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
- 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) - Relation Embedding based Graph Neural Networks for Handling
Heterogeneous Graph [58.99478502486377]
We propose a simple yet efficient framework to make the homogeneous GNNs have adequate ability to handle heterogeneous graphs.
Specifically, we propose Relation Embedding based Graph Neural Networks (RE-GNNs), which employ only one parameter per relation to embed the importance of edge type relations and self-loop connections.
arXiv Detail & Related papers (2022-09-23T05:24:18Z) - 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) - mSHINE: A Multiple-meta-paths Simultaneous Learning Framework for
Heterogeneous Information Network Embedding [15.400191040779376]
Heterogeneous information networks (HINs) are used to model objects with abundant information using explicit network structure.
Traditional network embedding algorithms are sub-optimal in capturing rich while potentially incompatible semantics provided by HINs.
mSHINE is designed to simultaneously learn multiple node representations for different meta-paths.
arXiv Detail & Related papers (2021-04-06T11:35:56Z) - 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) - Adaptive Universal Generalized PageRank Graph Neural Network [36.850433364139924]
Graph neural networks (GNNs) are designed to exploit both sources of evidence but they do not optimally trade-off their utility.
We introduce a new Generalized PageRank (GPR) GNN architecture that adaptively learns the GPR weights.
GPR-GNN offers significant performance improvement compared to existing techniques on both synthetic and benchmark data.
arXiv Detail & Related papers (2020-06-14T19:27:39Z) - 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.