GTC: GNN-Transformer Co-contrastive Learning for Self-supervised Heterogeneous Graph Representation

• URL: http://arxiv.org/abs/2403.15520v1
• Date: Fri, 22 Mar 2024 12:22:44 GMT
• Title: GTC: GNN-Transformer Co-contrastive Learning for Self-supervised Heterogeneous Graph Representation
• Authors: Yundong Sun, Dongjie Zhu, Yansong Wang, Zhaoshuo Tian,
• Abstract summary: This paper proposes a collaborative learning scheme for GNN-Transformer and constructs GTC architecture. For the Transformer branch, we propose Metapath-aware Hop2Token and CG-Hetphormer, which can cooperate with GNN to attentively encode neighborhood information from different levels. Experiments on real datasets show that GTC exhibits superior performance compared with state-of-the-art methods.
• Score: 0.9249657468385781
• License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
• Abstract: Graph Neural Networks (GNNs) have emerged as the most powerful weapon for various graph tasks due to the message-passing mechanism's great local information aggregation ability. However, over-smoothing has always hindered GNNs from going deeper and capturing multi-hop neighbors. Unlike GNNs, Transformers can model global information and multi-hop interactions via multi-head self-attention and a proper Transformer structure can show more immunity to the over-smoothing problem. So, can we propose a novel framework to combine GNN and Transformer, integrating both GNN's local information aggregation and Transformer's global information modeling ability to eliminate the over-smoothing problem? To realize this, this paper proposes a collaborative learning scheme for GNN-Transformer and constructs GTC architecture. GTC leverages the GNN and Transformer branch to encode node information from different views respectively, and establishes contrastive learning tasks based on the encoded cross-view information to realize self-supervised heterogeneous graph representation. For the Transformer branch, we propose Metapath-aware Hop2Token and CG-Hetphormer, which can cooperate with GNN to attentively encode neighborhood information from different levels. As far as we know, this is the first attempt in the field of graph representation learning to utilize both GNN and Transformer to collaboratively capture different view information and conduct cross-view contrastive learning. The experiments on real datasets show that GTC exhibits superior performance compared with state-of-the-art methods. Codes can be available at https://github.com/PHD-lanyu/GTC.

Related papers

• Learning Graph Quantized Tokenizers for Transformers [28.79505338383552]
  Graph Transformers (GTs) have emerged as a leading model in deep learning, outperforming Graph Neural Networks (GNNs) in various graph learning tasks. We introduce GQT (textbfGraph textbfQuantized textbfTokenizer), which decouples tokenizer training from Transformer training by leveraging graph self-supervised learning. By combining the GQT with token modulation, a Transformer encoder achieves state-of-the-art performance on 16 out of 18 benchmarks, including large-scale homophilic and heterophilic datasets.
  arXiv  Detail & Related papers  (2024-10-17T17:38:24Z)
• DuoFormer: Leveraging Hierarchical Visual Representations by Local and Global Attention [1.5624421399300303]
  We propose a novel hierarchical transformer model that adeptly integrates the feature extraction capabilities of Convolutional Neural Networks (CNNs) with the advanced representational potential of Vision Transformers (ViTs) Addressing the lack of inductive biases and dependence on extensive training datasets in ViTs, our model employs a CNN backbone to generate hierarchical visual representations. These representations are then adapted for transformer input through an innovative patch tokenization.
  arXiv  Detail & Related papers  (2024-07-18T22:15:35Z)
• Cell Graph Transformer for Nuclei Classification [78.47566396839628]
  We develop a cell graph transformer (CGT) that treats nodes and edges as input tokens to enable learnable adjacency and information exchange among all nodes. Poorly features can lead to noisy self-attention scores and inferior convergence. We propose a novel topology-aware pretraining method that leverages a graph convolutional network (GCN) to learn a feature extractor.
  arXiv  Detail & Related papers  (2024-02-20T12:01:30Z)
• TransGNN: Harnessing the Collaborative Power of Transformers and Graph Neural Networks for Recommender Systems [31.922581157563272]
  Graph Neural Networks (GNNs) have emerged as promising solutions for collaborative filtering (CF) We propose TransGNN, a novel model that integrates Transformer and GNN layers in an alternating fashion to mutually enhance their capabilities.
  arXiv  Detail & Related papers  (2023-08-28T07:03:08Z)
• SGFormer: Simplifying and Empowering Transformers for Large-Graph Representations [75.71298846760303]
  We show that a one-layer attention can bring up surprisingly competitive performance across node property prediction benchmarks. We frame the proposed scheme as Simplified Graph Transformers (SGFormer), which is empowered by a simple attention model. We believe the proposed methodology alone enlightens a new technical path of independent interest for building Transformers on large graphs.
  arXiv  Detail & Related papers  (2023-06-19T08:03:25Z)
• Representing Long-Range Context for Graph Neural Networks with Global Attention [37.212747564546156]
  We propose the use of Transformer-based self-attention to learn long-range pairwise relationships. Our method, which we call GraphTrans, applies a permutation-invariant Transformer module after a standard GNN module. Our results suggest that purely-learning-based approaches without graph structure may be suitable for learning high-level, long-range relationships on graphs.
  arXiv  Detail & Related papers  (2022-01-21T18:16:21Z)
• Graph Neural Networks with Learnable Structural and Positional Representations [83.24058411666483]
  A major issue with arbitrary graphs is the absence of canonical positional information of nodes. We introduce Positional nodes (PE) of nodes, and inject it into the input layer, like in Transformers. We observe a performance increase for molecular datasets, from 2.87% up to 64.14% when considering learnable PE for both GNN classes.
  arXiv  Detail & Related papers  (2021-10-15T05:59:15Z)
• MSG-Transformer: Exchanging Local Spatial Information by Manipulating Messenger Tokens [129.10351459066501]
  We propose a specialized token for each region that serves as a messenger (MSG) By manipulating these MSG tokens, one can flexibly exchange visual information across regions. We then integrate the MSG token into a multi-scale architecture named MSG-Transformer.
  arXiv  Detail & Related papers  (2021-05-31T17:16:42Z)
• A Unified View on Graph Neural Networks as Graph Signal Denoising [49.980783124401555]
  Graph Neural Networks (GNNs) have risen to prominence in learning representations for graph structured data. In this work, we establish mathematically that the aggregation processes in a group of representative GNN models can be regarded as solving a graph denoising problem. We instantiate a novel GNN model, ADA-UGNN, derived from UGNN, to handle graphs with adaptive smoothness across nodes.
  arXiv  Detail & Related papers  (2020-10-05T04:57:18Z)
• Graph Neural Networks: Architectures, Stability and Transferability [176.3960927323358]
  Graph Neural Networks (GNNs) are information processing architectures for signals supported on graphs. They are generalizations of convolutional neural networks (CNNs) in which individual layers contain banks of graph convolutional filters.
  arXiv  Detail & Related papers  (2020-08-04T18:57:36Z)

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.