Leveraging Multi-facet Paths for Heterogeneous Graph Representation Learning

• URL: http://arxiv.org/abs/2407.20648v1
• Date: Tue, 30 Jul 2024 08:45:32 GMT
• Title: Leveraging Multi-facet Paths for Heterogeneous Graph Representation Learning
• Authors: JongWoo Kim, SeongYeub Chu, HyeongMin Park, Bryan Wong, MunYong Yi,
• Abstract summary: 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.
• Score: 2.603958690885184
• License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
• Abstract: Recent advancements in graph neural networks (GNNs) and heterogeneous GNNs (HGNNs) have advanced node embeddings and relationship learning for various tasks. However, existing methods often rely on domain-specific predefined meta-paths, which are coarse-grained and focus solely on aspects like node type, limiting their ability to capture complex interactions. We introduce MF2Vec, a model that uses multi-faceted (fine-grained) paths instead of predefined meta-paths. MF2Vec extracts paths via random walks and generates multi-faceted vectors, ignoring predefined schemas. This method learns diverse aspects of nodes and their relationships, constructs a homogeneous network, and creates node embeddings for classification, link prediction, and clustering. Extensive experiments show that MF2Vec outperforms existing methods, offering a more flexible and comprehensive framework for analyzing complex networks. The code is available at https://anonymous.4open.science/r/MF2Vec-6ABC.

Related papers

• Discovering Message Passing Hierarchies for Mesh-Based Physics Simulation [61.89682310797067]
  We introduce DHMP, which learns Dynamic Hierarchies for Message Passing networks through a differentiable node selection method. Our experiments demonstrate the effectiveness of DHMP, achieving 22.7% improvement on average compared to recent fixed-hierarchy message passing networks.
  arXiv  Detail & Related papers  (2024-10-03T15:18:00Z)
• HAGNN: Hybrid Aggregation for Heterogeneous Graph Neural Networks [15.22198175691658]
  Heterogeneous graph neural networks (GNNs) have been successful in handling heterogeneous graphs. Recent work pointed out that simple homogeneous graph model without meta-path can also achieve comparable results. We propose a novel framework to utilize the rich type semantic information in heterogeneous graphs comprehensively, namely HAGNN.
  arXiv  Detail & Related papers  (2023-07-04T10:40:20Z)
• Heterogeneous Graph Tree Networks [8.50892442127182]
  Heterogeneous graph neural networks (HGNNs) have attracted increasing research interest in recent three years. One class is meta-path-based HGNNs which either require domain knowledge to handcraft meta-paths or consume huge amount of time and memory to automatically construct meta-paths. We propose two models: Heterogeneous Graph Tree Convolutional Network (HetGTCN) and Heterogeneous Graph Tree Attention Network (HetGTAN)
  arXiv  Detail & Related papers  (2022-09-01T17:22:01Z)
• HybridGNN: Learning Hybrid Representation in Multiplex Heterogeneous Networks [26.549559266395775]
  We propose HybridGNN, an end-to-end graph neural network model with hybrid aggregation flows and hierarchical attentions. We show that HybridGNN achieves the best performance compared to several state-of-the-art baselines.
  arXiv  Detail & Related papers  (2022-08-03T13:39:47Z)
• 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)
• 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)
• Meta-Path-Free Representation Learning on Heterogeneous Networks [5.106061955284303]
  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.
  arXiv  Detail & Related papers  (2021-02-16T12:37:38Z)
• 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)
• Towards Deeper Graph Neural Networks with Differentiable Group Normalization [61.20639338417576]
  Graph neural networks (GNNs) learn the representation of a node by aggregating its neighbors. Over-smoothing is one of the key issues which limit the performance of GNNs as the number of layers increases. We introduce two over-smoothing metrics and a novel technique, i.e., differentiable group normalization (DGN)
  arXiv  Detail & Related papers  (2020-06-12T07:18:02Z)
• Unsupervised Differentiable Multi-aspect Network Embedding [52.981277420394846]
  We propose a novel end-to-end framework for multi-aspect network embedding, called asp2vec. Our proposed framework can be readily extended to heterogeneous networks.
  arXiv  Detail & Related papers  (2020-06-07T19:26:20Z)
• MAGNN: Metapath Aggregated Graph Neural Network for Heterogeneous Graph Embedding [36.6390478350677]
  We propose a new model named Metapath Aggregated Graph Neural Network (MAGNN) to boost the final performance. MAGNN employs three major components, i.e., the node content transformation to encapsulate input node attributes, the intra-metapath aggregation to incorporate intermediate semantic nodes, and the inter-metapath aggregation to combine messages from multiple metapaths. Experiments show that MAGNN achieves more accurate prediction results than state-of-the-art baselines.
  arXiv  Detail & Related papers  (2020-02-05T08:21:00Z)

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.