Reinforcement Learning Enhanced Heterogeneous Graph Neural Network

• URL: http://arxiv.org/abs/2010.13735v1
• Date: Mon, 26 Oct 2020 17:22:24 GMT
• Title: Reinforcement Learning Enhanced Heterogeneous Graph Neural Network
• Authors: Zhiqiang Zhong and Cheng-Te Li and Jun Pang
• Abstract summary: We present a Reinforcement Learning enhanced Heterogeneous Graph Neural Network (RL-HGNN) to design different meta-paths for the nodes in a Heterogeneous Information Networks (HINs) Specifically, RL-HGNN models the meta-path design process as a Markov Decision Process and uses a policy network to adaptively design a meta-path for each node to learn its effective representations. Experimental results demonstrate the effectiveness of RL-HGNN, and reveals that it can identify meaningful meta-paths that would have been ignored by human knowledge.
• Score: 13.720544777078642
• License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
• Abstract: Heterogeneous Information Networks (HINs), involving a diversity of node types and relation types, are pervasive in many real-world applications. Recently, increasing attention has been paid to heterogeneous graph representation learning (HGRL) which aims to embed rich structural and semantics information in HIN into low-dimensional node representations. To date, most HGRL models rely on manual customisation of meta paths to capture the semantics underlying the given HIN. However, the dependency on the handcrafted meta-paths requires rich domain knowledge which is extremely difficult to obtain for complex and semantic rich HINs. Moreover, strictly defined meta-paths will limit the HGRL's access to more comprehensive information in HINs. To fully unleash the power of HGRL, we present a Reinforcement Learning enhanced Heterogeneous Graph Neural Network (RL-HGNN), to design different meta-paths for the nodes in a HIN. Specifically, RL-HGNN models the meta-path design process as a Markov Decision Process and uses a policy network to adaptively design a meta-path for each node to learn its effective representations. The policy network is trained with deep reinforcement learning by exploiting the performance of the model on a downstream task. We further propose an extension, RL-HGNN++, to ameliorate the meta-path design procedure and accelerate the training process. Experimental results demonstrate the effectiveness of RL-HGNN, and reveals that it can identify meaningful meta-paths that would have been ignored by human knowledge.

Related papers

• DiRW: Path-Aware Digraph Learning for Heterophily [23.498557237805414]
  Graph neural network (GNN) has emerged as a powerful representation learning tool for graph-structured data. We propose Directed Random Walk (DiRW), which can be viewed as a plug-and-play strategy or an innovative neural architecture. DiRW incorporates a direction-aware path sampler optimized from perspectives of walk probability, length, and number.
  arXiv  Detail & Related papers  (2024-10-14T09:26:56Z)
• Language Models are Graph Learners [70.14063765424012]
  Language Models (LMs) are challenging the dominance of domain-specific models, including Graph Neural Networks (GNNs) and Graph Transformers (GTs) We propose a novel approach that empowers off-the-shelf LMs to achieve performance comparable to state-of-the-art GNNs on node classification tasks.
  arXiv  Detail & Related papers  (2024-10-03T08:27:54Z)
• Enhancing Graph Neural Networks with Limited Labeled Data by Actively Distilling Knowledge from Large Language Models [30.867447814409623]
  Graph neural networks (GNNs) have great ability in node classification, a fundamental task on graphs. We propose a novel approach that integrates Large Language Models (LLMs) and GNNs. Our model in improving node classification accuracy with considerably limited labeled data, surpassing state-of-the-art baselines by significant margins.
  arXiv  Detail & Related papers  (2024-07-19T02:34:10Z)
• Enhancing Intra-class Information Extraction for Heterophilous Graphs: One Neural Architecture Search Approach [41.84399177525008]
  We propose IIE-GNN (Intra-class Information Enhanced Graph Neural Networks) to achieve two improvements. A unified framework is proposed based on the literature, in which the intra-class information from the node itself and neighbors can be extracted. We also conduct experiments to show that IIE-GNN can improve the model performance by designing node-wise GNNs to enhance intra-class information extraction.
  arXiv  Detail & Related papers  (2022-11-20T14:37:09Z)
• Higher-Order Attribute-Enhancing Heterogeneous Graph Neural Networks [67.25782890241496]
  We propose a higher-order Attribute-Enhancing Graph Neural Network (HAEGNN) for heterogeneous network representation learning. HAEGNN simultaneously incorporates meta-paths and meta-graphs for rich, heterogeneous semantics. It shows superior performance against the state-of-the-art methods in node classification, node clustering, and visualization.
  arXiv  Detail & Related papers  (2021-04-16T04:56:38Z)
• Uniting Heterogeneity, Inductiveness, and Efficiency for Graph Representation Learning [68.97378785686723]
  graph neural networks (GNNs) have greatly advanced the performance of node representation learning on graphs. A majority class of GNNs are only designed for homogeneous graphs, leading to inferior adaptivity to the more informative heterogeneous graphs. We propose a novel inductive, meta path-free message passing scheme that packs up heterogeneous node features with their associated edges from both low- and high-order neighbor nodes.
  arXiv  Detail & Related papers  (2021-04-04T23:31:39Z)
• Optimizing Memory Placement using Evolutionary Graph Reinforcement Learning [56.83172249278467]
  We introduce Evolutionary Graph Reinforcement Learning (EGRL), a method designed for large search spaces. We train and validate our approach directly on the Intel NNP-I chip for inference. We additionally achieve 28-78% speed-up compared to the native NNP-I compiler on all three workloads.
  arXiv  Detail & Related papers  (2020-07-14T18:50:12Z)
• GCN for HIN via Implicit Utilization of Attention and Meta-paths [104.24467864133942]
  Heterogeneous information network (HIN) embedding aims to map the structure and semantic information in a HIN to distributed representations. We propose a novel neural network method via implicitly utilizing attention and meta-paths. We first use the multi-layer graph convolutional network (GCN) framework, which performs a discriminative aggregation at each layer. We then give an effective relaxation and improvement via introducing a new propagation operation which can be separated from aggregation.
  arXiv  Detail & Related papers  (2020-07-06T11:09:40Z)
• Policy-GNN: Aggregation Optimization for Graph Neural Networks [60.50932472042379]
  Graph neural networks (GNNs) aim to model the local graph structures and capture the hierarchical patterns by aggregating the information from neighbors. It is a challenging task to develop an effective aggregation strategy for each node, given complex graphs and sparse features. We propose Policy-GNN, a meta-policy framework that models the sampling procedure and message passing of GNNs into a combined learning process.
  arXiv  Detail & Related papers  (2020-06-26T17:03:06Z)
• Interpretable and Efficient Heterogeneous Graph Convolutional Network [27.316334213279973]
  We propose an interpretable and efficient Heterogeneous Graph Convolutional Network (ie-HGCN) to learn the representations of objects in Heterogeneous Information Network (HINs) ie-HGCN can automatically extract useful meta-paths for each object from all possible meta-paths within a length limit. It can also reduce the computational cost by avoiding intermediate HIN transformation and neighborhood attention.
  arXiv  Detail & Related papers  (2020-05-27T06:06:00Z)

This list is automatically generated from the titles and abstracts of the papers in this site.

This site does not guarantee the quality of this site (including all information) and is not responsible for any consequences.