Reinforcement Learning on Graphs: A Survey (2022-04-13T00:00:00.000000Z)

TL;DR

This survey provides a comprehensive overview of these fusion works to Graph Reinforcement Learning (GRL) as a unified formulation and creates a collection of papers for both interested scholars who want to enter this rapidly developing domain and experts who would like to compare GRL methods.

Abstract

Graph mining tasks arise from many different application domains, including social networks, biological networks, transportation, and E-commerce, which have been receiving great attention from the theoretical and algorithmic design communities in recent years, and there has been some pioneering work employing the research-rich Reinforcement Learning (RL) techniques to address graph mining tasks. However, these fusion works are dispersed in different research domains, which makes them difficult to compare. In this survey, we provide a comprehensive overview of these fusion works and generalize these works to Graph Reinforcement Learning (GRL) as a unified formulation. We further discuss the applications of GRL methods across various domains, and simultaneously propose the key challenges and advantages of integrating graph mining and RL methods. Furthermore, we propose important directions and challenges to be solved in the future. To our knowledge, this is the latest work on a comprehensive survey of GRL, this work provides a global view and a learning resource for scholars. Based on our review, we create a collection of papers for both interested scholars who want to enter this rapidly developing domain and experts who would like to compare GRL methods.

Authors

Mingshuo Nie

1 papers

Dongming Chen

1 papers

Dongqi Wang

1 papers

TL;DR

Abstract

Authors

References222 items

Influence Maximization in Complex Networks by Using Evolutionary Deep Reinforcement Learning

RedPacketBike: A Graph-Based Demand Modeling and Crowd-Driven Station Rebalancing Framework for Bike Sharing Systems

Multi-View Tensor Graph Neural Networks Through Reinforced Aggregation

NetRL: Task-Aware Network Denoising via Deep Reinforcement Learning

Deep Reinforcement Learning With Graph Representation for Vehicle Repositioning

SparRL: Graph Sparsification via Deep Reinforcement Learning

Explaining Deep Graph Networks via Input Perturbation

Step by step: A hierarchical framework for multi-hop knowledge graph reasoning with reinforcement learning

Deep Reinforcement Learning Guided Graph Neural Networks for Brain Network Analysis

Automated Data Augmentations for Graph Classification

Network Representation Learning Algorithm Based on Complete Subgraph Folding

Network Embedding Algorithm Taking in Variational Graph AutoEncoder

Reinforced, Incremental and Cross-Lingual Event Detection From Social Messages

Interpretable and Effective Reinforcement Learning for Attacking against Graph-based Rumor Detection

A novel embedding learning framework for relation completion and recommendation based on graph neural network and multi-task learning

Solving Dynamic Graph Problems with Multi-Attention Deep Reinforcement Learning

Learning self-driven collective dynamics with graph networks

Dynamic knowledge graph reasoning based on deep reinforcement learning

A new ensemble deep graph reinforcement learning network for spatio-temporal traffic volume forecasting in a freeway network

Multi-hop Knowledge Graph Reasoning Based on Hyperbolic Knowledge Graph Embedding and Reinforcement Learning

AFGSL: Automatic Feature Generation based on Graph Structure Learning

GQNAS: Graph Q Network for Neural Architecture Search

Vulcan: Solving the Steiner Tree Problem with Graph Neural Networks and Deep Reinforcement Learning

A Weighted Heterogeneous Graph-Based Dialog System

Dynamic graph convolutional network for long-term traffic flow prediction with reinforcement learning

ACE-HGNN: Adaptive Curvature Exploration Hyperbolic Graph Neural Network

Model-Based Transfer Reinforcement Learning Based on Graphical Model Representations

TimeTraveler: Reinforcement Learning for Temporal Knowledge Graph Forecasting

Full-Scale Information Diffusion Prediction With Reinforced Recurrent Networks

Graph Adversarial Attack via Rewiring

RLPath: a knowledge graph link prediction method using reinforcement learning based attentive relation path searching and representation learning

Graph neural network and reinforcement learning for multi‐agent cooperative control of connected autonomous vehicles

Unified Conversational Recommendation Policy Learning via Graph-based Reinforcement Learning

Ordering-Based Causal Discovery with Reinforcement Learning

Deep Graph Convolutional Reinforcement Learning for Financial Portfolio Management - DeepPocket

Hypernetwork Dismantling via Deep Reinforcement Learning

GraphLight: Graph-based Reinforcement Learning for Traffic Signal Control

Reinforced Neighborhood Selection Guided Multi-Relational Graph Neural Networks

Reinforcement Learning For Data Poisoning on Graph Neural Networks

On Explainability of Graph Neural Networks via Subgraph Explorations

SUGAR: Subgraph Neural Network with Reinforcement Pooling and Self-Supervised Mutual Information Mechanism

Reinforcement Learning with Dual Attention Guided Graph Convolution for Relation Extraction

MemoryPath: A deep reinforcement learning framework for incorporating memory component into knowledge graph reasoning

Combining Deep Reinforcement Learning With Graph Neural Networks for Optimal VNF Placement

Explainability in Graph Neural Networks: A Taxonomic Survey

GAEA: Graph Augmentation for Equitable Access via Reinforcement Learning

DAPath: Distance-aware knowledge graph reasoning based on deep reinforcement learning

GRL: Knowledge graph completion with GAN-based reinforcement learning

Auto Graph Encoder-Decoder for Neural Network Pruning

Parameterized Explainer for Graph Neural Network

Personalised meta-path generation for heterogeneous graph neural networks

Reinforcement Learning Enhanced Heterogeneous Graph Neural Network

A survey of community detection methods in multilayer networks

PGM-Explainer: Probabilistic Graphical Model Explanations for Graph Neural Networks

Controlling Graph Dynamics with Reinforcement Learning and Graph Neural Networks

Enhancing Graph Neural Network-based Fraud Detectors against Camouflaged Fraudsters

Lifelong Property Price Prediction: A Case Study for the Toronto Real Estate Market

Reinforcement Learning based Recommendation with Graph Convolutional Q-network

Incremental Mobile User Profiling: Reinforcement Learning with Spatial Knowledge Graph for Modeling Event Streams

Reasoning Like Human: Hierarchical Reinforcement Learning for Knowledge Graph Reasoning

Learning for Graph Matching and Related Combinatorial Optimization Problems

An Efficient Neighborhood-based Interaction Model for Recommendation on Heterogeneous Graph

Graph Neural Architecture Search

Policy-GNN: Aggregation Optimization for Graph Neural Networks

Graph Backdoor

Backdoor Attacks to Graph Neural Networks

Risk-Aware Identification of Highly Suspected COVID-19 Cases in Social IoT: A Joint Graph Theory and Reinforcement Learning Approach

Interactive Recommender System via Knowledge Graph-enhanced Reinforcement Learning

Learning TSP Requires Rethinking Generalization

DeepGraphMolGen, a multi-objective, computational strategy for generating molecules with desirable properties: a graph convolution and reinforcement learning approach

XGNN: Towards Model-Level Explanations of Graph Neural Networks

ADRL: An attention-based deep reinforcement learning framework for knowledge graph reasoning

Graph Policy Network for Transferable Active Learning on Graphs

OpenGraphGym: A Parallel Reinforcement Learning Framework for Graph Optimization Problems

Finding key players in complex networks through deep reinforcement learning

Learning Network Representation Through Reinforcement Learning