Search Results for author:
Found 239 papers, 27 papers with code
Toward Faster and Simpler Matrix Normalization via Rank-1 Update
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
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.
A Deep Decomposable Model for Disentangling Syntax and Semantics in Sentence Representation
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.
Inflate and Shrink:Enriching and Reducing Interactions for Fast Text-Image Retrieval
Through an inflating operation followed by a shrinking operation, both efficiency and accuracy of a late-interaction model are boosted.
A Predicate-Function-Argument Annotation of Natural Language for Open-Domain Information eXpression
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.
Optimal Estimator for Unlabeled Linear Regression
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
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.
Multi-Hop Open-Domain Question Answering over Structured and Unstructured Knowledge
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.
Cross-Lingual Cross-Modal Consolidation for Effective Multilingual Video Corpus Moment Retrieval
Existing multilingual video corpus moment retrieval (mVCMR) methods are mainly based on a two-stream structure.
Learning to Selectively Learn for Weakly Supervised Paraphrase Generation with Model-based Reinforcement Learning
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.
CoopInit: Initializing Generative Adversarial Networks via Cooperative Learning
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.
Sparse Recovery with Shuffled Labels: Statistical Limits and Practical Estimators
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
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.
Steering Graph Neural Networks with Pinning Control
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.
Building Shortcuts between Distant Nodes with Biaffine Mapping for Graph Convolutional Networks
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.
OPORP: One Permutation + One Random Projection
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
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.
Sharper Analysis for Minibatch Stochastic Proximal Point Methods: Stability, Smoothness, and Deviation
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.
Exploration in Model-based Reinforcement Learning with Randomized Reward
We further extend our theory to generalized function approximation and identified conditions for reward randomization to attain provably efficient exploration.
Rethinking the Structure of Stochastic Gradients: Empirical and Statistical Evidence
Unfortunately, formal statistical tests for analyzing the structure and heavy tails of stochastic gradients in deep learning are still under-explored.
Analysis of Error Feedback in Federated Non-Convex Optimization with Biased Compression
Moreover, we develop a new analysis of the EF under partial client participation, which is an important scenario in FL.
Degenerate Swin to Win: Plain Window-based Transformer without Sophisticated Operations
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.
R2-MLP: Round-Roll MLP for Multi-View 3D Object Recognition
Recently, vision architectures based exclusively on multi-layer perceptrons (MLPs) have gained much attention in the computer vision community.
On Penalization in Stochastic Multi-armed Bandits
We study an important variant of the stochastic multi-armed bandit (MAB) problem, which takes penalization into consideration.
Dual Multi-scale Mean Teacher Network for Semi-supervised Infection Segmentation in Chest CT Volume for COVID-19
Automated detecting lung infections from computed tomography (CT) data plays an important role for combating COVID-19.
Asymmetric Hashing for Fast Ranking via Neural Network Measures
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.
A pruning method based on the dissimilarity of angle among channels and filters
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.
Improving the Transferability of Adversarial Attacks on Face Recognition with Beneficial Perturbation Feature Augmentation
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.
Deep Latent Mixture Model for Recommendation
Recent advances in neural networks have been successfully applied to many tasks in online recommendation applications.
Constrained Approximate Similarity Search on Proximity Graph
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.
Prompting through Prototype: A Prototype-based Prompt Learning on Pretrained Vision-Language Models
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.
Denoising Enhanced Distantly Supervised Ultrafine Entity Typing
Specifically, we build a noise model to estimate the unknown labeling noise distribution over input contexts and noisy type labels.
Flow-based Perturbation for Cause-effect Inference
A new causal discovery method is introduced to solve the bivariate causal discovery problem.
Marksman Backdoor: Backdoor Attacks with Arbitrary Target Class
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.
Decomposing User-APP Graph into Subgraphs for Effective APP and User Embedding Learning
In this paper, we formulate the APP-installation user embedding learning into a bipartite graph embedding problem.
CoopHash: Cooperative Learning of Multipurpose Descriptor and Contrastive Pair Generator via Variational MCMC Teaching for Supervised Image Hashing
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
Pruning on neural networks before training not only compresses the original models, but also accelerates the network training phase, which has substantial application value.
FeatureBox: Feature Engineering on GPUs for Massive-Scale Ads Systems
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.
Boost CTR Prediction for New Advertisements via Modeling Visual Content
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.
Tree-based Text-Vision BERT for Video Search in Baidu Video Advertising
How to pair the video ads with the user search is the core task of Baidu video advertising.
NL2GDPR: Automatically Develop GDPR Compliant Android Application Features from Natural Language
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
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
Although the gain formula in Li (2010) was derived for logistic regression loss, it is a generic formula for loss functions with second-derivatives.
pGMM Kernel Regression and Comparisons with Boosted Trees
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
VFGs learn the representation of high dimensional data via a message-passing scheme by integrating flow-based functions through variational inference.
Best Subset Selection with Efficient Primal-Dual Algorithm
Best subset selection is considered the `gold standard' for many sparse learning problems.
$k$-Median Clustering via Metric Embedding: Towards Better Initialization with Differential Privacy
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
We first examine the vulnerability of ViTs against various backdoor attacks and find that ViTs are also quite vulnerable to existing attacks.
CGAR: Critic Guided Action Redistribution in Reinforcement Leaning
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.
Proximity Graph Maintenance for Fast Online Nearest Neighbor Search
Given a vertex deletion request, we thoroughly investigate solutions to update the connections of the vertex.
Noisy $\ell^{0}$-Sparse Subspace Clustering on Dimensionality Reduced Data
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
This article proposes a new method to estimate the world points and projection matrices from their correspondences.
On Convergence of FedProx: Local Dissimilarity Invariant Bounds, Non-smoothness and Beyond
The FedProx algorithm is a simple yet powerful distributed proximal point optimization method widely used for federated learning (FL) over heterogeneous data.
Boosting the Confidence of Generalization for $L_2$-Stable Randomized Learning Algorithms
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.
One Loss for Quantization: Deep Hashing with Discrete Wasserstein Distributional Matching
However, in the existing deep supervised hashing methods, coding balance and low-quantization error are difficult to achieve and involve several losses.
Revisiting the role of heterophily in graph representation learning: An edge classification perspective
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.
Fast ABC-Boost: A Unified Framework for Selecting the Base Class in Multi-Class Classification
Our framework has parameters $(s, g, w)$.
Dataset Pruning: Reducing Training Data by Examining Generalization Influence
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
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
We study COMP-AMS, a distributed optimization framework based on gradient averaging and adaptive AMSGrad algorithm.
Multi-view Geometry: Correspondences Refinement Based on Algebraic Properties
To our knowledge, there are no theoretical results for multi-view correspondences prior to this paper.
SpaceE: Knowledge Graph Embedding by Relational Linear Transformation in the Entity Space
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.
An Energy-Based Prior for Generative Saliency
With the generative saliency model, we can obtain a pixel-wise uncertainty map from an image, indicating model confidence in the saliency prediction.
A Class of Two-Timescale Stochastic EM Algorithms for Nonconvex Latent Variable Models
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
In this paper, we analyze the generalization performance of the Iterative Hard Thresholding (IHT) algorithm widely used for sparse recovery problems.
MISF: Multi-level Interactive Siamese Filtering for High-Fidelity Image Inpainting
As a result, the final method takes the advantage of effective semantic & image-level filling for high-fidelity inpainting.
Label-Smoothed Backdoor Attack
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.
BOAT: Bilateral Local Attention Vision Transformer
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
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
For example, one can apply GCWS on the outputs of the last layer to boost the accuracy of trained deep neural networks.
Communication-Efficient TeraByte-Scale Model Training Framework for Online Advertising
In this paper, we propose a hardware-aware training workflow that couples the hardware topology into the algorithm design.
Boosting RGB-D Saliency Detection by Leveraging Unlabeled RGB Images
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.
Learning Generative Vision Transformer with Energy-Based Latent Space for Saliency Prediction
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.
Causal Discovery with Flow-based Conditional Density Estimation
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.
Mitigating Forgetting in Online Continual Learning with Neuron Calibration
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.
Rate-Optimal Subspace Estimation on Random Graphs
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
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
The sparse generalized eigenvalue problem (SGEP) aims to find the leading eigenvector with sparsity structure.
Backdoor Attack with Imperceptible Input and Latent Modification
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.
C-OPH: Improving the Accuracy of One Permutation Hashing (OPH) with Circulant Permutations
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
Nevertheless, multi-view CNN models cannot model the communications between patches from different views, limiting its effectiveness in 3D object recognition.
Layer-wise and Dimension-wise Locally Adaptive Federated Learning
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.
Causal Discovery via Cholesky Factorization
Discovering the causal relationship via recovering the directed acyclic graph (DAG) structure from the observed data is a challenging combinatorial problem.
Boosting the Confidence of Near-Tight Generalization Bounds for Uniformly Stable Randomized Algorithms
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.
A new look at fairness in stochastic multi-armed bandit problems
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
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
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.
Constructing Orthogonal Convolutions in an Explicit Manner
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
In this paper, we work on a seamless marriage of imbalanced regression and self-supervised learning.
Practical Adversarial Training with Differential Privacy for Deep Learning
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
It is attracting attention to the long-tailed recognition problem, a burning issue that has become very popular recently.
Ranked #32 on
Long-tail Learning
on CIFAR-100-LT (ρ=100)
$f$-Divergence Thermodynamic Variational Objective: a Deformed Geometry Perspective
In this paper, we propose a $f$-divergence Thermodynamic Variational Objective ($f$-TVO).
Unsupervised Contrastive Learning for Signal-Dependent Noise Synthesis
We present a simple yet robust noise synthesis framework based on unsupervised contrastive learning.
Fairness-aware Federated Learning
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.
C-MinHash: Improving Minwise Hashing with Circulant Permutation
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
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
While adaptive gradient methods have been proven effective for training neural nets, the study of adaptive gradient methods in federated learning is scarce.
C-MinHash: Practically Reducing Two Permutations to Just One
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
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
Adaptive gradient methods including Adam, AdaGrad, and their variants have been very successful for training deep learning models, such as neural networks.
C-MinHash: Rigorously Reducing $K$ Permutations to Two
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
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
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
More recently, using smaller patches with a pyramid structure, Vision Permutator (ViP) and Global Filter Network (GFNet) achieve better performance than S$^2$-MLP.
Rethinking Token-Mixing MLP for MLP-based Vision Backbone
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.
A Systematic Collection of Medical Image Datasets for Deep Learning
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
In the application of Innovation Search for outlier detection, the directions of innovation were utilized to measure the innovation of the data points.
Learning Deep Latent Variable Models by Short-Run MCMC Inference With Optimal Transport Correction
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
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.
A Multi-Task Network for Joint Specular Highlight Detection and Removal
Specular highlight detection and removal are fundamental and challenging tasks.
S$^2$-MLP: Spatial-Shift MLP Architecture for Vision
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
Recent pretrained vision-language models have achieved impressive performance on cross-modal retrieval tasks in English.
Mitigating Forgetting in Online Continual Learning with Neuron Calibration
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.
High-quality Low-dose CT Reconstruction Using Convolutional Neural Networks with Spatial and Channel Squeeze and Excitation
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.
Quantization Algorithms for Random Fourier Features
Closely related to RP, the method of random Fourier features (RFF) has also become popular, for approximating the Gaussian kernel.
Simulation on the Transparency of Electrons and Ion Back Flow for a Time Projection Chamber based on Staggered Multiple THGEMs
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
Specifically, we propose a general algorithmic framework that can convert existing adaptive gradient methods to their decentralized counterparts.
Temporal Cue Guided Video Highlight Detection With Low-Rank Audio-Visual Fusion
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.
LIRA: Learnable, Imperceptible and Robust Backdoor Attacks
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.
Robust Watermarking for Deep Neural Networks via Bi-Level Optimization
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
Energy-based models (EBMs) for generative modeling parametrize a single net and can be directly trained by maximum likelihood estimation.
Cross-Probe BERT for Efficient and Effective Cross-Modal Search
Inspired by the great success of BERT in NLP tasks, many text-vision BERT models emerged recently.
MISSO: Minimization by Incremental Stochastic Surrogate Optimization for Large Scale Nonconvex and Nonsmooth Problems
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.
Learning Energy-Based Model with Variational Auto-Encoder as Amortized Sampler
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
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
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.
Optimal Prediction of the Number of Unseen Species with Multiplicity
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.
Thunder: a Fast Coordinate Selection Solver for Sparse Learning
L1 regularization has been broadly employed to pursue model sparsity.
Ratio Trace Formulation of Wasserstein Discriminant Analysis
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
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
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
In this paper, we propose to solve LRTC via tensor networks with a Tucker wrapper.
Exploring global diverse attention via pairwise temporal relation for video summarization
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.
A Framework of Randomized Selection Based Certified Defenses Against Data Poisoning Attacks
Random selection based defenses can achieve certified robustness by averaging the classifiers' predictions on the sub-datasets sampled from the training set.
Understanding and Detecting Convergence for Stochastic Gradient Descent with Momentum
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.
FedSKETCH: Communication-Efficient and Private Federated Learning via Sketching
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.
MeDaS: An open-source platform as service to help break the walls between medicine and informatics
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
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.
Cross-Lingual Unsupervised Sentiment Classification with Multi-View Transfer Learning
Recent neural network models have achieved impressive performance on sentiment classification in English as well as other languages.
Cooperative Rate-Splitting for Secrecy Sum-Rate Enhancement in Multi-antenna Broadcast Channels
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
The thriving of deep models and generative models provides approaches to model high dimensional distributions.
Randomized Kernel Multi-view Discriminant Analysis
In this paper, we propose the kernel version of multi-view discriminant analysis, called kernel multi-view discriminant analysis (KMvDA).
Distributed Primal-Dual Optimization for Online Multi-Task Learning
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.
IVFS: Simple and Efficient Feature Selection for High Dimensional Topology Preservation
Feature selection is an important tool to deal with high dimensional data.
Solving the Robust Matrix Completion Problem via a System of Nonlinear Equations
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 $M=L_*+S_*\in\mathbb{R}^{m\times n}$.
An Inverse-free Truncated Rayleigh-Ritz Method for Sparse Generalized Eigenvalue Problem
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
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
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.
Selective Convolutional Network: An Efficient Object Detector with Ignoring Background
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
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.
Outlier Detection and Data Clustering via Innovation Search
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.
Generalization Error Analysis of Quantized Compressive Learning
In this paper, we consider the learning problem where the projected data is further compressed by scalar quantization, which is called quantized compressive learning.
Outlier Detection and Robust PCA Using a Convex Measure of Innovation
In other word, an outlier carries some innovation with respect to most of the other data points.
Re-randomized Densification for One Permutation Hashing and Bin-wise Consistent Weighted Sampling
Jaccard similarity is widely used as a distance measure in many machine learning and search applications.
Towards Practical Alternating Least-Squares for CCA
To promote the practical use of ALS for CCA, we propose truly alternating least-squares.
Random Projections with Asymmetric Quantization
The method of random projection has been a popular tool for data compression, similarity search, and machine learning.
Möbius Transformation for Fast Inner Product Search on Graph
We present a fast search on graph algorithm for Maximum Inner Product Search (MIPS).
A Fourier Analytical Approach to Estimation of Smooth Functions in Gaussian Shift Model
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
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
Retrieval of relevant vectors produced by representation learning critically influences the efficiency in natural language processing (NLP) tasks.
Graph Analysis and Graph Pooling in the Spatial Domain
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.
Zeroth Order Optimization by a Mixture of Evolution Strategies
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
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
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.
On Convergence of Distributed Approximate Newton Methods: Globalization, Sharper Bounds and Beyond
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
A tacit assumption in linear regression is that (response, predictor)-pairs correspond to identical observational units.
End-to-end Deep Reinforcement Learning Based Coreference Resolution
Recent neural network models have significantly advanced the task of coreference resolution.
Ranked #13 on
Coreference Resolution
on CoNLL 2012
Integration of Knowledge Graph Embedding Into Topic Modeling with Hierarchical Dirichlet Process
Leveraging domain knowledge is an effective strategy for enhancing the quality of inferred low-dimensional representations of documents by topic models.
DEEP GEOMETRICAL GRAPH CLASSIFICATION
In the second step, the GNN is applied to the point-cloud representation of the graph provided by the embedding method.
On Random Deep Weight-Tied Autoencoders: Exact Asymptotic Analysis, Phase Transitions, and Implications to Training
We study the behavior of weight-tied multilayer vanilla autoencoders under the assumption of random weights.
Logician: A Unified End-to-End Neural Approach for Open-Domain Information Extraction
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.
Cycle-SUM: Cycle-consistent Adversarial LSTM Networks for Unsupervised Video Summarization
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.
Ranked #6 on
Unsupervised Video Summarization
on TvSum
An Optimistic Acceleration of AMSGrad for Nonconvex Optimization
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
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.
Logician and Orator: Learning from the Duality between Language and Knowledge in Open Domain
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.
Fast Binary Functional Search on Graph
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
As a remedy, online feature selection has attracted increasing attention in recent years.
Several Tunable GMM Kernels
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.
Sign-Full Random Projections
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
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
Random projections have been increasingly adopted for a diverse set of tasks in machine learning involving dimensionality reduction.
Image matting with normalized weight and semi-supervised learning
Image matting is an important vision problem.
On the Iteration Complexity of Support Recovery via Hard Thresholding Pursuit
Recovering the support of a sparse signal from its compressed samples has been one of the most important problems in high dimensional statistics.
L2GSCI: Local to Global Seam Cutting and Integrating for Accurate Face Contour Extraction
Current face alignment algorithms can robustly find a set of landmarks along face contour.
Tunable GMM Kernels
The linearized GMM kernel was extensively compared in with linearized radial basis function (RBF) kernel.
Generalized Intersection Kernel
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
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
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
Random projections constitute a simple, yet effective technique for dimensionality reduction with applications in learning and search problems.
Relational Multi-Manifold Co-Clustering
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.
Constrained Low-Rank Learning Using Least Squares-Based Regularization
To achieve this goal, we cast the problem into a constrained rank minimization framework by adopting the least squares regularization.