Search Results for author: Qiang Liu

Found 229 papers, 78 papers with code

Harmless Transfer Learning for Item Embeddings

no code implementations Findings (NAACL) 2022 Chengyue Gong, Xiaocong Du, Dhruv Choudhary, Bhargav Bhushanam, Qiang Liu, Arun Kejariwal

On the definition side, we reduce the bias in transfer loss by focusing on the items to which information from high-frequency items can be efficiently transferred.

Recommendation Systems Transfer Learning

Network Pruning by Greedy Subnetwork Selection

no code implementations ICML 2020 Mao Ye, Chengyue Gong, Lizhen Nie, Denny Zhou, Adam Klivans, Qiang Liu

Theoretically, we show that the small networks pruned using our method achieve provably lower loss than small networks trained from scratch with the same size.

Network Pruning

Accountable Off-Policy Evaluation via a Kernelized Bellman Statistics

no code implementations ICML 2020 Yihao Feng, Tongzheng Ren, Ziyang Tang, Qiang Liu

In this work, we investigate the statistical properties of the kernel loss, which allows us to find a feasible set that contains the true value function with high probability.

Off-policy evaluation

A Chance-Constrained Generative Framework for Sequence Optimization

no code implementations ICML 2020 Xianggen Liu, Jian Peng, Qiang Liu, Sen Song

Deep generative modeling has achieved many successes for continuous data generation, such as producing realistic images and controlling their properties (e. g., styles).

CvFormer: Cross-view transFormers with Pre-training for fMRI Analysis of Human Brain

no code implementations14 Sep 2023 Xiangzhu Meng, Qiang Liu, Shu Wu, Liang Wang

In recent years, functional magnetic resonance imaging (fMRI) has been widely utilized to diagnose neurological disease, by exploiting the region of interest (RoI) nodes as well as their connectivities in human brain.

Contrastive Learning

TiBGL: Template-induced Brain Graph Learning for Functional Neuroimaging Analysis

no code implementations14 Sep 2023 Xiangzhu Meng, Wei Wei, Qiang Liu, Shu Wu, Liang Wang

Motivated by the related medical findings on functional connectivites, TiBGL proposes template-induced brain graph learning to extract template brain graphs for all groups.

Graph Learning

InstaFlow: One Step is Enough for High-Quality Diffusion-Based Text-to-Image Generation

1 code implementation12 Sep 2023 Xingchao Liu, Xiwen Zhang, Jianzhu Ma, Jian Peng, Qiang Liu

Leveraging our new pipeline, we create, to the best of our knowledge, the first one-step diffusion-based text-to-image generator with SD-level image quality, achieving an FID (Frechet Inception Distance) of $23. 3$ on MS COCO 2017-5k, surpassing the previous state-of-the-art technique, progressive distillation, by a significant margin ($37. 2$ $\rightarrow$ $23. 3$ in FID).

Wasserstein Quantum Monte Carlo: A Novel Approach for Solving the Quantum Many-Body Schrödinger Equation

1 code implementation6 Jul 2023 Kirill Neklyudov, Jannes Nys, Luca Thiede, Juan Carrasquilla, Qiang Liu, Max Welling, Alireza Makhzani

One of the common computational approaches to this problem is Quantum Variational Monte Carlo (QVMC), in which ground-state solutions are obtained by minimizing the energy of the system within a restricted family of parameterized wave functions.

Variational Monte Carlo

Mining Stable Preferences: Adaptive Modality Decorrelation for Multimedia Recommendation

no code implementations25 Jun 2023 Jinghao Zhang, Qiang Liu, Shu Wu, Liang Wang

Even worse, the strong statistical correlation might mislead models to learn the spurious preference towards inconsequential modalities.

Inter-Cell Network Slicing With Transfer Learning Empowered Multi-Agent Deep Reinforcement Learning

no code implementations20 Jun 2023 Tianlun Hu, Qi Liao, Qiang Liu, Georg Carle

Network slicing enables operators to efficiently support diverse applications on a common physical infrastructure.

Transfer Learning

FAMO: Fast Adaptive Multitask Optimization

1 code implementation6 Jun 2023 Bo Liu, Yihao Feng, Peter Stone, Qiang Liu

One of the grand enduring goals of AI is to create generalist agents that can learn multiple different tasks from diverse data via multitask learning (MTL).

LIBERO: Benchmarking Knowledge Transfer for Lifelong Robot Learning

no code implementations5 Jun 2023 Bo Liu, Yifeng Zhu, Chongkai Gao, Yihao Feng, Qiang Liu, Yuke Zhu, Peter Stone

Specifically, LIBERO highlights five key research topics in LLDM: 1) how to efficiently transfer declarative knowledge, procedural knowledge, or the mixture of both; 2) how to design effective policy architectures and 3) effective algorithms for LLDM; 4) the robustness of a lifelong learner with respect to task ordering; and 5) the effect of model pretraining for LLDM.

Benchmarking Decision Making +2

Out-of-distribution Evidence-aware Fake News Detection via Dual Adversarial Debiasing

no code implementations25 Apr 2023 Qiang Liu, Junfei Wu, Shu Wu, Liang Wang

Then, DAL reversely optimizes news-aspect and evidence-aspect debiasing discriminators to mitigate the impact of news and evidence content biases.

Fake News Detection

LLM+P: Empowering Large Language Models with Optimal Planning Proficiency

1 code implementation22 Apr 2023 Bo Liu, Yuqian Jiang, Xiaohan Zhang, Qiang Liu, Shiqi Zhang, Joydeep Biswas, Peter Stone

LLM+P takes in a natural language description of a planning problem, then returns a correct (or optimal) plan for solving that problem in natural language.

Deep Stable Multi-Interest Learning for Out-of-distribution Sequential Recommendation

no code implementations12 Apr 2023 Qiang Liu, Zhaocheng Liu, Zhenxi Zhu, Shu Wu, Liang Wang

However, none of existing multi-interest recommendation models consider the Out-Of-Distribution (OOD) generalization problem, in which interest distribution may change.

Sequential Recommendation

Uncertainty Calibration for Counterfactual Propensity Estimation in Recommendation

no code implementations23 Mar 2023 WenBo Hu, Xin Sun, Qiang Liu, Shu Wu

In recommendation systems, a large portion of the ratings are missing due to the selection biases, which is known as Missing Not At Random.

Imputation Recommendation Systems

Efficient Transformer-based 3D Object Detection with Dynamic Token Halting

no code implementations9 Mar 2023 Mao Ye, Gregory P. Meyer, Yuning Chai, Qiang Liu

Although halting a token is a non-differentiable operation, our method allows for differentiable end-to-end learning by leveraging an equivalent differentiable forward-pass.

3D Object Detection Autonomous Vehicles +1

MetaTKG: Learning Evolutionary Meta-Knowledge for Temporal Knowledge Graph Reasoning

no code implementations2 Feb 2023 Yuwei Xia, Mengqi Zhang, Qiang Liu, Shu Wu, Xiao-Yu Zhang

Most existing works focus on exploring evolutionary information in history to obtain effective temporal embeddings for entities and relations, but they ignore the variation in evolution patterns of facts, which makes them struggle to adapt to future data with different evolution patterns.

Knowledge Graphs Meta-Learning

Metamobility: Connecting Future Mobility with Metaverse

no code implementations17 Jan 2023 Haoxin Wang, Ziran Wang, Dawei Chen, Qiang Liu, Hongyu Ke, Kyungtae Han

A Metaverse is a perpetual, immersive, and shared digital universe that is linked to but beyond the physical reality, and this emerging technology is attracting enormous attention from different industries.

Network Slicing via Transfer Learning aided Distributed Deep Reinforcement Learning

no code implementations9 Jan 2023 Tianlun Hu, Qi Liao, Qiang Liu, Georg Carle

In this paper, we propose a novel transfer learning (TL) aided multi-agent deep reinforcement learning (MADRL) approach with inter-agent similarity analysis for inter-cell inter-slice resource partitioning.

Management reinforcement-learning +2

Sparsely Annotated Semantic Segmentation With Adaptive Gaussian Mixtures

1 code implementation CVPR 2023 Linshan Wu, Zhun Zhong, Leyuan Fang, Xingxin He, Qiang Liu, Jiayi Ma, Hao Chen

Our AGMM can effectively endow reliable supervision for unlabeled pixels based on the distributions of labeled and unlabeled pixels.

Contrastive Learning Semantic Segmentation

FlowGrad: Controlling the Output of Generative ODEs With Gradients

no code implementations CVPR 2023 Xingchao Liu, Lemeng Wu, Shujian Zhang, Chengyue Gong, Wei Ping, Qiang Liu

To further accelerate the computation of the back-propagation, we propose to use a non-uniform discretization to approximate the ODE trajectory, where we measure how straight the trajectory is and gather the straight parts into one discretization step.

Image Manipulation

Planning-oriented Autonomous Driving

1 code implementation CVPR 2023 Yihan Hu, Jiazhi Yang, Li Chen, Keyu Li, Chonghao Sima, Xizhou Zhu, Siqi Chai, Senyao Du, Tianwei Lin, Wenhai Wang, Lewei Lu, Xiaosong Jia, Qiang Liu, Jifeng Dai, Yu Qiao, Hongyang Li

Oriented at this, we revisit the key components within perception and prediction, and prioritize the tasks such that all these tasks contribute to planning.

Autonomous Driving Philosophy

PathFusion: Path-consistent Lidar-Camera Deep Feature Fusion

no code implementations12 Dec 2022 Lemeng Wu, Dilin Wang, Meng Li, Yunyang Xiong, Raghuraman Krishnamoorthi, Qiang Liu, Vikas Chandra

PathFusion introduces a path consistency loss between shallow and deep features, which encourages the 2D backbone and its fusion path to transform 2D features in a way that is semantically aligned with the transform of the 3D backbone.

Fast Point Cloud Generation with Straight Flows

1 code implementation CVPR 2023 Lemeng Wu, Dilin Wang, Chengyue Gong, Xingchao Liu, Yunyang Xiong, Rakesh Ranjan, Raghuraman Krishnamoorthi, Vikas Chandra, Qiang Liu

We perform evaluations on multiple 3D tasks and find that our PSF performs comparably to the standard diffusion model, outperforming other efficient 3D point cloud generation methods.

Point Cloud Completion

Distributed Node Covering Optimization for Large Scale Networks and Its Application on Social Advertising

no code implementations16 Nov 2022 Qiang Liu

Combinatorial optimizations are usually complex and inefficient, which limits their applications in large-scale networks with billions of links.

Efficient and Accurate Quantized Image Super-Resolution on Mobile NPUs, Mobile AI & AIM 2022 challenge: Report

2 code implementations7 Nov 2022 Andrey Ignatov, Radu Timofte, Maurizio Denna, Abdel Younes, Ganzorig Gankhuyag, Jingang Huh, Myeong Kyun Kim, Kihwan Yoon, Hyeon-Cheol Moon, Seungho Lee, Yoonsik Choe, Jinwoo Jeong, Sungjei Kim, Maciej Smyl, Tomasz Latkowski, Pawel Kubik, Michal Sokolski, Yujie Ma, Jiahao Chao, Zhou Zhou, Hongfan Gao, Zhengfeng Yang, Zhenbing Zeng, Zhengyang Zhuge, Chenghua Li, Dan Zhu, Mengdi Sun, Ran Duan, Yan Gao, Lingshun Kong, Long Sun, Xiang Li, Xingdong Zhang, Jiawei Zhang, Yaqi Wu, Jinshan Pan, Gaocheng Yu, Jin Zhang, Feng Zhang, Zhe Ma, Hongbin Wang, Hojin Cho, Steve Kim, Huaen Li, Yanbo Ma, Ziwei Luo, Youwei Li, Lei Yu, Zhihong Wen, Qi Wu, Haoqiang Fan, Shuaicheng Liu, Lize Zhang, Zhikai Zong, Jeremy Kwon, Junxi Zhang, Mengyuan Li, Nianxiang Fu, Guanchen Ding, Han Zhu, Zhenzhong Chen, Gen Li, Yuanfan Zhang, Lei Sun, Dafeng Zhang, Neo Yang, Fitz Liu, Jerry Zhao, Mustafa Ayazoglu, Bahri Batuhan Bilecen, Shota Hirose, Kasidis Arunruangsirilert, Luo Ao, Ho Chun Leung, Andrew Wei, Jie Liu, Qiang Liu, Dahai Yu, Ao Li, Lei Luo, Ce Zhu, Seongmin Hong, Dongwon Park, Joonhee Lee, Byeong Hyun Lee, Seunggyu Lee, Se Young Chun, Ruiyuan He, Xuhao Jiang, Haihang Ruan, Xinjian Zhang, Jing Liu, Garas Gendy, Nabil Sabor, Jingchao Hou, Guanghui He

While numerous solutions have been proposed for this problem in the past, they are usually not compatible with low-power mobile NPUs having many computational and memory constraints.

Image Super-Resolution

Atlas: Automate Online Service Configuration in Network Slicing

1 code implementation30 Oct 2022 Qiang Liu, Nakjung Choi, Tao Han

First, we design a learning-based simulator to reduce the sim-to-real discrepancy, which is accomplished by a new parameter searching method based on Bayesian optimization.

Bayesian Optimization Safe Exploration +1

Sampling with Mollified Interaction Energy Descent

1 code implementation24 Oct 2022 Lingxiao Li, Qiang Liu, Anna Korba, Mikhail Yurochkin, Justin Solomon

These energies rely on mollifier functions -- smooth approximations of the Dirac delta originated from PDE theory.

The Devil is in the Conflict: Disentangled Information Graph Neural Networks for Fraud Detection

no code implementations22 Oct 2022 ZHIXUN LI, Dingshuo Chen, Qiang Liu, Shu Wu

In this paper, we argue that the performance degradation is mainly attributed to the inconsistency between topology and attribute.

Fraud Detection Inductive Bias

Sampling in Constrained Domains with Orthogonal-Space Variational Gradient Descent

1 code implementation12 Oct 2022 Ruqi Zhang, Qiang Liu, Xin T. Tong

Sampling methods, as important inference and learning techniques, are typically designed for unconstrained domains.


Adversarial Contrastive Learning for Evidence-aware Fake News Detection with Graph Neural Networks

1 code implementation11 Oct 2022 Junfei Wu, Weizhi Xu, Qiang Liu, Shu Wu, Liang Wang

Comprehensive experiments have demonstrated the superiority of GETRAL over the state-of-the-arts and validated the efficacy of semantic mining with graph structure and contrastive learning.

Contrastive Learning Fake News Detection +2

Neural Volumetric Mesh Generator

no code implementations6 Oct 2022 Yan Zheng, Lemeng Wu, Xingchao Liu, Zhen Chen, Qiang Liu, QiXing Huang

We first propose a diffusion-based generative model to tackle this problem by generating voxelized shapes with close-to-reality outlines and structures.

Rectified Flow: A Marginal Preserving Approach to Optimal Transport

1 code implementation29 Sep 2022 Qiang Liu

We present a flow-based approach to the optimal transport (OT) problem between two continuous distributions $\pi_0,\pi_1$ on $\mathbb{R}^d$, of minimizing a transport cost $\mathbb{E}[c(X_1-X_0)]$ in the set of couplings $(X_0, X_1)$ whose marginal distributions on $X_0, X_1$ equals $\pi_0,\pi_1$, respectively, where $c$ is a cost function.

Improving Molecular Pretraining with Complementary Featurizations

no code implementations29 Sep 2022 Yanqiao Zhu, Dingshuo Chen, Yuanqi Du, Yingze Wang, Qiang Liu, Shu Wu

Molecular pretraining, which learns molecular representations over massive unlabeled data, has become a prominent paradigm to solve a variety of tasks in computational chemistry and drug discovery.

Drug Discovery Molecular Property Prediction +1

BOME! Bilevel Optimization Made Easy: A Simple First-Order Approach

no code implementations19 Sep 2022 Mao Ye, Bo Liu, Stephen Wright, Peter Stone, Qiang Liu

Bilevel optimization (BO) is useful for solving a variety of important machine learning problems including but not limited to hyperparameter optimization, meta-learning, continual learning, and reinforcement learning.

Bilevel Optimization Continual Learning +3

Flow Straight and Fast: Learning to Generate and Transfer Data with Rectified Flow

2 code implementations7 Sep 2022 Xingchao Liu, Chengyue Gong, Qiang Liu

The idea of rectified flow is to learn the ODE to follow the straight paths connecting the points drawn from \pi_0 and \pi_1 as much as possible.

Domain Adaptation Image-to-Image Translation +1

Deep Stable Representation Learning on Electronic Health Records

1 code implementation3 Sep 2022 Yingtao Luo, Zhaocheng Liu, Qiang Liu

The unstable correlation between procedures and diagnoses existed in the training distribution can cause spurious correlation between historical EHR and future diagnosis.

Disease Prediction Representation Learning

Future Gradient Descent for Adapting the Temporal Shifting Data Distribution in Online Recommendation Systems

no code implementations2 Sep 2022 Mao Ye, Ruichen Jiang, Haoxiang Wang, Dhruv Choudhary, Xiaocong Du, Bhargav Bhushanam, Aryan Mokhtari, Arun Kejariwal, Qiang Liu

One of the key challenges of learning an online recommendation model is the temporal domain shift, which causes the mismatch between the training and testing data distribution and hence domain generalization error.

Domain Generalization Recommendation Systems

Diffusion-based Molecule Generation with Informative Prior Bridges

no code implementations2 Sep 2022 Lemeng Wu, Chengyue Gong, Xingchao Liu, Mao Ye, Qiang Liu

AI-based molecule generation provides a promising approach to a large area of biomedical sciences and engineering, such as antibody design, hydrolase engineering, or vaccine development.

Point Cloud Generation

First Hitting Diffusion Models for Generating Manifold, Graph and Categorical Data

no code implementations2 Sep 2022 Mao Ye, Lemeng Wu, Qiang Liu

We propose a family of First Hitting Diffusion Models (FHDM), deep generative models that generate data with a diffusion process that terminates at a random first hitting time.

Let us Build Bridges: Understanding and Extending Diffusion Generative Models

no code implementations31 Aug 2022 Xingchao Liu, Lemeng Wu, Mao Ye, Qiang Liu

Diffusion-based generative models have achieved promising results recently, but raise an array of open questions in terms of conceptual understanding, theoretical analysis, algorithm improvement and extensions to discrete, structured, non-Euclidean domains.


Metric Residual Networks for Sample Efficient Goal-Conditioned Reinforcement Learning

2 code implementations17 Aug 2022 Bo Liu, Yihao Feng, Qiang Liu, Peter Stone

Furthermore, we introduce the metric residual network (MRN) that deliberately decomposes the action-value function Q(s, a, g) into the negated summation of a metric plus a residual asymmetric component.

reinforcement-learning Reinforcement Learning (RL)

Improving Multi-Interest Network with Stable Learning

no code implementations14 Jul 2022 Zhaocheng Liu, Yingtao Luo, Di Zeng, Qiang Liu, Daqing Chang, Dongying Kong, Zhi Chen

Modeling users' dynamic preferences from historical behaviors lies at the core of modern recommender systems.

Recommendation Systems

Network Pruning via Feature Shift Minimization

1 code implementation6 Jul 2022 Yuanzhi Duan, Yue Zhou, Peng He, Qiang Liu, Shukai Duan, Xiaofang Hu

In this paper, we propose a novel Feature Shift Minimization (FSM) method to compress CNN models, which evaluates the feature shift by converging the information of both features and filters.

Network Pruning

Split Localized Conformal Prediction

1 code implementation27 Jun 2022 Xing Han, Ziyang Tang, Joydeep Ghosh, Qiang Liu

The modified score inherits the spirit of split conformal methods, which is simple and efficient and can scale to high dimensional settings.

Conformal Prediction Density Estimation +2

HOPE: Hierarchical Spatial-temporal Network for Occupancy Flow Prediction

no code implementations21 Jun 2022 Yihan Hu, Wenxin Shao, Bo Jiang, Jiajie Chen, Siqi Chai, Zhening Yang, Jingyu Qian, Helong Zhou, Qiang Liu

In this report, we introduce our solution to the Occupancy and Flow Prediction challenge in the Waymo Open Dataset Challenges at CVPR 2022, which ranks 1st on the leaderboard.

A Langevin-like Sampler for Discrete Distributions

1 code implementation20 Jun 2022 Ruqi Zhang, Xingchao Liu, Qiang Liu

We propose discrete Langevin proposal (DLP), a simple and scalable gradient-based proposal for sampling complex high-dimensional discrete distributions.

Efficient Exploration Text Generation

CAINNFlow: Convolutional block Attention modules and Invertible Neural Networks Flow for anomaly detection and localization tasks

no code implementations4 Jun 2022 Ruiqing Yan, Fan Zhang, Mengyuan Huang, Wu Liu, Dongyu Hu, Jinfeng Li, Qiang Liu, Jinrong Jiang, Qianjin Guo, Linghan Zheng

Detection of object anomalies is crucial in industrial processes, but unsupervised anomaly detection and localization is particularly important due to the difficulty of obtaining a large number of defective samples and the unpredictable types of anomalies in real life.

Unsupervised Anomaly Detection

Estimating spot volatility under infinite variation jumps with dependent market microstructure noise

no code implementations31 May 2022 Qiang Liu, Zhi Liu

Jumps and market microstructure noise are stylized features of high-frequency financial data.

Continual Learning and Private Unlearning

1 code implementation24 Mar 2022 Bo Liu, Qiang Liu, Peter Stone

As intelligent agents become autonomous over longer periods of time, they may eventually become lifelong counterparts to specific people.

Continual Learning

WCL-BBCD: A Contrastive Learning and Knowledge Graph Approach to Named Entity Recognition

no code implementations14 Mar 2022 Renjie Zhou, Qiang Hu, Jian Wan, Jilin Zhang, Qiang Liu, Tianxiang Hu, Jianjun Li

The model first trains the sentence pairs in the text, calculate similarity between sentence pairs, and fine-tunes BERT used for the named entity recognition task according to the similarity, so as to alleviate word ambiguity.

Contrastive Learning Knowledge Graphs +3

A Survey on Deep Graph Generation: Methods and Applications

no code implementations13 Mar 2022 Yanqiao Zhu, Yuanqi Du, Yinkai Wang, Yichen Xu, Jieyu Zhang, Qiang Liu, Shu Wu

In this paper, we conduct a comprehensive review on the existing literature of deep graph generation from a variety of emerging methods to its wide application areas.

Graph Generation Graph Learning

A Dual Neighborhood Hypergraph Neural Network for Change Detection in VHR Remote Sensing Images

no code implementations27 Feb 2022 Junzheng Wu, Ruigang Fu, Qiang Liu, Weiping Ni, Kenan Cheng, Biao Li, Yuli Sun

To address this limitation, a dual neighborhood hypergraph neural network is proposed in this article, which combines the multiscale superpixel segmentation and hypergraph convolution to model and exploit the complex relationships.

Change Detection

How to Fill the Optimum Set? Population Gradient Descent with Harmless Diversity

no code implementations16 Feb 2022 Chengyue Gong, Lemeng Wu, Qiang Liu

Although traditional optimization methods focus on finding a single optimal solution, most objective functions in modern machine learning problems, especially those in deep learning, often have multiple or infinite numbers of optima.

EdgeMap: CrowdSourcing High Definition Map in Automotive Edge Computing

no code implementations20 Jan 2022 Qiang Liu, Yuru Zhang, Haoxin Wang

High definition (HD) map needs to be updated frequently to capture road changes, which is constrained by limited specialized collection vehicles.

Edge-computing Vocal Bursts Intensity Prediction

Evidence-aware Fake News Detection with Graph Neural Networks

1 code implementation18 Jan 2022 Weizhi Xu, Junfei Wu, Qiang Liu, Shu Wu, Liang Wang

In this paper, we focus on the evidence-based fake news detection, where several evidences are utilized to probe the veracity of news (i. e., a claim).

Fake News Detection Graph structure learning

Operator Deep Q-Learning: Zero-Shot Reward Transferring in Reinforcement Learning

no code implementations1 Jan 2022 Ziyang Tang, Yihao Feng, Qiang Liu

The benefit of learning the operator is that we can incorporate any new reward function as input and attain its corresponding value function in a zero-shot manner.

Q-Learning reinforcement-learning +1

Are we really making much progress? Revisiting, benchmarking, and refining heterogeneous graph neural networks

1 code implementation30 Dec 2021 Qingsong Lv, Ming Ding, Qiang Liu, Yuxiang Chen, Wenzheng Feng, Siming He, Chang Zhou, Jianguo Jiang, Yuxiao Dong, Jie Tang

Heterogeneous graph neural networks (HGNNs) have been blossoming in recent years, but the unique data processing and evaluation setups used by each work obstruct a full understanding of their advancements.


Network Compression via Central Filter

1 code implementation10 Dec 2021 Yuanzhi Duan, Xiaofang Hu, Yue Zhou, Qiang Liu, Shukai Duan

In this paper, by exploring the similarities between feature maps, we propose a novel filter pruning method, Central Filter (CF), which suggests that a filter is approximately equal to a set of other filters after appropriate adjustments.

Network Pruning

FuseDream: Training-Free Text-to-Image Generation with Improved CLIP+GAN Space Optimization

1 code implementation2 Dec 2021 Xingchao Liu, Chengyue Gong, Lemeng Wu, Shujian Zhang, Hao Su, Qiang Liu

We approach text-to-image generation by combining the power of the retrained CLIP representation with an off-the-shelf image generator (GANs), optimizing in the latent space of GAN to find images that achieve maximum CLIP score with the given input text.

Navigate Zero-Shot Text-to-Image Generation

Profiling Pareto Front With Multi-Objective Stein Variational Gradient Descent

1 code implementation NeurIPS 2021 Xingchao Liu, Xin Tong, Qiang Liu

Finding diverse and representative Pareto solutions from the Pareto front is a key challenge in multi-objective optimization (MOO).

Automatic and Harmless Regularization with Constrained and Lexicographic Optimization: A Dynamic Barrier Approach

no code implementations NeurIPS 2021 Chengyue Gong, Xingchao Liu, Qiang Liu

In this work, we consider constrained optimization as a more principled approach for trading off two losses, with a special emphasis on lexicographic optimization, a degenerated limit of constrained optimization which optimizes a secondary loss inside the optimal set of the main loss.

Sampling with Trusthworthy Constraints: A Variational Gradient Framework

1 code implementation NeurIPS 2021 Xingchao Liu, Xin Tong, Qiang Liu

In this work, we propose a family of constrained sampling algorithms which generalize Langevin Dynamics (LD) and Stein Variational Gradient Descent (SVGD) to incorporate a moment constraint specified by a general nonlinear function.

Bayesian Inference Fairness

argmax centroid

no code implementations NeurIPS 2021 Chengyue Gong, Mao Ye, Qiang Liu

We propose a general method to construct centroid approximation for the distribution of maximum points of a random function (a. k. a.

Domain Adaptation Few-Shot Image Classification +2

VLMo: Unified Vision-Language Pre-Training with Mixture-of-Modality-Experts

2 code implementations3 Nov 2021 Hangbo Bao, Wenhui Wang, Li Dong, Qiang Liu, Owais Khan Mohammed, Kriti Aggarwal, Subhojit Som, Furu Wei

We present a unified Vision-Language pretrained Model (VLMo) that jointly learns a dual encoder and a fusion encoder with a modular Transformer network.

Image Retrieval Retrieval +3

OnSlicing: Online End-to-End Network Slicing with Reinforcement Learning

no code implementations2 Nov 2021 Qiang Liu, Nakjung Choi, Tao Han

As online learning is converged, OnSlicing reduces 12. 5% usage without any violations as compared to the state-of-the-art online DRL solution.

reinforcement-learning Reinforcement Learning (RL)

Latent Structure Mining with Contrastive Modality Fusion for Multimedia Recommendation

1 code implementation1 Nov 2021 Jinghao Zhang, Yanqiao Zhu, Qiang Liu, Mengqi Zhang, Shu Wu, Liang Wang

Although having access to multiple modalities might allow us to capture rich information, we argue that the simple coarse-grained fusion by linear combination or concatenation in previous work is insufficient to fully understand content information and item relationships. To this end, we propose a latent structure MIning with ContRastive mOdality fusion method (MICRO for brevity).

Collaborative Filtering

Conflict-Averse Gradient Descent for Multi-task Learning

3 code implementations NeurIPS 2021 Bo Liu, Xingchao Liu, Xiaojie Jin, Peter Stone, Qiang Liu

The goal of multi-task learning is to enable more efficient learning than single task learning by sharing model structures for a diverse set of tasks.

Multi-Task Learning

Pareto Navigation Gradient Descent: a First-Order Algorithm for Optimization in Pareto Set

no code implementations17 Oct 2021 Mao Ye, Qiang Liu

The notion of the Pareto set allows us to focus on the set of (often infinite number of) models that cannot be strictly improved.

Multi-Task Learning

Centroid Approximation for Bootstrap: Improving Particle Quality at Inference

no code implementations17 Oct 2021 Mao Ye, Qiang Liu

In this work, we propose an efficient method to explicitly \emph{optimize} a small set of high quality ``centroid'' points to better approximate the ideal bootstrap distribution.

Exciting-Inhibition Network for Person Reidentification in Internet of Things

no code implementations IEEE Internet of Things Journal 2021 Meixia Fu, Songlin Sun, Qilian Liang, Xiaoyun Tong, Qiang Liu

Index Terms—Channel-spatial attention block (CSAB), exciting-inhibition network (EINet), Internet of Things (IoT), person reidentification (re-ID), soft batch dropblock.

Person Re-Identification

Relation-aware Heterogeneous Graph for User Profiling

1 code implementation14 Oct 2021 Qilong Yan, Yufeng Zhang, Qiang Liu, Shu Wu, Liang Wang

User profiling has long been an important problem that investigates user interests in many real applications.

Node Classification

Speeding up Deep Model Training by Sharing Weights and Then Unsharing

no code implementations8 Oct 2021 Shuo Yang, Le Hou, Xiaodan Song, Qiang Liu, Denny Zhou

Our approach exploits the special structure of BERT that contains a stack of repeated modules (i. e., transformer encoders).

NASViT: Neural Architecture Search for Efficient Vision Transformers with Gradient Conflict aware Supernet Training

1 code implementation ICLR 2022 Chengyue Gong, Dilin Wang, Meng Li, Xinlei Chen, Zhicheng Yan, Yuandong Tian, Qiang Liu, Vikas Chandra

In this work, we observe that the poor performance is due to a gradient conflict issue: the gradients of different sub-networks conflict with that of the supernet more severely in ViTs than CNNs, which leads to early saturation in training and inferior convergence.

Data Augmentation Image Classification +2

Neural Energy Minimization for Molecular Conformation Optimization

no code implementations ICLR 2022 Jiaqi Guan, Wesley Wei Qian, Qiang Liu, Wei-Ying Ma, Jianzhu Ma, Jian Peng

Assuming different forms of the underlying potential energy function, we can not only reinterpret and unify many of the existing models but also derive new variants of SE(3)-equivariant neural networks in a principled manner.

Pareto Navigation Gradient Descent: a First Order Algorithm for Optimization in Pareto Set

no code implementations29 Sep 2021 Mao Ye, Qiang Liu

The notion of the Pareto set allows us to focus on the set of (often infinite number of) models that cannot be strictly improved.

Multi-Task Learning

An Empirical Study of Graph Contrastive Learning

2 code implementations2 Sep 2021 Yanqiao Zhu, Yichen Xu, Qiang Liu, Shu Wu

We envision this work to provide useful empirical evidence of effective GCL algorithms and offer several insights for future research.

Graph Classification Management +1

Structure-Aware Hard Negative Mining for Heterogeneous Graph Contrastive Learning

no code implementations31 Aug 2021 Yanqiao Zhu, Yichen Xu, Hejie Cui, Carl Yang, Qiang Liu, Shu Wu

Recently, heterogeneous Graph Neural Networks (GNNs) have become a de facto model for analyzing HGs, while most of them rely on a relative large number of labeled data.

Contrastive Learning

Deep Contrastive Multiview Network Embedding

no code implementations16 Aug 2021 Mengqi Zhang, Yanqiao Zhu, Qiang Liu, Shu Wu, Liang Wang

In our work, different views can be obtained based on the various relations among nodes.

Contrastive Learning Graph Embedding +1

Deep Active Learning for Text Classification with Diverse Interpretations

no code implementations15 Aug 2021 Qiang Liu, Yanqiao Zhu, Zhaocheng Liu, Yufeng Zhang, Shu Wu

To train high-performing models with the minimal annotation cost, active learning is proposed to select and label the most informative samples, yet it is still challenging to measure informativeness of samples used in DNNs.

Active Learning Informativeness +2

Real-Time Anchor-Free Single-Stage 3D Detection with IoU-Awareness

no code implementations29 Jul 2021 Runzhou Ge, Zhuangzhuang Ding, Yihan Hu, Wenxin Shao, Li Huang, Kun Li, Qiang Liu

Extended from our last year's award-winning model AFDet, we have made a handful of modifications to the base model, to improve the accuracy and at the same time to greatly reduce the latency.

Data Augmentation

The Deep Neural Network based Photometry and Astrometry Framework for Wide Field Small Aperture Telescopes

no code implementations28 Jun 2021 Peng Jia, Yongyang Sun, Zhimin Yang, Rui Sun, Qiang Liu

Wide field small aperture telescopes (WFSATs) are preferable observation instruments for time domain astronomy, because they could obtain images of celestial objects with high cadence in a cost-effective way.

Astronomy regression +1

MaxUp: Lightweight Adversarial Training With Data Augmentation Improves Neural Network Training

no code implementations CVPR 2021 Chengyue Gong, Tongzheng Ren, Mao Ye, Qiang Liu

The idea is to generate a set of augmented data with some random perturbations or transforms, and minimize the maximum, or worst case loss over the augmented data.

Data Augmentation Image Classification +1

Any equation is a forest: Symbolic genetic algorithm for discovering open-form partial differential equations (SGA-PDE)

2 code implementations9 Jun 2021 Yuntian Chen, Yingtao Luo, Qiang Liu, Hao Xu, Dongxiao Zhang

Partial differential equations (PDEs) are concise and understandable representations of domain knowledge, which are essential for deepening our understanding of physical processes and predicting future responses.

Physics-Guided Discovery of Highly Nonlinear Parametric Partial Differential Equations

no code implementations2 Jun 2021 Yingtao Luo, Qiang Liu, Yuntian Chen, WenBo Hu, Tian Tian, Jun Zhu

Especially, the discovery of PDEs with highly nonlinear coefficients from low-quality data remains largely under-addressed.

Density Estimation Model Optimization

Automatic and Harmless Regularization with Constrained and Lexicographic Optimization: A Dynamic Barrier Approach

no code implementations NeurIPS 2021 Chengyue Gong, Xingchao Liu, Qiang Liu

In this work, we consider constrained optimization as a more principled approach for trading off two losses, with a special emphasis on lexicographic optimization, a degenerated limit of constrained optimization which optimizes a secondary loss inside the optimal set of the main loss.

Profiling Pareto Front With Multi-Objective Stein Variational Gradient Descent

1 code implementation NeurIPS 2021 Xingchao Liu, Xin Tong, Qiang Liu

Finding diverse and representative Pareto solutions from the Pareto front is a key challenge in multi-objective optimization (MOO).

Sampling with Trusthworthy Constraints: A Variational Gradient Framework

1 code implementation NeurIPS 2021 Xingchao Liu, Xin Tong, Qiang Liu

In this work, we propose a family of constrained sampling algorithms which generalize Langevin Dynamics (LD) and Stein Variational Gradient Descent (SVGD) to incorporate a moment constraint specified by a general nonlinear function.

Bayesian Inference Fairness

Coach-Player Multi-Agent Reinforcement Learning for Dynamic Team Composition

1 code implementation18 May 2021 Bo Liu, Qiang Liu, Peter Stone, Animesh Garg, Yuke Zhu, Animashree Anandkumar

Specifically, we 1) adopt the attention mechanism for both the coach and the players; 2) propose a variational objective to regularize learning; and 3) design an adaptive communication method to let the coach decide when to communicate with the players.

Multi-agent Reinforcement Learning reinforcement-learning +2

Vision Transformers with Patch Diversification

1 code implementation26 Apr 2021 Chengyue Gong, Dilin Wang, Meng Li, Vikas Chandra, Qiang Liu

To alleviate this problem, in this work, we introduce novel loss functions in vision transformer training to explicitly encourage diversity across patch representations for more discriminative feature extraction.

Image Classification Semantic Segmentation

Mining Latent Structures for Multimedia Recommendation

1 code implementation19 Apr 2021 Jinghao Zhang, Yanqiao Zhu, Qiang Liu, Shu Wu, Shuhui Wang, Liang Wang

To be specific, in the proposed LATTICE model, we devise a novel modality-aware structure learning layer, which learns item-item structures for each modality and aggregates multiple modalities to obtain latent item graphs.

Collaborative Filtering Recommendation Systems

Dynamic Graph Neural Networks for Sequential Recommendation

1 code implementation15 Apr 2021 Mengqi Zhang, Shu Wu, Xueli Yu, Qiang Liu, Liang Wang

We propose a new method named Dynamic Graph Neural Network for Sequential Recommendation (DGSR), which connects different user sequences through a dynamic graph structure, exploring the interactive behavior of users and items with time and order information.

Graph Attention Link Prediction +1

DyGCN: Dynamic Graph Embedding with Graph Convolutional Network

no code implementations7 Apr 2021 Zeyu Cui, Zekun Li, Shu Wu, XiaoYu Zhang, Qiang Liu, Liang Wang, Mengmeng Ai

We naturally generalizes the embedding propagation scheme of GCN to dynamic setting in an efficient manner, which is to propagate the change along the graph to update node embeddings.

Dynamic graph embedding

VCNet and Functional Targeted Regularization For Learning Causal Effects of Continuous Treatments

1 code implementation14 Mar 2021 Lizhen Nie, Mao Ye, Qiang Liu, Dan Nicolae

Motivated by the rising abundance of observational data with continuous treatments, we investigate the problem of estimating the average dose-response curve (ADRF).

Non-asymptotic Confidence Intervals of Off-policy Evaluation: Primal and Dual Bounds

no code implementations ICLR 2021 Yihao Feng, Ziyang Tang, Na Zhang, Qiang Liu

Off-policy evaluation (OPE) is the task of estimating the expected reward of a given policy based on offline data previously collected under different policies.

Off-policy evaluation Open-Ended Question Answering

A Survey on Graph Structure Learning: Progress and Opportunities

no code implementations4 Mar 2021 Yanqiao Zhu, Weizhi Xu, Jinghao Zhang, Yuanqi Du, Jieyu Zhang, Qiang Liu, Carl Yang, Shu Wu

Specifically, we first formulate a general pipeline of GSL and review state-of-the-art methods classified by the way of modeling graph structures, followed by applications of GSL across domains.

Graph structure learning

DNN2LR: Automatic Feature Crossing for Credit Scoring

no code implementations24 Feb 2021 Qiang Liu, Zhaocheng Liu, Haoli Zhang, Yuntian Chen, Jun Zhu

Accordingly, we can design an automatic feature crossing method to find feature interactions in DNN, and use them as cross features in LR.

Feature Engineering

Firefly Neural Architecture Descent: a General Approach for Growing Neural Networks

1 code implementation NeurIPS 2020 Lemeng Wu, Bo Liu, Peter Stone, Qiang Liu

We propose firefly neural architecture descent, a general framework for progressively and dynamically growing neural networks to jointly optimize the networks' parameters and architectures.

Continual Learning Image Classification +1

Centroid Transformers: Learning to Abstract with Attention

no code implementations17 Feb 2021 Lemeng Wu, Xingchao Liu, Qiang Liu

Self-attention, as the key block of transformers, is a powerful mechanism for extracting features from the inputs.

Abstractive Text Summarization Clustering +1

AlphaNet: Improved Training of Supernets with Alpha-Divergence

2 code implementations16 Feb 2021 Dilin Wang, Chengyue Gong, Meng Li, Qiang Liu, Vikas Chandra

Weight-sharing NAS builds a supernet that assembles all the architectures as its sub-networks and jointly trains the supernet with the sub-networks.

Image Classification Neural Architecture Search

Coherent ray-wave structured light based on (helical) Ince-Gaussian modes

no code implementations4 Feb 2021 Zhaoyang Wang, Yijie Shen, Qiang Liu, Xing Fu

The topological evolution of classic eigenmodes including Hermite-Laguerre-Gaussian and (helical) InceGaussian modes is exploited to construct coherent state modes, which unifies the representations of travelingwave (TW) and standing-wave (SW) ray-wave structured light for the first time and realizes the TW-SW unified ray-wave geometric beam with topology of raytrajectories splitting effect, breaking the boundary of TW and SW structured light.


Disentangled Self-Attentive Neural Networks for Click-Through Rate Prediction

2 code implementations11 Jan 2021 Yichen Xu, Yanqiao Zhu, Feng Yu, Qiang Liu, Shu Wu

To better model complex feature interaction, in this paper we propose a novel DisentanglEd Self-atTentIve NEtwork (DESTINE) framework for CTR prediction that explicitly decouples the computation of unary feature importance from pairwise interaction.

Click-Through Rate Prediction Feature Importance

Varying Coefficient Neural Network with Functional Targeted Regularization for Estimating Continuous Treatment Effects

no code implementations ICLR 2021 Lizhen Nie, Mao Ye, Qiang Liu, Dan Nicolae

With the rising abundance of observational data with continuous treatments, we investigate the problem of estimating average dose-response curve (ADRF).

Fast Training of Contrastive Learning with Intermediate Contrastive Loss

no code implementations1 Jan 2021 Chengyue Gong, Xingchao Liu, Qiang Liu

We apply our method to recently-proposed MOCO, SimCLR, SwAV and notice that we can reduce the computational cost with little loss on the performance of ImageNet linear classification and other downstream tasks.

Contrastive Learning

Speeding up Deep Learning Training by Sharing Weights and Then Unsharing

no code implementations1 Jan 2021 Shuo Yang, Le Hou, Xiaodan Song, Qiang Liu, Denny Zhou

It has been widely observed that increasing deep learning model sizes often leads to significant performance improvements on a variety of natural language processing and computer vision tasks.

A Coach-Player Framework for Dynamic Team Composition

no code implementations1 Jan 2021 Bo Liu, Qiang Liu, Peter Stone, Animesh Garg, Yuke Zhu, Anima Anandkumar

The performance of our method is comparable or even better than the setting where all players have a full view of the environment, but no coach.

LiveMap: Real-Time Dynamic Map in Automotive Edge Computing

no code implementations16 Dec 2020 Qiang Liu, Tao Han, Jiang, Xie, BaekGyu Kim

In this paper, we propose LiveMap, a real-time dynamic map, that detects, matches, and tracks objects on the road with crowdsourcing data from connected vehicles in sub-second.

Autonomous Driving Edge-computing +3

Eudoxus: Characterizing and Accelerating Localization in Autonomous Machines

no code implementations2 Dec 2020 Yiming Gan, Yu Bo, Boyuan Tian, Leimeng Xu, Wei Hu, Shaoshan Liu, Qiang Liu, Yanjun Zhang, Jie Tang, Yuhao Zhu

We develop and commercialize autonomous machines, such as logistic robots and self-driving cars, around the globe.

Self-Driving Cars Hardware Architecture

AlphaMatch: Improving Consistency for Semi-supervised Learning with Alpha-divergence

no code implementations CVPR 2021 Chengyue Gong, Dilin Wang, Qiang Liu

Semi-supervised learning (SSL) is a key approach toward more data-efficient machine learning by jointly leverage both labeled and unlabeled data.

Certified Monotonic Neural Networks

1 code implementation NeurIPS 2020 Xingchao Liu, Xing Han, Na Zhang, Qiang Liu

In this work, we propose to certify the monotonicity of the general piece-wise linear neural networks by solving a mixed integer linear programming problem. This provides a new general approach for learning monotonic neural networks with arbitrary model structures.


Smart obervation method with wide field small aperture telescopes for real time transient detection

no code implementations20 Nov 2020 Peng Jia, Qiang Liu, Yongyang Sun, Yitian Zheng, Wenbo Liu, Yifei Zhao

The ARGUS uses a deep learning based astronomical detection algorithm implemented in embedded devices in each WFSATs to detect astronomical targets.

Ensemble Learning

Debiasing Convolutional Neural Networks via Meta Orthogonalization

1 code implementation15 Nov 2020 Kurtis Evan David, Qiang Liu, Ruth Fong

While deep learning models often achieve strong task performance, their successes are hampered by their inability to disentangle spurious correlations from causative factors, such as when they use protected attributes (e. g., race, gender, etc.)

Word Embeddings

When Contrastive Learning Meets Active Learning: A Novel Graph Active Learning Paradigm with Self-Supervision

no code implementations30 Oct 2020 Yanqiao Zhu, Weizhi Xu, Qiang Liu, Shu Wu

To this end, we present a minimax selection scheme that explicitly harnesses neighborhood information and discover homophilous subgraphs to facilitate active selection.

Active Learning Contrastive Learning +2

Greedy Optimization Provably Wins the Lottery: Logarithmic Number of Winning Tickets is Enough

1 code implementation NeurIPS 2020 Mao Ye, Lemeng Wu, Qiang Liu

Despite the great success of deep learning, recent works show that large deep neural networks are often highly redundant and can be significantly reduced in size.

Off-Policy Interval Estimation with Lipschitz Value Iteration

no code implementations NeurIPS 2020 Ziyang Tang, Yihao Feng, Na Zhang, Jian Peng, Qiang Liu

Off-policy evaluation provides an essential tool for evaluating the effects of different policies or treatments using only observed data.

Decision Making Medical Diagnosis +1

Graph Contrastive Learning with Adaptive Augmentation

1 code implementation27 Oct 2020 Yanqiao Zhu, Yichen Xu, Feng Yu, Qiang Liu, Shu Wu, Liang Wang

On the node attribute level, we corrupt node features by adding more noise to unimportant node features, to enforce the model to recognize underlying semantic information.

Contrastive Learning Data Augmentation +2

Population Gradients improve performance across data-sets and architectures in object classification

no code implementations23 Oct 2020 Yurika Sakai, Andrey Kormilitzin, Qiang Liu, Alejo Nevado-Holgado

The most successful methods such as ReLU transfer functions, batch normalization, Xavier initialization, dropout, learning rate decay, or dynamic optimizers, have become standards in the field due, particularly, to their ability to increase the performance of Neural Networks (NNs) significantly and in almost all situations.

General Classification

An efficient representation of chronological events in medical texts

no code implementations EMNLP (Louhi) 2020 Andrey Kormilitzin, Nemanja Vaci, Qiang Liu, Hao Ni, Goran Nenadic, Alejo Nevado-Holgado

In this work we addressed the problem of capturing sequential information contained in longitudinal electronic health records (EHRs).

Adaptive Dense-to-Sparse Paradigm for Pruning Online Recommendation System with Non-Stationary Data

no code implementations16 Oct 2020 Mao Ye, Dhruv Choudhary, Jiecao Yu, Ellie Wen, Zeliang Chen, Jiyan Yang, Jongsoo Park, Qiang Liu, Arun Kejariwal

To the best of our knowledge, this is the first work to provide in-depth analysis and discussion of applying pruning to online recommendation systems with non-stationary data distribution.

Recommendation Systems

Modeling Dyadic Conversations for Personality Inference

no code implementations26 Sep 2020 Qiang Liu

We adjust the formulation of each layer of a conventional GRU with sequence to sequence learning and personal information of both sides of the conversation.

DNN2LR: Interpretation-inspired Feature Crossing for Real-world Tabular Data

no code implementations22 Aug 2020 Zhaocheng Liu, Qiang Liu, Haoli Zhang, Yuntian Chen

Simple classifiers, e. g., Logistic Regression (LR), are globally interpretable, but not powerful enough to model complex nonlinear interactions among features in tabular data.

DeepSlicing: Deep Reinforcement Learning Assisted Resource Allocation for Network Slicing

no code implementations17 Aug 2020 Qiang Liu, Tao Han, Ning Zhang, Ye Wang

Network slicing enables multiple virtual networks run on the same physical infrastructure to support various use cases in 5G and beyond.

reinforcement-learning Reinforcement Learning (RL)

Disentangled Item Representation for Recommender Systems

no code implementations17 Aug 2020 Zeyu Cui, Feng Yu, Shu Wu, Qiang Liu, Liang Wang

In this way, the items are represented at the attribute level, which can provide fine-grained information of items in recommendation.

Recommendation Systems

Accountable Off-Policy Evaluation With Kernel Bellman Statistics

no code implementations15 Aug 2020 Yihao Feng, Tongzheng Ren, Ziyang Tang, Qiang Liu

We consider off-policy evaluation (OPE), which evaluates the performance of a new policy from observed data collected from previous experiments, without requiring the execution of the new policy.

Medical Diagnosis Off-policy evaluation +1

Deep Active Learning by Model Interpretability

no code implementations23 Jul 2020 Qiang Liu, Zhaocheng Liu, Xiaofang Zhu, Yeliang Xiu

In this paper, inspired by piece-wise linear interpretability in DNN, we introduce the linearly separable regions of samples to the problem of active learning, and propose a novel Deep Active learning approach by Model Interpretability (DAMI).

Active Learning Clustering +1

Simplification of Graph Convolutional Networks: A Matrix Factorization-based Perspective

no code implementations17 Jul 2020 Qiang Liu, Haoli Zhang, Zhaocheng Liu

Moreover, we have also conducted experiments on a typical task of graph embedding, i. e., community detection, and the proposed UCMF model outperforms several representative graph embedding models.

Community Detection Distributed Computing +2

Go Wide, Then Narrow: Efficient Training of Deep Thin Networks

no code implementations ICML 2020 Denny Zhou, Mao Ye, Chen Chen, Tianjian Meng, Mingxing Tan, Xiaodan Song, Quoc Le, Qiang Liu, Dale Schuurmans

This is achieved by layerwise imitation, that is, forcing the thin network to mimic the intermediate outputs of the wide network from layer to layer.

Model Compression

TFNet: Multi-Semantic Feature Interaction for CTR Prediction

no code implementations29 Jun 2020 Shu Wu, Feng Yu, Xueli Yu, Qiang Liu, Liang Wang, Tieniu Tan, Jie Shao, Fan Huang

The CTR (Click-Through Rate) prediction plays a central role in the domain of computational advertising and recommender systems.

Click-Through Rate Prediction Recommendation Systems

Deep Graph Contrastive Representation Learning

2 code implementations7 Jun 2020 Yanqiao Zhu, Yichen Xu, Feng Yu, Qiang Liu, Shu Wu, Liang Wang

Moreover, our unsupervised method even surpasses its supervised counterparts on transductive tasks, demonstrating its great potential in real-world applications.

Contrastive Learning Graph Representation Learning +1

SAFER: A Structure-free Approach for Certified Robustness to Adversarial Word Substitutions

1 code implementation ACL 2020 Mao Ye, Chengyue Gong, Qiang Liu

For security reasons, it is of critical importance to develop models with certified robustness that can provably guarantee that the prediction is can not be altered by any possible synonymous word substitution.

text-classification Text Classification

TAGNN: Target Attentive Graph Neural Networks for Session-based Recommendation

1 code implementation6 May 2020 Feng Yu, Yanqiao Zhu, Qiang Liu, Shu Wu, Liang Wang, Tieniu Tan

However, these methods compress a session into one fixed representation vector without considering the target items to be predicted.

Session-Based Recommendations

An Empirical Study on Feature Discretization

no code implementations27 Apr 2020 Qiang Liu, Zhaocheng Liu, Haoli Zhang

When dealing with continuous numeric features, we usually adopt feature discretization.

Dimension Independent Generalization Error by Stochastic Gradient Descent

no code implementations25 Mar 2020 Xi Chen, Qiang Liu, Xin T. Tong

One classical canon of statistics is that large models are prone to overfitting, and model selection procedures are necessary for high dimensional data.

Model Selection regression

Black-box Off-policy Estimation for Infinite-Horizon Reinforcement Learning

no code implementations ICLR 2020 Ali Mousavi, Lihong Li, Qiang Liu, Denny Zhou

Off-policy estimation for long-horizon problems is important in many real-life applications such as healthcare and robotics, where high-fidelity simulators may not be available and on-policy evaluation is expensive or impossible.

reinforcement-learning Reinforcement Learning (RL)

Steepest Descent Neural Architecture Optimization: Escaping Local Optimum with Signed Neural Splitting

no code implementations23 Mar 2020 Lemeng Wu, Mao Ye, Qi Lei, Jason D. Lee, Qiang Liu

Recently, Liu et al.[19] proposed a splitting steepest descent (S2D) method that jointly optimizes the neural parameters and architectures based on progressively growing network structures by splitting neurons into multiple copies in a steepest descent fashion.

Good Subnetworks Provably Exist: Pruning via Greedy Forward Selection

1 code implementation3 Mar 2020 Mao Ye, Chengyue Gong, Lizhen Nie, Denny Zhou, Adam Klivans, Qiang Liu

This differs from the existing methods based on backward elimination, which remove redundant neurons from the large network.

Network Pruning

Stein Variational Inference for Discrete Distributions

no code implementations1 Mar 2020 Jun Han, Fan Ding, Xianglong Liu, Lorenzo Torresani, Jian Peng, Qiang Liu

In addition, such transform can be straightforwardly employed in gradient-free kernelized Stein discrepancy to perform goodness-of-fit (GOF) test on discrete distributions.

Variational Inference

Statistical Adaptive Stochastic Gradient Methods

1 code implementation25 Feb 2020 Pengchuan Zhang, Hunter Lang, Qiang Liu, Lin Xiao

We propose a statistical adaptive procedure called SALSA for automatically scheduling the learning rate (step size) in stochastic gradient methods.


Stein Self-Repulsive Dynamics: Benefits From Past Samples

1 code implementation NeurIPS 2020 Mao Ye, Tongzheng Ren, Qiang Liu

Our idea is to introduce Stein variational gradient as a repulsive force to push the samples of Langevin dynamics away from the past trajectories.

Black-Box Certification with Randomized Smoothing: A Functional Optimization Based Framework

no code implementations NeurIPS 2020 Dinghuai Zhang, Mao Ye, Chengyue Gong, Zhanxing Zhu, Qiang Liu

Randomized classifiers have been shown to provide a promising approach for achieving certified robustness against adversarial attacks in deep learning.

Detection and Classification of Astronomical Targets with Deep Neural Networks in Wide Field Small Aperture Telescopes

no code implementations21 Feb 2020 Peng Jia, Qiang Liu, Yongyang Sun

To increase the generalization ability of our framework, we use both simulated and real observation images to train the neural network.

General Classification Transfer Learning

Post-training Quantization with Multiple Points: Mixed Precision without Mixed Precision

no code implementations20 Feb 2020 Xingchao Liu, Mao Ye, Dengyong Zhou, Qiang Liu

We propose multipoint quantization, a quantization method that approximates a full-precision weight vector using a linear combination of multiple vectors of low-bit numbers; this is in contrast to typical quantization methods that approximate each weight using a single low precision number.

object-detection Object Detection +1

MaxUp: A Simple Way to Improve Generalization of Neural Network Training

1 code implementation20 Feb 2020 Chengyue Gong, Tongzheng Ren, Mao Ye, Qiang Liu

The idea is to generate a set of augmented data with some random perturbations or transforms and minimize the maximum, or worst case loss over the augmented data.

Few-Shot Image Classification General Classification +1

Attributed Multi-Relational Attention Network for Fact-checking URL Recommendation

1 code implementation7 Jan 2020 Di You, Nguyen Vo, Kyumin Lee, Qiang Liu

To combat fake news, researchers mostly focused on detecting fake news and journalists built and maintained fact-checking sites (e. g., Snopes. com and Politifact. com).

Fact Checking Graph Attention +1

Deep Interaction Machine: A Simple but Effective Model for High-order Feature Interactions

1 code implementation1 Jan 2020 Feng Yu, Zhaocheng Liu, Qiang Liu, Haoli Zhang, Shu Wu, Liang Wang

IM is an efficient and exact implementation of high-order FM, whose time complexity linearly grows with the order of interactions and the number of feature fields.

Click-Through Rate Prediction Feature Engineering

Deep Interaction Machine: A Simple but Effective Model for High-order Feature Interactions

no code implementations CIKM 2020 Feng Yu, Zhaocheng Liu, Qiang Liu, Haoli Zhang, Shu Wu, Liang Wang

IM is an efficient and exact implementation of high-order FM, whose time complexity linearly grows with the order of interactions and the number of feature fields.

Click-Through Rate Prediction Feature Engineering

The Black-Scholes-Merton dual equation

no code implementations22 Dec 2019 Shuxin Guo, Qiang Liu

We derive the Black-Scholes-Merton dual equation, which has exactly the same form as the Black-Scholes-Merton equation.

Learning Preferences and Demands in Visual Recommendation

no code implementations11 Nov 2019 Qiang Liu, Shu Wu, Liang Wang

For modeling users' demands on different categories of items, the problem can be formulated as recommendation with contextual and sequential information.

Recommendation Systems

Stein Variational Gradient Descent With Matrix-Valued Kernels

1 code implementation NeurIPS 2019 Dilin Wang, Ziyang Tang, Chandrajit Bajaj, Qiang Liu

Stein variational gradient descent (SVGD) is a particle-based inference algorithm that leverages gradient information for efficient approximate inference.

Bayesian Inference

Energy-Aware Neural Architecture Optimization with Fast Splitting Steepest Descent

1 code implementation ICLR 2020 Dilin Wang, Meng Li, Lemeng Wu, Vikas Chandra, Qiang Liu

Designing energy-efficient networks is of critical importance for enabling state-of-the-art deep learning in mobile and edge settings where the computation and energy budgets are highly limited.

Splitting Steepest Descent for Growing Neural Architectures

1 code implementation NeurIPS 2019 Qiang Liu, Lemeng Wu, Dilin Wang

We develop a progressive training approach for neural networks which adaptively grows the network structure by splitting existing neurons to multiple off-springs.