
Influence Estimation and Maximization via Neural MeanField Dynamics
We propose a novel learning framework using neural meanfield (NMF) dyna...
read it

Permutation Invariant Policy Optimization for MeanField MultiAgent Reinforcement Learning: A Principled Approach
Multiagent reinforcement learning (MARL) becomes more challenging in th...
read it

Theoretical Study of Random Noise Defense against QueryBased BlackBox Attacks
The querybased blackbox attacks, which don't require any knowledge abo...
read it

Mean Field Game GAN
We propose a novel mean field games (MFGs) based GAN(generative adversar...
read it

GraphBased TriAttention Network for Answer Ranking in CQA
In communitybased question answering (CQA) platforms, automatic answer ...
read it

Reinforcement Learning for Adaptive Mesh Refinement
Largescale finite element simulations of complex physical systems gover...
read it

Dealing with NonStationarity in MultiAgent Reinforcement Learning via Trust Region Decomposition
Nonstationarity is one thorny issue in multiagent reinforcement learni...
read it

Structured Diversification Emergence via Reinforced Organization Control and Hierarchical Consensus Learning
When solving a complex task, humans will spontaneously form teams and to...
read it

Learning High Dimensional Wasserstein Geodesics
We propose a new formulation and learning strategy for computing the Was...
read it

Hawkes Processes on Graphons
We propose a novel framework for modeling multiple multivariate point pr...
read it

Generalize a Small Pretrained Model to Arbitrarily Large TSP Instances
For the traveling salesman problem (TSP), the existing supervised learni...
read it

Learning Graphons via Structured GromovWasserstein Barycenters
We propose a novel and principled method to learn a nonparametric graph ...
read it

A Hypergradient Approach to Robust Regression without Correspondence
We consider a regression problem, where the correspondence between input...
read it

Reliable Offpolicy Evaluation for Reinforcement Learning
In a sequential decisionmaking problem, offpolicy evaluation (OPE) est...
read it

Inductive Relational Matrix Completion
Data sparsity and coldstart issues emerge as two major bottlenecks for ...
read it

GraphOpt: Learning Optimization Models of Graph Formation
Formation mechanisms are fundamental to the study of complex networks, b...
read it

Structural Landmarking and Interaction Modelling: on Resolution Dilemmas in Graph Classification
Graph neural networks are promising architecture for learning and infere...
read it

Network Diffusions via Neural MeanField Dynamics
We propose a novel learning framework based on neural meanfield dynamic...
read it

HessianFree HighResolution Nesterov Acceleration for Sampling
We propose an acceleratedgradientbased MCMC method. It relies on a mod...
read it

HessianFree HighResolution Nesterov Accelerationfor Sampling
We propose an acceleratedgradientbased MCMC method. It relies on a mod...
read it

Learning to Incentivize Other Learning Agents
The challenge of developing powerful and general Reinforcement Learning ...
read it

F2A2: Flexible Fullydecentralized Approximate Actorcritic for Cooperative Multiagent Reinforcement Learning
Traditional centralized multiagent reinforcement learning (MARL) algori...
read it

Learning Cost Functions for Optimal Transport
Learning the cost function for optimal transport from observed transport...
read it

Transformer Hawkes Process
Modern data acquisition routinely produce massive amounts of event seque...
read it

Improving Sampling Accuracy of Stochastic Gradient MCMC Methods via Nonuniform Subsampling of Gradients
Common Stochastic Gradient MCMC methods approximate gradients by stochas...
read it

Beyond Clicks: Modeling MultiRelational Item Graph for SessionBased Target Behavior Prediction
Sessionbased target behavior prediction aims to predict the next item t...
read it

Differentiable Topk Operator with Optimal Transport
The topk operation, i.e., finding the k largest or smallest elements fr...
read it

HyperMeta Reinforcement Learning with Sparse Reward
Despite their success, existing meta reinforcement learning methods stil...
read it

Learning Structured Communication for Multiagent Reinforcement Learning
This work explores the largescale multiagent communication mechanism u...
read it

Statistical Guarantees of Generative Adversarial Networks for Distribution Estimation
Generative Adversarial Networks (GANs) have achieved great success in un...
read it

Learning Stochastic Behaviour of Aggregate Data
Learning nonlinear dynamics of aggregate data is a challenging problem s...
read it

Improving DomainAdapted Sentiment Classification by Deep Adversarial Mutual Learning
Domainadapted sentiment classification refers to training on a labeled ...
read it

Hierarchical Cooperative MultiAgent Reinforcement Learning with Skill Discovery
Human players in professional team sports achieve high level coordinatio...
read it

Heterogeneous Graphbased Knowledge Transfer for Generalized Zeroshot Learning
Generalized zeroshot learning (GZSL) tackles the problem of learning to...
read it

Single Episode Policy Transfer in Reinforcement Learning
Transfer and adaptation to new unknown environmental dynamics is a key c...
read it

Infinitehorizon OffPolicy Policy Evaluation with Multiple Behavior Policies
We consider offpolicy policy evaluation when the trajectory data are ge...
read it

Learning Robust Representations with Graph Denoising Policy Network
Graph representation learning, aiming to learn lowdimensional represent...
read it

Stein Bridging: Enabling Mutual Reinforcement between Explicit and Implicit Generative Models
Deep generative models are generally categorized into explicit models an...
read it

Integrating independent and centralized multiagent reinforcement learning for traffic signal network optimization
Traffic congestion in metropolitan areas is a worldwide problem that ca...
read it

Meta Learning with Relational Information for Short Sequences
This paper proposes a new metalearning method  named HARMLESS (HAwkes...
read it

Modeling Event Propagation via Graph Biased Temporal Point Process
Temporal point process is widely used for sequential data modeling. In t...
read it

Visual Anomaly Detection in Event Sequence Data
Anomaly detection is a common analytical task that aims to identify rare...
read it

Reinforcement Learning with Policy Mixture Model for Temporal Point Processes Clustering
Temporal point process is an expressive tool for modeling event sequence...
read it

On Scalable and Efficient Computation of Large Scale Optimal Transport
Optimal Transport (OT) naturally arises in many machine learning applica...
read it

GromovWasserstein Learning for Graph Matching and Node Embedding
A novel GromovWasserstein learning framework is proposed to jointly mat...
read it

CM3: Cooperative Multigoal Multistage Multiagent Reinforcement Learning
We propose CM3, a new deep reinforcement learning method for cooperative...
read it

LinkNBed: MultiGraph Representation Learning with Entity Linkage
Knowledge graphs have emerged as an important model for studying complex...
read it

Learning Deep Hidden Nonlinear Dynamics from Aggregate Data
Learning nonlinear dynamics from diffusion data is a challenging problem...
read it

Supervised Reinforcement Learning with Recurrent Neural Network for Dynamic Treatment Recommendation
Dynamic treatment recommendation systems based on largescale electronic...
read it

Learning to Optimize via Wasserstein Deep Inverse Optimal Control
We study the inverse optimal control problem in social sciences: we aim ...
read it
Hongyuan Zha
is this you? claim profile
Professor of Computing of Georgia Institute of Technology, Consultant at Yahoo, Scientific Advisor at proofpoint