Search Results for author: Hongyuan Zha

Found 128 papers, 38 papers with code

AutoMix: Mixup Networks for Sample Interpolation via Cooperative Barycenter Learning

no code implementations ECCV 2020 Jianchao Zhu, Liangliang Shi, Junchi Yan, Hongyuan Zha

This paper proposes new ways of sample mixing by thinking of the process as generation of barycenter in a metric space for data augmentation.

Data Augmentation

A Variational Autoencoder for Neural Temporal Point Processes with Dynamic Latent Graphs

no code implementations26 Dec 2023 Sikun Yang, Hongyuan Zha

In particular, we use a sequential latent variable model to learn a dependency graph between the observed dimensions, for each sub-interval.

Point Processes

Can language agents be alternatives to PPO? A Preliminary Empirical Study On OpenAI Gym

1 code implementation6 Dec 2023 Junjie Sheng, Zixiao Huang, Chuyun Shen, Wenhao Li, Yun Hua, Bo Jin, Hongyuan Zha, Xiangfeng Wang

The formidable capacity for zero- or few-shot decision-making in language agents encourages us to pose a compelling question: Can language agents be alternatives to PPO agents in traditional sequential decision-making tasks?

Benchmarking Decision Making +1

Score Matching-based Pseudolikelihood Estimation of Neural Marked Spatio-Temporal Point Process with Uncertainty Quantification

no code implementations25 Oct 2023 Zichong Li, Qunzhi Xu, Zhenghao Xu, Yajun Mei, Tuo Zhao, Hongyuan Zha

Specifically, our framework adopts a normalization-free objective by estimating the pseudolikelihood of marked STPPs through score-matching and offers uncertainty quantification for the predicted event time, location and mark by computing confidence regions over the generated samples.

Point Processes Uncertainty Quantification

Negotiated Reasoning: On Provably Addressing Relative Over-Generalization

no code implementations8 Jun 2023 Junjie Sheng, Wenhao Li, Bo Jin, Hongyuan Zha, Jun Wang, Xiangfeng Wang

Recent methods have shown that assigning reasoning ability to agents can mitigate RO algorithmically and empirically, but there has been a lack of theoretical understanding of RO, let alone designing provably RO-free methods.

Multi-agent Reinforcement Learning

Semantically Aligned Task Decomposition in Multi-Agent Reinforcement Learning

no code implementations18 May 2023 Wenhao Li, Dan Qiao, Baoxiang Wang, Xiangfeng Wang, Bo Jin, Hongyuan Zha

The difficulty of appropriately assigning credit is particularly heightened in cooperative MARL with sparse reward, due to the concurrent time and structural scales involved.

Decision Making Multi-agent Reinforcement Learning +2

Information Design in Multi-Agent Reinforcement Learning

1 code implementation NeurIPS 2023 Yue Lin, Wenhao Li, Hongyuan Zha, Baoxiang Wang

To thrive in those environments, the agent needs to influence other agents so their actions become more helpful and less harmful.

Multi-agent Reinforcement Learning reinforcement-learning +1

Diverse Policy Optimization for Structured Action Space

1 code implementation23 Feb 2023 Wenhao Li, Baoxiang Wang, Shanchao Yang, Hongyuan Zha

We propose a simple and effective RL method, Diverse Policy Optimization (DPO), to model the policies in structured action space as the energy-based models (EBM) by following the probabilistic RL framework.

Reinforcement Learning (RL)

Mean Parity Fair Regression in RKHS

1 code implementation21 Feb 2023 Shaokui Wei, Jiayin Liu, Bing Li, Hongyuan Zha

We study the fair regression problem under the notion of Mean Parity (MP) fairness, which requires the conditional mean of the learned function output to be constant with respect to the sensitive attributes.

Fairness regression

Learning Roles with Emergent Social Value Orientations

no code implementations31 Jan 2023 Wenhao Li, Xiangfeng Wang, Bo Jin, Jingyi Lu, Hongyuan Zha

Social dilemmas can be considered situations where individual rationality leads to collective irrationality.

Multi-agent Reinforcement Learning Role Embedding

Estimating Latent Population Flows from Aggregated Data via Inversing Multi-Marginal Optimal Transport

no code implementations30 Dec 2022 Sikun Yang, Hongyuan Zha

In particular, we propose to estimate the transition flows from aggregated data by learning the cost functions of the MOT framework, which enables us to capture time-varying dynamic patterns.

Learning to Optimize Permutation Flow Shop Scheduling via Graph-based Imitation Learning

1 code implementation31 Oct 2022 Longkang Li, Siyuan Liang, Zihao Zhu, Chris Ding, Hongyuan Zha, Baoyuan Wu

Compared to the state-of-the-art reinforcement learning method, our model's network parameters are reduced to only 37\% of theirs, and the solution gap of our model towards the expert solutions decreases from 6. 8\% to 1. 3\% on average.

Computational Efficiency Imitation Learning +3

Adaptive Distribution Calibration for Few-Shot Learning with Hierarchical Optimal Transport

no code implementations9 Oct 2022 Dandan Guo, Long Tian, He Zhao, Mingyuan Zhou, Hongyuan Zha

A recent solution to this problem is calibrating the distribution of these few sample classes by transferring statistics from the base classes with sufficient examples, where how to decide the transfer weights from base classes to novel classes is the key.

Domain Generalization Few-Shot Learning

Differentially Private Estimation of Hawkes Process

no code implementations15 Sep 2022 Simiao Zuo, Tianyi Liu, Tuo Zhao, Hongyuan Zha

Point process models are of great importance in real world applications.

Learning to Re-weight Examples with Optimal Transport for Imbalanced Classification

no code implementations5 Aug 2022 Dandan Guo, Zhuo Li, Meixi Zheng, He Zhao, Mingyuan Zhou, Hongyuan Zha

Specifically, we view the training set as an imbalanced distribution over its samples, which is transported by OT to a balanced distribution obtained from the meta set.

Bilevel Optimization imbalanced classification

Robust Knowledge Adaptation for Dynamic Graph Neural Networks

no code implementations22 Jul 2022 Hanjie Li, Changsheng Li, Kaituo Feng, Ye Yuan, Guoren Wang, Hongyuan Zha

Recent years have witnessed the increasing attentions paid to dynamic graph neural networks for modelling such graph data, where almost all the existing approaches assume that when a new link is built, the embeddings of the neighbor nodes should be updated by learning the temporal dynamics to propagate new information.

reinforcement-learning Reinforcement Learning (RL)

Learning Neural Hamiltonian Dynamics: A Methodological Overview

1 code implementation28 Feb 2022 Zhijie Chen, Mingquan Feng, Junchi Yan, Hongyuan Zha

The past few years have witnessed an increased interest in learning Hamiltonian dynamics in deep learning frameworks.

Inductive Bias

Obtaining Dyadic Fairness by Optimal Transport

1 code implementation9 Feb 2022 Moyi Yang, Junjie Sheng, Xiangfeng Wang, Wenyan Liu, Bo Jin, Jun Wang, Hongyuan Zha

Fairness has been taken as a critical metric in machine learning models, which is considered as an important component of trustworthy machine learning.

Fairness Link Prediction

Multi-Agent Path Finding with Prioritized Communication Learning

1 code implementation8 Feb 2022 Wenhao Li, Hongjun Chen, Bo Jin, Wenzhe Tan, Hongyuan Zha, Xiangfeng Wang

The learning-based, fully decentralized framework has been introduced to alleviate real-time problems and simultaneously pursue optimal planning policy.

Multi-Agent Path Finding Multi-agent Reinforcement Learning +1

VMAgent: Scheduling Simulator for Reinforcement Learning

2 code implementations9 Dec 2021 Junjie Sheng, Shengliang Cai, Haochuan Cui, Wenhao Li, Yun Hua, Bo Jin, Wenli Zhou, Yiqiu Hu, Lei Zhu, Qian Peng, Hongyuan Zha, Xiangfeng Wang

A novel simulator called VMAgent is introduced to help RL researchers better explore new methods, especially for virtual machine scheduling.

Cloud Computing reinforcement-learning +2

Learning Prototype-oriented Set Representations for Meta-Learning

no code implementations ICLR 2022 Dandan Guo, Long Tian, Minghe Zhang, Mingyuan Zhou, Hongyuan Zha

Since our plug-and-play framework can be applied to many meta-learning problems, we further instantiate it to the cases of few-shot classification and implicit meta generative modeling.

Meta-Learning

Edge Rewiring Goes Neural: Boosting Network Resilience without Rich Features

1 code implementation18 Oct 2021 Shanchao Yang, Kaili Ma, Baoxiang Wang, Tianshu Yu, Hongyuan Zha

In this case, GNNs can barely learn useful information, resulting in prohibitive difficulty in making actions for successively rewiring edges under a reinforcement learning context.

reinforcement-learning Reinforcement Learning (RL)

Low-rank Matrix Recovery With Unknown Correspondence

no code implementations15 Oct 2021 Zhiwei Tang, Tsung-Hui Chang, Xiaojing Ye, Hongyuan Zha

We study a matrix recovery problem with unknown correspondence: given the observation matrix $M_o=[A,\tilde P B]$, where $\tilde P$ is an unknown permutation matrix, we aim to recover the underlying matrix $M=[A, B]$.

A Principled Permutation Invariant Approach to Mean-Field Multi-Agent Reinforcement Learning

no code implementations29 Sep 2021 Yan Li, Lingxiao Wang, Jiachen Yang, Ethan Wang, Zhaoran Wang, Tuo Zhao, Hongyuan Zha

To exploit the permutation invariance therein, we propose the mean-field proximal policy optimization (MF-PPO) algorithm, at the core of which is a permutation- invariant actor-critic neural architecture.

Inductive Bias Multi-agent Reinforcement Learning +2

Self-Training with Differentiable Teacher

no code implementations Findings (NAACL) 2022 Simiao Zuo, Yue Yu, Chen Liang, Haoming Jiang, Siawpeng Er, Chao Zhang, Tuo Zhao, Hongyuan Zha

In self-training, the student contributes to the prediction performance, and the teacher controls the training process by generating pseudo-labels.

named-entity-recognition Named Entity Recognition +3

Sqrt(d) Dimension Dependence of Langevin Monte Carlo

no code implementations ICLR 2022 Ruilin Li, Hongyuan Zha, Molei Tao

This article considers the popular MCMC method of unadjusted Langevin Monte Carlo (LMC) and provides a non-asymptotic analysis of its sampling error in 2-Wasserstein distance.

Influence Estimation and Maximization via Neural Mean-Field Dynamics

no code implementations3 Jun 2021 Shushan He, Hongyuan Zha, Xiaojing Ye

Directly using information diffusion cascade data, our framework can simultaneously learn the structure of the diffusion network and the evolution of node infection probabilities.

Mean-Square Analysis with An Application to Optimal Dimension Dependence of Langevin Monte Carlo

no code implementations NeurIPS 2021 Ruilin Li, Hongyuan Zha, Molei Tao

This bound improves the best previously known $\widetilde{\mathcal{O}}\left(\frac{d}{\epsilon}\right)$ result and is optimal in both dimension $d$ and accuracy tolerance $\epsilon$ for log-smooth and log-strongly-convex target measures.

Permutation Invariant Policy Optimization for Mean-Field Multi-Agent Reinforcement Learning: A Principled Approach

no code implementations18 May 2021 Yan Li, Lingxiao Wang, Jiachen Yang, Ethan Wang, Zhaoran Wang, Tuo Zhao, Hongyuan Zha

To exploit the permutation invariance therein, we propose the mean-field proximal policy optimization (MF-PPO) algorithm, at the core of which is a permutation-invariant actor-critic neural architecture.

Inductive Bias Multi-agent Reinforcement Learning

Random Noise Defense Against Query-Based Black-Box Attacks

1 code implementation NeurIPS 2021 Zeyu Qin, Yanbo Fan, Hongyuan Zha, Baoyuan Wu

We conduct the theoretical analysis about the effectiveness of RND against query-based black-box attacks and the corresponding adaptive attacks.

Adversarial Robustness

Mean Field Game GAN

no code implementations14 Mar 2021 Shaojun Ma, Haomin Zhou, Hongyuan Zha

We propose a novel mean field games (MFGs) based GAN(generative adversarial network) framework.

Generative Adversarial Network

Graph-Based Tri-Attention Network for Answer Ranking in CQA

no code implementations5 Mar 2021 Wei zhang, Zeyuan Chen, Chao Dong, Wen Wang, Hongyuan Zha, Jianyong Wang

However, they encounter two main limitations: (1) Correlations between answers in the same question are often overlooked.

Question Answering

Reinforcement Learning for Adaptive Mesh Refinement

no code implementations1 Mar 2021 Jiachen Yang, Tarik Dzanic, Brenden Petersen, Jun Kudo, Ketan Mittal, Vladimir Tomov, Jean-Sylvain Camier, Tuo Zhao, Hongyuan Zha, Tzanio Kolev, Robert Anderson, Daniel Faissol

Large-scale finite element simulations of complex physical systems governed by partial differential equations (PDE) crucially depend on adaptive mesh refinement (AMR) to allocate computational budget to regions where higher resolution is required.

Inductive Bias reinforcement-learning +1

Dealing with Non-Stationarity in MARL via Trust-Region Decomposition

no code implementations ICLR 2022 Wenhao Li, Xiangfeng Wang, Bo Jin, Junjie Sheng, Hongyuan Zha

In this paper, we introduce a novel notion, the $\delta$-measurement, to explicitly measure the non-stationarity of a policy sequence, which can be further proved to be bounded by the KL-divergence of consecutive joint policies.

Multi-agent Reinforcement Learning

Structured Diversification Emergence via Reinforced Organization Control and Hierarchical Consensus Learning

no code implementations9 Feb 2021 Wenhao Li, Xiangfeng Wang, Bo Jin, Junjie Sheng, Yun Hua, Hongyuan Zha

In order to improve the efficiency of cooperation and exploration, we propose a structured diversification emergence MARL framework named {\sc{Rochico}} based on reinforced organization control and hierarchical consensus learning.

Multi-agent Reinforcement Learning

Learning High Dimensional Wasserstein Geodesics

no code implementations5 Feb 2021 Shu Liu, Shaojun Ma, Yongxin Chen, Hongyuan Zha, Haomin Zhou

We propose a new formulation and learning strategy for computing the Wasserstein geodesic between two probability distributions in high dimensions.

Vocal Bursts Intensity Prediction

Hawkes Processes on Graphons

no code implementations4 Feb 2021 Hongteng Xu, Dixin Luo, Hongyuan Zha

We propose a novel framework for modeling multiple multivariate point processes, each with heterogeneous event types that share an underlying space and obey the same generative mechanism.

Point Processes

Inductive Collaborative Filtering via Relation Graph Learning

no code implementations1 Jan 2021 Qitian Wu, Hengrui Zhang, Xiaofeng Gao, Hongyuan Zha

In this paper, we propose an inductive collaborative filtering framework that learns a hidden relational graph among users from the rating matrix.

Collaborative Filtering Graph Learning +2

Mutual Calibration between Explicit and Implicit Deep Generative Models

no code implementations1 Jan 2021 Qitian Wu, Rui Gao, Hongyuan Zha

Deep generative models are generally categorized into explicit models and implicit models.

Fair Differential Privacy Can Mitigate the Disparate Impact on Model Accuracy

no code implementations1 Jan 2021 Wenyan Liu, Xiangfeng Wang, Xingjian Lu, Junhong Cheng, Bo Jin, Xiaoling Wang, Hongyuan Zha

This paper proposes a fair differential privacy algorithm (FairDP) to mitigate the disparate impact on model accuracy for each class.

Fairness

Generalize a Small Pre-trained Model to Arbitrarily Large TSP Instances

1 code implementation19 Dec 2020 Zhang-Hua Fu, Kai-Bin Qiu, Hongyuan Zha

For the traveling salesman problem (TSP), the existing supervised learning based algorithms suffer seriously from the lack of generalization ability.

Graph Sampling Reinforcement Learning (RL) +1

Learning Graphons via Structured Gromov-Wasserstein Barycenters

1 code implementation10 Dec 2020 Hongteng Xu, Dixin Luo, Lawrence Carin, Hongyuan Zha

Accordingly, given a set of graphs generated by an underlying graphon, we learn the corresponding step function as the Gromov-Wasserstein barycenter of the given graphs.

LEMMA

Differentiable Top-k with Optimal Transport

no code implementations NeurIPS 2020 Yujia Xie, Hanjun Dai, Minshuo Chen, Bo Dai, Tuo Zhao, Hongyuan Zha, Wei Wei, Tomas Pfister

Finding the k largest or smallest elements from a collection of scores, i. e., top-k operation, is an important model component widely used in information retrieval, machine learning, and data mining.

Information Retrieval Retrieval

Learning Strategic Network Emergence Games

no code implementations NeurIPS 2020 Rakshit Trivedi, Hongyuan Zha

Real-world networks, especially the ones that emerge due to actions of animate agents (e. g. humans, animals), are the result of underlying strategic mechanisms aimed at maximizing individual or collective benefits.

A Hypergradient Approach to Robust Regression without Correspondence

no code implementations ICLR 2021 Yujia Xie, Yixiu Mao, Simiao Zuo, Hongteng Xu, Xiaojing Ye, Tuo Zhao, Hongyuan Zha

Due to the combinatorial nature of the problem, most existing methods are only applicable when the sample size is small, and limited to linear regression models.

Multi-Object Tracking regression

Reliable Off-policy Evaluation for Reinforcement Learning

no code implementations8 Nov 2020 Jie Wang, Rui Gao, Hongyuan Zha

In a sequential decision-making problem, off-policy evaluation estimates the expected cumulative reward of a target policy using logged trajectory data generated from a different behavior policy, without execution of the target policy.

Decision Making Off-policy evaluation +1

Differentiable Top-$k$ with Optimal Transport

no code implementations NeurIPS Workshop LMCA 2020 Yujia Xie, Hanjun Dai, Minshuo Chen, Bo Dai, Tuo Zhao, Hongyuan Zha, Wei Wei, Tomas Pfister

The top-$k$ operation, i. e., finding the $k$ largest or smallest elements from a collection of scores, is an important model component, which is widely used in information retrieval, machine learning, and data mining.

Information Retrieval Retrieval

Towards Open-World Recommendation: An Inductive Model-based Collaborative Filtering Approach

1 code implementation9 Jul 2020 Qitian Wu, Hengrui Zhang, Xiaofeng Gao, Junchi Yan, Hongyuan Zha

The first model follows conventional matrix factorization which factorizes a group of key users' rating matrix to obtain meta latents.

Collaborative Filtering Matrix Completion +2

GraphOpt: Learning Optimization Models of Graph Formation

no code implementations ICML 2020 Rakshit Trivedi, Jiachen Yang, Hongyuan Zha

Formation mechanisms are fundamental to the study of complex networks, but learning them from observations is challenging.

Decision Making Link Prediction

Hessian-Free High-Resolution Nesterov Acceleration for Sampling

no code implementations16 Jun 2020 Ruilin Li, Hongyuan Zha, Molei Tao

Nesterov's Accelerated Gradient (NAG) for optimization has better performance than its continuous time limit (noiseless kinetic Langevin) when a finite step-size is employed \citep{shi2021understanding}.

Vocal Bursts Intensity Prediction

Network Diffusions via Neural Mean-Field Dynamics

1 code implementation NeurIPS 2020 Shushan He, Hongyuan Zha, Xiaojing Ye

We propose a novel learning framework based on neural mean-field dynamics for inference and estimation problems of diffusion on networks.

Learning to Incentivize Other Learning Agents

2 code implementations NeurIPS 2020 Jiachen Yang, Ang Li, Mehrdad Farajtabar, Peter Sunehag, Edward Hughes, Hongyuan Zha

The challenge of developing powerful and general Reinforcement Learning (RL) agents has received increasing attention in recent years.

General Reinforcement Learning Reinforcement Learning (RL)

F2A2: Flexible Fully-decentralized Approximate Actor-critic for Cooperative Multi-agent Reinforcement Learning

no code implementations17 Apr 2020 Wenhao Li, Bo Jin, Xiangfeng Wang, Junchi Yan, Hongyuan Zha

Traditional centralized multi-agent reinforcement learning (MARL) algorithms are sometimes unpractical in complicated applications, due to non-interactivity between agents, curse of dimensionality and computation complexity.

Multi-agent Reinforcement Learning Reinforcement Learning (RL) +2

Learning Cost Functions for Optimal Transport

no code implementations22 Feb 2020 Shaojun Ma, Haodong Sun, Xiaojing Ye, Hongyuan Zha, Haomin Zhou

Inverse optimal transport (OT) refers to the problem of learning the cost function for OT from observed transport plan or its samples.

Transformer Hawkes Process

3 code implementations ICML 2020 Simiao Zuo, Haoming Jiang, Zichong Li, Tuo Zhao, Hongyuan Zha

Modern data acquisition routinely produce massive amounts of event sequence data in various domains, such as social media, healthcare, and financial markets.

Computational Efficiency Point Processes

Improving Sampling Accuracy of Stochastic Gradient MCMC Methods via Non-uniform Subsampling of Gradients

no code implementations20 Feb 2020 Ruilin Li, Xin Wang, Hongyuan Zha, Molei Tao

In our practical implementation of EWSG, the non-uniform subsampling is performed efficiently via a Metropolis-Hastings chain on the data index, which is coupled to the MCMC algorithm.

Computational Efficiency

Beyond Clicks: Modeling Multi-Relational Item Graph for Session-Based Target Behavior Prediction

1 code implementation19 Feb 2020 Wen Wang, Wei zhang, Shukai Liu, Qi Liu, Bo Zhang, Leyu Lin, Hongyuan Zha

Specifically, we build a Multi-Relational Item Graph (MRIG) based on all behavior sequences from all sessions, involving target and auxiliary behavior types.

Representation Learning

Differentiable Top-k Operator with Optimal Transport

no code implementations16 Feb 2020 Yujia Xie, Hanjun Dai, Minshuo Chen, Bo Dai, Tuo Zhao, Hongyuan Zha, Wei Wei, Tomas Pfister

The top-k operation, i. e., finding the k largest or smallest elements from a collection of scores, is an important model component, which is widely used in information retrieval, machine learning, and data mining.

Information Retrieval Retrieval

HMRL: Hyper-Meta Learning for Sparse Reward Reinforcement Learning Problem

no code implementations11 Feb 2020 Yun Hua, Xiangfeng Wang, Bo Jin, Wenhao Li, Junchi Yan, Xiaofeng He, Hongyuan Zha

In spite of the success of existing meta reinforcement learning methods, they still have difficulty in learning a meta policy effectively for RL problems with sparse reward.

Meta-Learning Meta Reinforcement Learning +2

Learning Stochastic Behaviour from Aggregate Data

no code implementations10 Feb 2020 Shaojun Ma, Shu Liu, Hongyuan Zha, Haomin Zhou

Learning nonlinear dynamics from aggregate data is a challenging problem because the full trajectory of each individual is not available, namely, the individual observed at one time may not be observed at the next time point, or the identity of individual is unavailable.

Generative Adversarial Network

Distribution Approximation and Statistical Estimation Guarantees of Generative Adversarial Networks

no code implementations10 Feb 2020 Minshuo Chen, Wenjing Liao, Hongyuan Zha, Tuo Zhao

Generative Adversarial Networks (GANs) have achieved a great success in unsupervised learning.

Learning Long- and Short-Term User Literal-Preference with Multimodal Hierarchical Transformer Network for Personalized Image Caption

no code implementations AAAI Conference on Artificial Intelligence (AAAI 2020) 2020 Wei Zhang, Yue Ying, Pan Lu, Hongyuan Zha

Personalized image caption, a natural extension of the standard image caption task, requires to generate brief image descriptions tailored for users’ writing style and traits, and is more practical to meet users’ real demands.

Image Captioning

Improving Domain-Adapted Sentiment Classification by Deep Adversarial Mutual Learning

1 code implementation1 Feb 2020 Qianming Xue, Wei zhang, Hongyuan Zha

To improve domain-adapted sentiment classification by learning sentiment from the target domain as well, we devise a novel deep adversarial mutual learning approach involving two groups of feature extractors, domain discriminators, sentiment classifiers, and label probers.

Classification General Classification +2

Targeted sampling of enlarged neighborhood via Monte Carlo tree search for TSP

1 code implementation ICLR 2020 Zhang-Hua Fu, Kai-Bin Qiu, Meng Qiu, Hongyuan Zha

More precisely, the search process is considered as a Markov decision process (MDP), where a 2-opt local search is used to search within a small neighborhood, while a Monte Carlo tree search (MCTS) method (which iterates through simulation, selection and back-propagation steps), is used to sample a number of targeted actions within an enlarged neighborhood.

BIG-bench Machine Learning Combinatorial Optimization

Hierarchical Cooperative Multi-Agent Reinforcement Learning with Skill Discovery

1 code implementation7 Dec 2019 Jiachen Yang, Igor Borovikov, Hongyuan Zha

The interpretability of the learned skills show the promise of the proposed method for achieving human-AI cooperation in team sports games.

Multi-agent Reinforcement Learning Q-Learning +2

Heterogeneous Graph-based Knowledge Transfer for Generalized Zero-shot Learning

no code implementations20 Nov 2019 Jun-Jie Wang, Xiangfeng Wang, Bo Jin, Junchi Yan, Wenjie Zhang, Hongyuan Zha

To this end, we propose a novel heterogeneous graph-based knowledge transfer method (HGKT) for GZSL, agnostic to unseen classes and instances, by leveraging graph neural network.

Generalized Zero-Shot Learning Transfer Learning

Single Episode Policy Transfer in Reinforcement Learning

1 code implementation ICLR 2020 Jiachen Yang, Brenden Petersen, Hongyuan Zha, Daniel Faissol

An even greater challenge is performing near-optimally in a single attempt at test time, possibly without access to dense rewards, which is not addressed by current methods that require multiple experience rollouts for adaptation.

reinforcement-learning Reinforcement Learning (RL) +1

Infinite-horizon Off-Policy Policy Evaluation with Multiple Behavior Policies

no code implementations ICLR 2020 Xinyun Chen, Lu Wang, Yizhe Hang, Heng Ge, Hongyuan Zha

We consider off-policy policy evaluation when the trajectory data are generated by multiple behavior policies.

Learning Robust Representations with Graph Denoising Policy Network

no code implementations4 Oct 2019 Lu Wang, Wenchao Yu, Wei Wang, Wei Cheng, Wei zhang, Hongyuan Zha, Xiaofeng He, Haifeng Chen

Graph representation learning, aiming to learn low-dimensional representations which capture the geometric dependencies between nodes in the original graph, has gained increasing popularity in a variety of graph analysis tasks, including node classification and link prediction.

Denoising Graph Representation Learning +2

Bridging Explicit and Implicit Deep Generative Models via Neural Stein Estimators

no code implementations NeurIPS 2021 Qitian Wu, Rui Gao, Hongyuan Zha

To take full advantages of both models and enable mutual compensation, we propose a novel joint training framework that bridges an explicit (unnormalized) density estimator and an implicit sample generator via Stein discrepancy.

Stein Bridging: Enabling Mutual Reinforcement between Explicit and Implicit Generative Models

no code implementations25 Sep 2019 Qitian Wu, Rui Gao, Hongyuan Zha

Deep generative models are generally categorized into explicit models and implicit models.

Integrating independent and centralized multi-agent reinforcement learning for traffic signal network optimization

no code implementations23 Sep 2019 Zhi Zhang, Jiachen Yang, Hongyuan Zha

Traffic congestion in metropolitan areas is a world-wide problem that can be ameliorated by traffic lights that respond dynamically to real-time conditions.

Multi-agent Reinforcement Learning reinforcement-learning +1

Meta Learning with Relational Information for Short Sequences

1 code implementation NeurIPS 2019 Yujia Xie, Haoming Jiang, Feng Liu, Tuo Zhao, Hongyuan Zha

This paper proposes a new meta-learning method -- named HARMLESS (HAwkes Relational Meta LEarning method for Short Sequences) for learning heterogeneous point process models from short event sequence data along with a relational network.

Meta-Learning

DyRep: Learning Representations over Dynamic Graphs

2 code implementations ICLR 2019 Rakshit Trivedi, Mehrdad Farajtabar, Prasenjeet Biswal, Hongyuan Zha

We present DyRep - a novel modeling framework for dynamic graphs that posits representation learning as a latent mediation process bridging two observed processes namely -- dynamics of the network (realized as topological evolution) and dynamics on the network (realized as activities between nodes).

Dynamic Link Prediction Representation Learning

On Scalable and Efficient Computation of Large Scale Optimal Transport

no code implementations ICLR Workshop DeepGenStruct 2019 Yujia Xie, Minshuo Chen, Haoming Jiang, Tuo Zhao, Hongyuan Zha

Optimal Transport (OT) naturally arises in many machine learning applications, yet the heavy computational burden limits its wide-spread uses.

Domain Adaptation

Gromov-Wasserstein Learning for Graph Matching and Node Embedding

2 code implementations17 Jan 2019 Hongteng Xu, Dixin Luo, Hongyuan Zha, Lawrence Carin

A novel Gromov-Wasserstein learning framework is proposed to jointly match (align) graphs and learn embedding vectors for the associated graph nodes.

Graph Matching

CM3: Cooperative Multi-goal Multi-stage Multi-agent Reinforcement Learning

1 code implementation ICLR 2020 Jiachen Yang, Alireza Nakhaei, David Isele, Kikuo Fujimura, Hongyuan Zha

To address both challenges, we restructure the problem into a novel two-stage curriculum, in which single-agent goal attainment is learned prior to learning multi-agent cooperation, and we derive a new multi-goal multi-agent policy gradient with a credit function for localized credit assignment.

Autonomous Vehicles Efficient Exploration +3

Learning Deep Hidden Nonlinear Dynamics from Aggregate Data

no code implementations22 Jul 2018 Yisen Wang, Bo Dai, Lingkai Kong, Sarah Monazam Erfani, James Bailey, Hongyuan Zha

Learning nonlinear dynamics from diffusion data is a challenging problem since the individuals observed may be different at different time points, generally following an aggregate behaviour.

Supervised Reinforcement Learning with Recurrent Neural Network for Dynamic Treatment Recommendation

no code implementations4 Jul 2018 Lu Wang, Wei zhang, Xiaofeng He, Hongyuan Zha

Prior relevant studies recommend treatments either use supervised learning (e. g. matching the indicator signal which denotes doctor prescriptions), or reinforcement learning (e. g. maximizing evaluation signal which indicates cumulative reward from survival rates).

Recommendation Systems reinforcement-learning +1

Learning to Optimize via Wasserstein Deep Inverse Optimal Control

no code implementations22 May 2018 Yichen Wang, Le Song, Hongyuan Zha

We first propose a unified KL framework that generalizes existing maximum entropy inverse optimal control methods.

Generative Adversarial Network Recommendation Systems

Iterative Learning with Open-set Noisy Labels

1 code implementation CVPR 2018 Yisen Wang, Weiyang Liu, Xingjun Ma, James Bailey, Hongyuan Zha, Le Song, Shu-Tao Xia

We refer to this more complex scenario as the \textbf{open-set noisy label} problem and show that it is nontrivial in order to make accurate predictions.

Representation Learning over Dynamic Graphs

no code implementations11 Mar 2018 Rakshit Trivedi, Mehrdad Farajtabar, Prasenjeet Biswal, Hongyuan Zha

How can we effectively encode evolving information over dynamic graphs into low-dimensional representations?

Dynamic Link Prediction Representation Learning

A Fast Proximal Point Method for Computing Exact Wasserstein Distance

1 code implementation12 Feb 2018 Yujia Xie, Xiangfeng Wang, Ruijia Wang, Hongyuan Zha

However, as we will demonstrate, regularized variations with large regularization parameter will degradate the performance in several important machine learning applications, and small regularization parameter will fail due to numerical stability issues with existing algorithms.

BIG-bench Machine Learning

Learning to Match via Inverse Optimal Transport

no code implementations10 Feb 2018 Ruilin Li, Xiaojing Ye, Haomin Zhou, Hongyuan Zha

We emphasize that the discrete optimal transport plays the role of a variational principle which gives rise to an optimization-based framework for modeling the observed empirical matching data.

Visually Explainable Recommendation

no code implementations31 Jan 2018 Xu Chen, Yongfeng Zhang, Hongteng Xu, Yixin Cao, Zheng Qin, Hongyuan Zha

By this, we can not only provide recommendation results to the users, but also tell the users why an item is recommended by providing intuitive visual highlights in a personalized manner.

Explainable Recommendation Recommendation Systems

Decoupled Learning for Factorial Marked Temporal Point Processes

no code implementations21 Jan 2018 Weichang Wu, Junchi Yan, Xiaokang Yang, Hongyuan Zha

In conventional (multi-dimensional) marked temporal point process models, event is often encoded by a single discrete variable i. e. a marker.

Point Processes

tau-FPL: Tolerance-Constrained Learning in Linear Time

no code implementations15 Jan 2018 Ao Zhang, Nan Li, Jian Pu, Jun Wang, Junchi Yan, Hongyuan Zha

Learning a classifier with control on the false-positive rate plays a critical role in many machine learning applications.

Hawkes Processes for Invasive Species Modeling and Management

no code implementations12 Dec 2017 Amrita Gupta, Mehrdad Farajtabar, Bistra Dilkina, Hongyuan Zha

The spread of invasive species to new areas threatens the stability of ecosystems and causes major economic losses in agriculture and forestry.

Management

Predicting User Activity Level In Point Processes With Mass Transport Equation

no code implementations NeurIPS 2017 Yichen Wang, Xiaojing Ye, Hongyuan Zha, Le Song

Point processes are powerful tools to model user activities and have a plethora of applications in social sciences.

Point Processes

Learning Deep Mean Field Games for Modeling Large Population Behavior

no code implementations ICLR 2018 Jiachen Yang, Xiaojing Ye, Rakshit Trivedi, Huan Xu, Hongyuan Zha

We consider the problem of representing collective behavior of large populations and predicting the evolution of a population distribution over a discrete state space.

A unified framework for manifold landmarking

no code implementations25 Oct 2017 Hongteng Xu, Licheng Yu, Mark Davenport, Hongyuan Zha

Active manifold learning aims to select and label representative landmarks on a manifold from a given set of samples to improve semi-supervised manifold learning.

Learning Registered Point Processes from Idiosyncratic Observations

no code implementations ICML 2018 Hongteng Xu, Lawrence Carin, Hongyuan Zha

A parametric point process model is developed, with modeling based on the assumption that sequential observations often share latent phenomena, while also possessing idiosyncratic effects.

Point Processes

THAP: A Matlab Toolkit for Learning with Hawkes Processes

1 code implementation28 Aug 2017 Hongteng Xu, Hongyuan Zha

As a powerful tool of asynchronous event sequence analysis, point processes have been studied for a long time and achieved numerous successes in different fields.

Point Processes

Modeling The Intensity Function Of Point Process Via Recurrent Neural Networks

2 code implementations24 May 2017 Shuai Xiao, Junchi Yan, Stephen M. Chu, Xiaokang Yang, Hongyuan Zha

In this paper, we model the background by a Recurrent Neural Network (RNN) with its units aligned with time series indexes while the history effect is modeled by another RNN whose units are aligned with asynchronous events to capture the long-range dynamics.

Point Processes Time Series +1

Wasserstein Learning of Deep Generative Point Process Models

1 code implementation NeurIPS 2017 Shuai Xiao, Mehrdad Farajtabar, Xiaojing Ye, Junchi Yan, Le Song, Hongyuan Zha

Point processes are becoming very popular in modeling asynchronous sequential data due to their sound mathematical foundation and strength in modeling a variety of real-world phenomena.

Point Processes

Deep Extreme Multi-label Learning

1 code implementation12 Apr 2017 Wenjie Zhang, Junchi Yan, Xiangfeng Wang, Hongyuan Zha

Extreme multi-label learning (XML) or classification has been a practical and important problem since the boom of big data.

Classification Extreme Multi-Label Classification +2

Fake News Mitigation via Point Process Based Intervention

no code implementations ICML 2017 Mehrdad Farajtabar, Jiachen Yang, Xiaojing Ye, Huan Xu, Rakshit Trivedi, Elias Khalil, Shuang Li, Le Song, Hongyuan Zha

We propose the first multistage intervention framework that tackles fake news in social networks by combining reinforcement learning with a point process network activity model.

reinforcement-learning Reinforcement Learning (RL)

Recurrent Poisson Factorization for Temporal Recommendation

1 code implementation4 Mar 2017 Seyed Abbas Hosseini, Keivan Alizadeh, Ali Khodadadi, Ali Arabzadeh, Mehrdad Farajtabar, Hongyuan Zha, Hamid R. Rabiee

Poisson factorization is a probabilistic model of users and items for recommendation systems, where the so-called implicit consumer data is modeled by a factorized Poisson distribution.

Recommendation Systems

Learning Hawkes Processes from Short Doubly-Censored Event Sequences

1 code implementation ICML 2017 Hongteng Xu, Dixin Luo, Hongyuan Zha

Many real-world applications require robust algorithms to learn point processes based on a type of incomplete data --- the so-called short doubly-censored (SDC) event sequences.

Point Processes

A Dirichlet Mixture Model of Hawkes Processes for Event Sequence Clustering

1 code implementation NeurIPS 2017 Hongteng Xu, Hongyuan Zha

We propose an effective method to solve the event sequence clustering problems based on a novel Dirichlet mixture model of a special but significant type of point processes --- Hawkes process.

Bayesian Inference Clustering +1

Scalable Influence Maximization for Multiple Products in Continuous-Time Diffusion Networks

no code implementations8 Dec 2016 Nan Du, YIngyu Liang, Maria-Florina Balcan, Manuel Gomez-Rodriguez, Hongyuan Zha, Le Song

A typical viral marketing model identifies influential users in a social network to maximize a single product adoption assuming unlimited user attention, campaign budgets, and time.

Marketing

A constrained clustering based approach for matching a collection of feature sets

no code implementations12 Jun 2016 Junchi Yan, Zhe Ren, Hongyuan Zha, Stephen Chu

In this paper, we consider the problem of finding the feature correspondences among a collection of feature sets, by using their point-wise unary features.

Attribute Constrained Clustering +1

Self-Paced Multi-Task Learning

no code implementations6 Apr 2016 Changsheng Li, Junchi Yan, Fan Wei, Weishan Dong, Qingshan Liu, Hongyuan Zha

In this paper, we propose a novel multi-task learning (MTL) framework, called Self-Paced Multi-Task Learning (SPMTL).

Multi-Task Learning

A Self-Paced Regularization Framework for Multi-Label Learning

no code implementations22 Mar 2016 Changsheng Li, Fan Wei, Junchi Yan, Weishan Dong, Qingshan Liu, Xiao-Yu Zhang, Hongyuan Zha

In this paper, we propose a novel multi-label learning framework, called Multi-Label Self-Paced Learning (MLSPL), in an attempt to incorporate the self-paced learning strategy into multi-label learning regime.

Multi-Label Learning

Fractal Dimension Invariant Filtering and Its CNN-based Implementation

no code implementations CVPR 2017 Hongteng Xu, Junchi Yan, Nils Persson, Weiyao Lin, Hongyuan Zha

By adding a nonlinear post-processing step behind anisotropic filter banks, we demonstrate that the proposed filtering method is capable of preserving the local invariance of the fractal dimension of image.

Texture Classification

Patient Flow Prediction via Discriminative Learning of Mutually-Correcting Processes

no code implementations14 Feb 2016 Hongteng Xu, Weichang Wu, Shamim Nemati, Hongyuan Zha

By treating a sequence of transition events as a point process, we develop a novel framework for modeling patient flow through various CUs and jointly predicting patients' destination CUs and duration days.

feature selection Management

Learning Granger Causality for Hawkes Processes

no code implementations14 Feb 2016 Hongteng Xu, Mehrdad Farajtabar, Hongyuan Zha

In this paper, we propose an effective method, learning Granger causality, for a special but significant type of point processes --- Hawkes process.

Clustering Point Processes

Unsupervised Trajectory Clustering via Adaptive Multi-Kernel-Based Shrinkage

no code implementations ICCV 2015 Hongteng Xu, Yang Zhou, Weiyao Lin, Hongyuan Zha

Facing to the challenges of trajectory clustering, e. g., large variations within a cluster and ambiguities across clusters, we first introduce an adaptive multi-kernel-based estimation process to estimate the `shrunk' positions and speeds of trajectories' points.

Anomaly Detection Clustering +1

A Continuous-time Mutually-Exciting Point Process Framework for Prioritizing Events in Social Media

no code implementations13 Nov 2015 Mehrdad Farajtabar, Safoora Yousefi, Long Q. Tran, Le Song, Hongyuan Zha

In our experiments, we demonstrate that our algorithm is able to achieve the-state-of-the-art performance in terms of analyzing, predicting, and prioritizing events.

COEVOLVE: A Joint Point Process Model for Information Diffusion and Network Co-evolution

1 code implementation NeurIPS 2015 Mehrdad Farajtabar, Yichen Wang, Manuel Gomez Rodriguez, Shuang Li, Hongyuan Zha, Le Song

Information diffusion in online social networks is affected by the underlying network topology, but it also has the power to change it.

Discrete Hyper-Graph Matching

no code implementations CVPR 2015 Junchi Yan, Chao Zhang, Hongyuan Zha, Wei Liu, Xiaokang Yang, Stephen M. Chu

Evaluations on both synthetic and real-world data corroborate the efficiency of our method.

Graph Matching

Joint Active Learning with Feature Selection via CUR Matrix Decomposition

no code implementations4 Mar 2015 Changsheng Li, Xiangfeng Wang, Weishan Dong, Junchi Yan, Qingshan Liu, Hongyuan Zha

In particular, our method runs in one-shot without the procedure of iterative sample selection for progressive labeling.

Active Learning feature selection

A General Multi-Graph Matching Approach via Graduated Consistency-regularized Boosting

no code implementations20 Feb 2015 Junchi Yan, Minsu Cho, Hongyuan Zha, Xiaokang Yang, Stephen Chu

We propose multi-graph matching methods to incorporate the two aspects by boosting the affinity score, meanwhile gradually infusing the consistency as a regularizer.

Graph Matching

Shaping Social Activity by Incentivizing Users

no code implementations NeurIPS 2014 Mehrdad Farajtabar, Nan Du, Manuel Gomez Rodriguez, Isabel Valera, Hongyuan Zha, Le Song

Events in an online social network can be categorized roughly into endogenous events, where users just respond to the actions of their neighbors within the network, or exogenous events, where users take actions due to drives external to the network.

Linear Contour Learning: A Method for Supervised Dimension Reduction

no code implementations13 Aug 2014 Bing Li, Hongyuan Zha, Francesca Chiaromonte

We propose a novel approach to sufficient dimension reduction in regression, based on estimating contour directions of negligible variation for the response surface.

Dimensionality Reduction regression

Manifold Based Dynamic Texture Synthesis from Extremely Few Samples

no code implementations CVPR 2014 Hongteng Xu, Hongyuan Zha, Mark A. Davenport

In this paper, we present a novel method to synthesize dynamic texture sequences from extremely few samples, e. g., merely two possibly disparate frames, leveraging both Markov Random Fields (MRFs) and manifold learning.

Texture Synthesis

Scalable Influence Estimation in Continuous-Time Diffusion Networks

no code implementations NeurIPS 2013 Nan Du, Le Song, Manuel Gomez Rodriguez, Hongyuan Zha

If a piece of information is released from a media site, can it spread, in 1 month, to a million web pages?

Dirichlet-Bernoulli Alignment: A Generative Model for Multi-Class Multi-Label Multi-Instance Corpora

no code implementations NeurIPS 2009 Shuang-Hong Yang, Hongyuan Zha, Bao-Gang Hu

We propose Dirichlet-Bernoulli Alignment (DBA), a generative model for corpora in which each pattern (e. g., a document) contains a set of instances (e. g., paragraphs in the document) and belongs to multiple classes.

Entity Disambiguation General Classification +2

A General Boosting Method and its Application to Learning Ranking Functions for Web Search

no code implementations NeurIPS 2007 Zhaohui Zheng, Hongyuan Zha, Tong Zhang, Olivier Chapelle, Keke Chen, Gordon Sun

We present a general boosting method extending functional gradient boosting to optimize complex loss functions that are encountered in many machine learning problems.

Principal Manifolds and Nonlinear Dimension Reduction via Local Tangent Space Alignment

1 code implementation7 Dec 2002 Zhenyue Zhang, Hongyuan Zha

Nonlinear manifold learning from unorganized data points is a very challenging unsupervised learning and data visualization problem with a great variety of applications.

Data Visualization Dimensionality Reduction

Cannot find the paper you are looking for? You can Submit a new open access paper.