Bootstrap Latents of Nodes and Neighbors for Graph Self-Supervised Learning

• URL: http://arxiv.org/abs/2408.05087v1
• Date: Fri, 9 Aug 2024 14:17:52 GMT
• Title: Bootstrap Latents of Nodes and Neighbors for Graph Self-Supervised Learning
• Authors: Yunhui Liu, Huaisong Zhang, Tieke He, Tao Zheng, Jianhua Zhao,
• Abstract summary: Contrastive learning requires negative samples to prevent model collapse and learn discriminative representations. We introduce a cross-attention module to predict the supportiveness score of a neighbor with respect to the anchor node. Our method mitigates class collision from negative and noisy positive samples, concurrently enhancing intra-class compactness.
• Score: 27.278097015083343
• License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
• Abstract: Contrastive learning is a significant paradigm in graph self-supervised learning. However, it requires negative samples to prevent model collapse and learn discriminative representations. These negative samples inevitably lead to heavy computation, memory overhead and class collision, compromising the representation learning. Recent studies present that methods obviating negative samples can attain competitive performance and scalability enhancements, exemplified by bootstrapped graph latents (BGRL). However, BGRL neglects the inherent graph homophily, which provides valuable insights into underlying positive pairs. Our motivation arises from the observation that subtly introducing a few ground-truth positive pairs significantly improves BGRL. Although we can't obtain ground-truth positive pairs without labels under the self-supervised setting, edges in the graph can reflect noisy positive pairs, i.e., neighboring nodes often share the same label. Therefore, we propose to expand the positive pair set with node-neighbor pairs. Subsequently, we introduce a cross-attention module to predict the supportiveness score of a neighbor with respect to the anchor node. This score quantifies the positive support from each neighboring node, and is encoded into the training objective. Consequently, our method mitigates class collision from negative and noisy positive samples, concurrently enhancing intra-class compactness. Extensive experiments are conducted on five benchmark datasets and three downstream task node classification, node clustering, and node similarity search. The results demonstrate that our method generates node representations with enhanced intra-class compactness and achieves state-of-the-art performance.

Related papers

• Negative-Free Self-Supervised Gaussian Embedding of Graphs [29.26519601854811]
  Graph Contrastive Learning (GCL) has emerged as a promising graph self-supervised learning framework. We propose a negative-free objective to achieve uniformity, inspired by the fact that points distributed according to a normalized isotropic Gaussian are uniformly spread across the unit hypersphere. Our proposal achieves competitive performance with fewer parameters, shorter training times, and lower memory consumption compared to existing GCL methods.
  arXiv  Detail & Related papers  (2024-11-02T07:04:40Z)
• Reliable Node Similarity Matrix Guided Contrastive Graph Clustering [51.23437296378319]
  We introduce a new framework, Reliable Node Similarity Matrix Guided Contrastive Graph Clustering (NS4GC) Our method introduces node-neighbor alignment and semantic-aware sparsification, ensuring the node similarity matrix is both accurate and efficiently sparse.
  arXiv  Detail & Related papers  (2024-08-07T13:36:03Z)
• Smoothed Graph Contrastive Learning via Seamless Proximity Integration [30.247207861739245]
  Graph contrastive learning (GCL) aligns node representations by classifying node pairs into positives and negatives. We present a Smoothed Graph Contrastive Learning model (SGCL) that injects proximity information associated with positive/negative pairs in the contrastive loss. The proposed SGCL adjusts the penalties associated with node pairs in contrastive loss by incorporating three distinct smoothing techniques.
  arXiv  Detail & Related papers  (2024-02-23T11:32:46Z)
• Pseudo Contrastive Learning for Graph-based Semi-supervised Learning [67.37572762925836]
  Pseudo Labeling is a technique used to improve the performance of Graph Neural Networks (GNNs) We propose a general framework for GNNs, termed Pseudo Contrastive Learning (PCL)
  arXiv  Detail & Related papers  (2023-02-19T10:34:08Z)
• STERLING: Synergistic Representation Learning on Bipartite Graphs [78.86064828220613]
  A fundamental challenge of bipartite graph representation learning is how to extract node embeddings. Most recent bipartite graph SSL methods are based on contrastive learning which learns embeddings by discriminating positive and negative node pairs. We introduce a novel synergistic representation learning model (STERLING) to learn node embeddings without negative node pairs.
  arXiv  Detail & Related papers  (2023-01-25T03:21:42Z)
• Cluster-guided Contrastive Graph Clustering Network [53.16233290797777]
  We propose a Cluster-guided Contrastive deep Graph Clustering network (CCGC) We construct two views of the graph by designing special Siamese encoders whose weights are not shared between the sibling sub-networks. To construct semantic meaningful negative sample pairs, we regard the centers of different high-confidence clusters as negative samples.
  arXiv  Detail & Related papers  (2023-01-03T13:42:38Z)
• Enhancing Graph Contrastive Learning with Node Similarity [4.60032347615771]
  Graph contrastive learning (GCL) is a representative framework for self-supervised learning. GCL learns node representations by contrasting semantically similar nodes (positive samples) and dissimilar nodes (negative samples) with anchor nodes. We propose an enhanced objective that contains all positive samples and no false-negative samples.
  arXiv  Detail & Related papers  (2022-08-13T22:49:20Z)
• Structure-Aware Hard Negative Mining for Heterogeneous Graph Contrastive Learning [21.702342154458623]
  This work investigates Contrastive Learning (CL) on Graph Neural Networks (GNNs) We first generate multiple semantic views according to metapaths and network schemas. We then push node embeddings corresponding to different semantic views close to each other (positives) and pulling other embeddings apart (negatives) Considering the complex graph structure and the smoothing nature of GNNs, we propose a structure-aware hard negative mining scheme.
  arXiv  Detail & Related papers  (2021-08-31T14:44:49Z)
• Doubly Contrastive Deep Clustering [135.7001508427597]
  We present a novel Doubly Contrastive Deep Clustering (DCDC) framework, which constructs contrastive loss over both sample and class views. Specifically, for the sample view, we set the class distribution of the original sample and its augmented version as positive sample pairs. For the class view, we build the positive and negative pairs from the sample distribution of the class. In this way, two contrastive losses successfully constrain the clustering results of mini-batch samples in both sample and class level.
  arXiv  Detail & Related papers  (2021-03-09T15:15:32Z)
• Maximizing Cohesion and Separation in Graph Representation Learning: A Distance-aware Negative Sampling Approach [9.278968846447215]
  Unsupervised graph representation learning (GRL) is to learn a low-dimensional space of node embeddings that reflect the structure of a given unlabeled graph. Existing algorithms for this task rely on negative sampling objectives that maximize the similarity in node embeddings at nearby nodes. We present a novel Distance-aware Negative Sampling (DNS) which maximizes the separation of distant node-pairs.
  arXiv  Detail & Related papers  (2020-07-02T22:40:38Z)
• Understanding Negative Sampling in Graph Representation Learning [87.35038268508414]
  We show that negative sampling is as important as positive sampling in determining the optimization objective and the resulted variance. We propose Metropolis-Hastings (MCNS) to approximate the positive distribution with self-contrast approximation and accelerate negative sampling by Metropolis-Hastings. We evaluate our method on 5 datasets that cover extensive downstream graph learning tasks, including link prediction, node classification and personalized recommendation.
  arXiv  Detail & Related papers  (2020-05-20T06:25:21Z)

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.