Meta-Path-Free Representation Learning on Heterogeneous Networks

• URL: http://arxiv.org/abs/2102.08120v1
• Date: Tue, 16 Feb 2021 12:37:38 GMT
• Title: Meta-Path-Free Representation Learning on Heterogeneous Networks
• Authors: Jie Zhang, Jinru Ding, Suyuan Liu, Hongyan Wu
• Abstract summary: We propose a novel meta-path-free representation learning on heterogeneous networks, namely Heterogeneous graph Convolutional Networks (HCN) The proposed method fuses the heterogeneous and develops a $k$-strata algorithm ($k$ is an integer) to capture the $k$-hop structural and semantic information. The experimental results demonstrate that the proposed method significantly outperforms the current state-of-the-art methods in a variety of analytic tasks.
• Score: 5.106061955284303
• License: http://creativecommons.org/licenses/by/4.0/
• Abstract: Real-world networks and knowledge graphs are usually heterogeneous networks. Representation learning on heterogeneous networks is not only a popular but a pragmatic research field. The main challenge comes from the heterogeneity -- the diverse types of nodes and edges. Besides, for a given node in a HIN, the significance of a neighborhood node depends not only on the structural distance but semantics. How to effectively capture both structural and semantic relations is another challenge. The current state-of-the-art methods are based on the algorithm of meta-path and therefore have a serious disadvantage -- the performance depends on the arbitrary choosing of meta-path(s). However, the selection of meta-path(s) is experience-based and time-consuming. In this work, we propose a novel meta-path-free representation learning on heterogeneous networks, namely Heterogeneous graph Convolutional Networks (HCN). The proposed method fuses the heterogeneity and develops a $k$-strata algorithm ($k$ is an integer) to capture the $k$-hop structural and semantic information in heterogeneous networks. To the best of our knowledge, this is the first attempt to break out of the confinement of meta-paths for representation learning on heterogeneous networks. We carry out extensive experiments on three real-world heterogeneous networks. The experimental results demonstrate that the proposed method significantly outperforms the current state-of-the-art methods in a variety of analytic tasks.

Related papers

• Leveraging Multi-facet Paths for Heterogeneous Graph Representation Learning [2.603958690885184]
  We introduce MF2Vec, a model that uses multi-faceted (fine-grained) paths instead of predefined meta-paths. This method learns diverse aspects of nodes and their relationships, constructs a homogeneous network, and creates node embeddings for classification, link prediction, and clustering.
  arXiv  Detail & Related papers  (2024-07-30T08:45:32Z)
• RAW-GNN: RAndom Walk Aggregation based Graph Neural Network [48.139599737263445]
  We introduce a novel aggregation mechanism and develop a RAndom Walk Aggregation-based Graph Neural Network (called RAW-GNN) method. The new method utilizes breadth-first random walk search to capture homophily information and depth-first search to collect heterophily information. It replaces the conventional neighborhoods with path-based neighborhoods and introduces a new path-based aggregator based on Recurrent Neural Networks.
  arXiv  Detail & Related papers  (2022-06-28T12:19:01Z)
• Representation Learning on Heterostructures via Heterogeneous Anonymous Walks [9.94967091840104]
  We take the first step for representation learning on heterostructures, which is very challenging due to their highly diverse combinations of node types and underlying structures. We propose a theoretically guaranteed technique called heterogeneous anonymous walk embedding (HAW) and its variant coarse HAW (CHAW) We then devise the heterogeneous anonymous walk embedding (HAWE) and its variant coarse HAWE in a data-driven manner to circumvent using an extremely large number of possible walks and train embeddings.
  arXiv  Detail & Related papers  (2022-01-18T13:28:42Z)
• 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)
• Embedding Heterogeneous Networks into Hyperbolic Space Without Meta-path [9.153817737157365]
  We propose a novel self-guided random walk method that does not require meta-path for embedding heterogeneous networks into hyperbolic space. We conduct thorough experiments for the tasks of network reconstruction and link prediction on two public datasets.
  arXiv  Detail & Related papers  (2021-06-18T05:24:13Z)
• 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)
• 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)
• TriNE: Network Representation Learning for Tripartite Heterogeneous Networks [8.93957397187611]
  We develop a tripartite heterogeneous network embedding called TriNE. The method considers unique user-item-tag tripartite relationships, to build an objective function to model explicit relationships between nodes. Experiments on real-world tripartite networks validate the performance of TriNE for the online user response prediction.
  arXiv  Detail & Related papers  (2020-10-14T05:30:09Z)
• A Multi-Semantic Metapath Model for Large Scale Heterogeneous Network Representation Learning [52.83948119677194]
  We propose a multi-semantic metapath (MSM) model for large scale heterogeneous representation learning. Specifically, we generate multi-semantic metapath-based random walks to construct the heterogeneous neighborhood to handle the unbalanced distributions. We conduct systematical evaluations for the proposed framework on two challenging datasets: Amazon and Alibaba.
  arXiv  Detail & Related papers  (2020-07-19T22:50:20Z)
• Detecting Communities in Heterogeneous Multi-Relational Networks:A Message Passing based Approach [89.19237792558687]
  Community is a common characteristic of networks including social networks, biological networks, computer and information networks. We propose an efficient message passing based algorithm to simultaneously detect communities for all homogeneous networks.
  arXiv  Detail & Related papers  (2020-04-06T17:36:24Z)

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.