HeMI: Multi-view Embedding in Heterogeneous Graphs

• URL: http://arxiv.org/abs/2109.07008v1
• Date: Tue, 14 Sep 2021 23:04:42 GMT
• Title: HeMI: Multi-view Embedding in Heterogeneous Graphs
• Authors: Costas Mavromatis, George Karypis
• Abstract summary: representation learning of heterogeneous graphs (HGs) embeds the rich structure and semantics of such graphs into a low-dimensional space. We propose a self-supervised method that learns HG representations by relying on knowledge exchange and discovery among different HG structural semantics. We show that the proposed self-supervision both outperforms and improves competing methods by 1% and up to 10% for all tasks.
• Score: 8.87527266373087
• License: http://creativecommons.org/licenses/by/4.0/
• Abstract: Many real-world graphs involve different types of nodes and relations between nodes, being heterogeneous by nature. The representation learning of heterogeneous graphs (HGs) embeds the rich structure and semantics of such graphs into a low-dimensional space and facilitates various data mining tasks, such as node classification, node clustering, and link prediction. In this paper, we propose a self-supervised method that learns HG representations by relying on knowledge exchange and discovery among different HG structural semantics (meta-paths). Specifically, by maximizing the mutual information of meta-path representations, we promote meta-path information fusion and consensus, and ensure that globally shared semantics are encoded. By extensive experiments on node classification, node clustering, and link prediction tasks, we show that the proposed self-supervision both outperforms and improves competing methods by 1% and up to 10% for all tasks.

Related papers

• Histopathology Whole Slide Image Analysis with Heterogeneous Graph Representation Learning [78.49090351193269]
  We propose a novel graph-based framework to leverage the inter-relationships among different types of nuclei for WSI analysis. Specifically, we formulate the WSI as a heterogeneous graph with "nucleus-type" attribute to each node and a semantic attribute similarity to each edge. Our framework outperforms the state-of-the-art methods with considerable margins on various tasks.
  arXiv  Detail & Related papers  (2023-07-09T14:43:40Z)
• Geometry Contrastive Learning on Heterogeneous Graphs [50.58523799455101]
  This paper proposes a novel self-supervised learning method, termed as Geometry Contrastive Learning (GCL) GCL views a heterogeneous graph from Euclidean and hyperbolic perspective simultaneously, aiming to make a strong merger of the ability of modeling rich semantics and complex structures. Extensive experiments on four benchmarks data sets show that the proposed approach outperforms the strong baselines.
  arXiv  Detail & Related papers  (2022-06-25T03:54:53Z)
• A Variational Edge Partition Model for Supervised Graph Representation Learning [51.30365677476971]
  This paper introduces a graph generative process to model how the observed edges are generated by aggregating the node interactions over a set of overlapping node communities. We partition each edge into the summation of multiple community-specific weighted edges and use them to define community-specific GNNs. A variational inference framework is proposed to jointly learn a GNN based inference network that partitions the edges into different communities, these community-specific GNNs, and a GNN based predictor that combines community-specific GNNs for the end classification task.
  arXiv  Detail & Related papers  (2022-02-07T14:37:50Z)
• SHGNN: Structure-Aware Heterogeneous Graph Neural Network [77.78459918119536]
  This paper proposes a novel Structure-Aware Heterogeneous Graph Neural Network (SHGNN) to address the above limitations. We first utilize a feature propagation module to capture the local structure information of intermediate nodes in the meta-path. Next, we use a tree-attention aggregator to incorporate the graph structure information into the aggregation module on the meta-path. Finally, we leverage a meta-path aggregator to fuse the information aggregated from different meta-paths.
  arXiv  Detail & Related papers  (2021-12-12T14:18:18Z)
• HMSG: Heterogeneous Graph Neural Network based on Metapath Subgraph Learning [2.096172374930129]
  We propose a new heterogeneous graph neural network model named HMSG. We decompose the heterogeneous graph into multiple subgraphs. Each subgraph associates specific semantic and structural information. Through a type-specific attribute transformation, node attributes can also be transferred among different types of nodes.
  arXiv  Detail & Related papers  (2021-09-07T05:02:59Z)
• 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)
• Metapaths guided Neighbors aggregated Network for?Heterogeneous Graph Reasoning [5.228629954007088]
  We propose a Metapaths-guided Neighbors-aggregated Heterogeneous Graph Neural Network to improve performance. We conduct extensive experiments for the proposed MHN on three real-world heterogeneous graph datasets.
  arXiv  Detail & Related papers  (2021-03-11T05:42:06Z)
• Learning the Implicit Semantic Representation on Graph-Structured Data [57.670106959061634]
  Existing representation learning methods in graph convolutional networks are mainly designed by describing the neighborhood of each node as a perceptual whole. We propose a Semantic Graph Convolutional Networks (SGCN) that explores the implicit semantics by learning latent semantic-paths in graphs.
  arXiv  Detail & Related papers  (2021-01-16T16:18:43Z)
• Graph InfoClust: Leveraging cluster-level node information for unsupervised graph representation learning [12.592903558338444]
  We propose a graph representation learning method called Graph InfoClust. It seeks to additionally capture cluster-level information content. This optimization leads the node representations to capture richer information and nodal interactions, which improves their quality.
  arXiv  Detail & Related papers  (2020-09-15T09:33:20Z)
• Heterogeneous Graph Neural Network for Recommendation [35.58511642417818]
  How learn representative node embedding is the basis and core of personalized recommendation system. We propose Heterogeneous Graph neural network for Recommendation (HGRec) which injects high-order semantic into node embedding. Experimental results demonstrate the importance of rich high-order semantics and also show the potentially good interpretability of HGRec.
  arXiv  Detail & Related papers  (2020-09-02T03:16:48Z)

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.