Systems

1 code implementation12 Mar 2020 Weijie Zhao, Deping Xie, Ronglai Jia, Yulei Qian, Ruiquan Ding, Mingming Sun, Ping Li

For example, a sponsored online advertising system can contain more than $10^{11}$ sparse features, making the neural network a massive model with around 10 TB parameters.

Meta-CoTGAN: A Meta Cooperative Training Paradigm for Improving Adversarial Text Generation

no code implementations12 Mar 2020 Haiyan Yin, Dingcheng Li, Xu Li, Ping Li

To this end, we introduce a cooperative training paradigm, where a language model is cooperatively trained with the generator and we utilize the language model to efficiently shape the data distribution of the generator against mode collapse.

Adversarial Text Language Modelling +2

Selective Convolutional Network: An Efficient Object Detector with Ignoring Background

no code implementations4 Feb 2020 Hefei Ling, Yangyang Qin, Li Zhang, Yuxuan Shi, Ping Li

It is well known that attention mechanisms can effectively improve the performance of many CNNs including object detectors.

Structure-Feature based Graph Self-adaptive Pooling

1 code implementation30 Jan 2020 Liang Zhang, Xudong Wang, Hongsheng Li, Guangming Zhu, Peiyi Shen, Ping Li, Xiaoyuan Lu, Syed Afaq Ali Shah, Mohammed Bennamoun

To solve these problems mentioned above, we propose a novel graph self-adaptive pooling method with the following objectives: (1) to construct a reasonable pooled graph topology, structure and feature information of the graph are considered simultaneously, which provide additional veracity and objectivity in node selection; and (2) to make the pooled nodes contain sufficiently effective graph information, node feature information is aggregated before discarding the unimportant nodes; thus, the selected nodes contain information from neighbor nodes, which can enhance the use of features of the unselected nodes.

Graph Classification

Outlier Detection and Data Clustering via Innovation Search

no code implementations30 Dec 2019 Mostafa Rahmani, Ping Li

In this paper, we present a new discovery that the directions of innovation can be used to design a provable and strong robust (to outlier) PCA method.

Outlier Detection

Generalization Error Analysis of Quantized Compressive Learning

no code implementations NeurIPS 2019 Xiaoyun Li, Ping Li

In this paper, we consider the learning problem where the projected data is further compressed by scalar quantization, which is called quantized compressive learning.


Towards Practical Alternating Least-Squares for CCA

no code implementations NeurIPS 2019 Zhiqiang Xu, Ping Li

To promote the practical use of ALS for CCA, we propose truly alternating least-squares.

Random Projections with Asymmetric Quantization

no code implementations NeurIPS 2019 Xiaoyun Li, Ping Li

The method of random projection has been a popular tool for data compression, similarity search, and machine learning.

Data Compression Quantization

A Fourier Analytical Approach to Estimation of Smooth Functions in Gaussian Shift Model

no code implementations5 Nov 2019 Fan Zhou, Ping Li

Let $\mathbf{x}_j = \mathbf{\theta} + \mathbf{\epsilon}_j$, $j=1,\dots, n$ be i. i. d.

Reinforced Product Metadata Selection for Helpfulness Assessment of Customer Reviews

no code implementations IJCNLP 2019 Miao Fan, Chao Feng, Mingming Sun, Ping Li

Given a product, a selector (agent) learns from both the keys in the product metadata and one of its reviews to take an action that selects the correct value, and a successive predictor (network) makes the free-text review attend to this value to obtain better neural representations for helpfulness assessment.

On Efficient Retrieval of Top Similarity Vectors

no code implementations IJCNLP 2019 Shulong Tan, Zhixin Zhou, Zhaozhuo Xu, Ping Li

Retrieval of relevant vectors produced by representation learning critically influences the efficiency in natural language processing (NLP) tasks.

BIG-bench Machine Learning Representation Learning +1

Graph Analysis and Graph Pooling in the Spatial Domain

no code implementations3 Oct 2019 Mostafa Rahmani, Ping Li

The proposed approach leverages a spatial representation of the graph which makes the neural network aware of the differences between the nodes and also their locations in the graph.

Graph Embedding

Zeroth Order Optimization by a Mixture of Evolution Strategies

no code implementations25 Sep 2019 Jun-Kun Wang, Xiaoyun Li, Ping Li

Perhaps the only methods that enjoy convergence guarantees are the ones that sample the perturbed points uniformly from a unit sphere or from a multivariate Gaussian distribution with an isotropic covariance.

The Benefits of Diversity: Permutation Recovery in Unlabeled Sensing from Multiple Measurement Vectors

no code implementations5 Sep 2019 Hang Zhang, Martin Slawski, Ping Li

For the case in which both the signal and permutation are unknown, the problem is reformulated as a bi-convex optimization problem with an auxiliary variable, which can be solved by the Alternating Direction Method of Multipliers (ADMM).

Multi-Spectral Visual Odometry without Explicit Stereo Matching

no code implementations23 Aug 2019 Weichen Dai, Yu Zhang, Donglei Sun, Naira Hovakimyan, Ping Li

Moreover, the proposed method can also provide a metric 3D reconstruction in semi-dense density with multi-spectral information, which is not available from existing multi-spectral methods.

3D Reconstruction Stereo Matching +2

On Convergence of Distributed Approximate Newton Methods: Globalization, Sharper Bounds and Beyond

no code implementations6 Aug 2019 Xiao-Tong Yuan, Ping Li

We first introduce a simple variant of DANE equipped with backtracking line search, for which global asymptotic convergence and sharper local non-asymptotic convergence rate guarantees can be proved for both quadratic and non-quadratic strongly convex functions.

A Two-Stage Approach to Multivariate Linear Regression with Sparsely Mismatched Data

no code implementations16 Jul 2019 Martin Slawski, Emanuel Ben-David, Ping Li

A tacit assumption in linear regression is that (response, predictor)-pairs correspond to identical observational units.


Integration of Knowledge Graph Embedding Into Topic Modeling with Hierarchical Dirichlet Process

no code implementations NAACL 2019 Dingcheng Li, Siamak Zamani, Jingyuan Zhang, Ping Li

Leveraging domain knowledge is an effective strategy for enhancing the quality of inferred low-dimensional representations of documents by topic models.

Document Classification General Classification +3


no code implementations ICLR 2019 Mostafa Rahmani, Ping Li

In the second step, the GNN is applied to the point-cloud representation of the graph provided by the embedding method.

General Classification Graph Classification +2

Logician: A Unified End-to-End Neural Approach for Open-Domain Information Extraction

no code implementations29 Apr 2019 Mingming Sun, Xu Li, Xin Wang, Miao Fan, Yue Feng, Ping Li

In this paper, we consider the problem of open information extraction (OIE) for extracting entity and relation level intermediate structures from sentences in open-domain.

Open Information Extraction Relation Extraction

Cycle-SUM: Cycle-consistent Adversarial LSTM Networks for Unsupervised Video Summarization

no code implementations17 Apr 2019 Li Yuan, Francis EH Tay, Ping Li, Li Zhou, Jiashi Feng

The evaluator defines a learnable information preserving metric between original video and summary video and "supervises" the selector to identify the most informative frames to form the summary video.

Unsupervised Video Summarization

An Optimistic Acceleration of AMSGrad for Nonconvex Optimization

no code implementations ICLR 2020 Jun-Kun Wang, Xiaoyun Li, Belhal Karimi, Ping Li

We propose a new variant of AMSGrad, a popular adaptive gradient based optimization algorithm widely used for training deep neural networks.

RGB-D SLAM in Dynamic Environments Using Point Correlations

no code implementations8 Nov 2018 Weichen Dai, Yu Zhang, Ping Li, Zheng Fang, Sebastian Scherer

This method utilizes the correlation between map points to separate points that are part of the static scene and points that are part of different moving objects into different groups.

Motion Estimation Simultaneous Localization and Mapping

Logician and Orator: Learning from the Duality between Language and Knowledge in Open Domain

no code implementations EMNLP 2018 Mingming Sun, Xu Li, Ping Li

We propose the task of Open-Domain Information Narration (OIN) as the reverse task of Open Information Extraction (OIE), to implement the dual structure between language and knowledge in the open domain.

Open Information Extraction reinforcement-learning +2

Fast Binary Functional Search on Graph

no code implementations27 Sep 2018 Shulong Tan, Zhixin Zhou, Zhaozhuo Xu, Ping Li

As Approximate Nearest Neighbor Search (ANNS) techniques have specifications on metric distances, efficient searching by advanced measures is still an open question.

Provable Variable Selection for Streaming Features

no code implementations ICML 2018 Jing Wang, Jie Shen, Ping Li

As a remedy, online feature selection has attracted increasing attention in recent years.

Variable Selection

Several Tunable GMM Kernels

no code implementations8 May 2018 Ping Li

In this study, we propose a series of "tunable GMM kernels" which are simple and perform largely comparably to tree methods on the same datasets.

General Classification Multi-class Classification

Sign-Full Random Projections

no code implementations26 Apr 2018 Ping Li

At high similarity ($\rho\rightarrow1$), the asymptotic variance of recommended estimator is only $\frac{4}{3\pi} \approx 0. 4$ of the estimator for sign-sign projections.

Partial Hard Thresholding: Towards A Principled Analysis of Support Recovery

no code implementations NeurIPS 2017 Jie Shen, Ping Li

In machine learning and compressed sensing, it is of central importance to understand when a tractable algorithm recovers the support of a sparse signal from its compressed measurements.

Simple strategies for recovering inner products from coarsely quantized random projections

no code implementations NeurIPS 2017 Ping Li, Martin Slawski

Random projections have been increasingly adopted for a diverse set of tasks in machine learning involving dimensionality reduction.

Data Compression Dimensionality Reduction +1

On the Iteration Complexity of Support Recovery via Hard Thresholding Pursuit

no code implementations ICML 2017 Jie Shen, Ping Li

Recovering the support of a sparse signal from its compressed samples has been one of the most important problems in high dimensional statistics.

Tunable GMM Kernels

no code implementations9 Jan 2017 Ping Li

The linearized GMM kernel was extensively compared in with linearized radial basis function (RBF) kernel.

General Classification

Generalized Intersection Kernel

no code implementations29 Dec 2016 Ping Li

Following the very recent line of work on the ``generalized min-max'' (GMM) kernel, this study proposes the ``generalized intersection'' (GInt) kernel and the related ``normalized generalized min-max'' (NGMM) kernel.

Exact Recovery of Hard Thresholding Pursuit

no code implementations NeurIPS 2016 Xiaotong Yuan, Ping Li, Tong Zhang

In this paper, we bridge this gap by showing, for the first time, that exact recovery of the global sparse minimizer is possible for HTP-style methods under restricted strong condition number bounding conditions.

Learning Additive Exponential Family Graphical Models via \ell_{2,1}-norm Regularized M-Estimation

no code implementations NeurIPS 2016 Xiaotong Yuan, Ping Li, Tong Zhang, Qingshan Liu, Guangcan Liu

We investigate a subclass of exponential family graphical models of which the sufficient statistics are defined by arbitrary additive forms.

Quantized Random Projections and Non-Linear Estimation of Cosine Similarity

no code implementations NeurIPS 2016 Ping Li, Michael Mitzenmacher, Martin Slawski

Random projections constitute a simple, yet effective technique for dimensionality reduction with applications in learning and search problems.

Dimensionality Reduction Quantization

Relational Multi-Manifold Co-Clustering

no code implementations16 Nov 2016 Ping Li, Jiajun Bu, Chun Chen, Zhanying He, Deng Cai

In this study, we focus on improving the co-clustering performance via manifold ensemble learning, which is able to maximally approximate the intrinsic manifolds of both the sample and feature spaces.

Ensemble Learning

Constrained Low-Rank Learning Using Least Squares-Based Regularization

no code implementations15 Nov 2016 Ping Li, Jun Yu, Meng Wang, Luming Zhang, Deng Cai, Xuelong. Li

To achieve this goal, we cast the problem into a constrained rank minimization framework by adopting the least squares regularization.

General Classification Image Categorization +2