Scalable Deep Metric Learning on Attributed Graphs

• URL: http://arxiv.org/abs/2411.13014v1
• Date: Wed, 20 Nov 2024 03:34:31 GMT
• Title: Scalable Deep Metric Learning on Attributed Graphs
• Authors: Xiang Li, Gagan Agrawal, Ruoming Jin, Rajiv Ramnath,
• Abstract summary: We develop a graph embedding method, which is based on extending deep metric and unbiased contrastive learning techniques. Based on a multi-classt loss function, we present two algorithms -- DMT for semi-supervised learning and DMAT-i for the unsupervised case.
• Score: 10.092560681589578
• License:
• Abstract: We consider the problem of constructing embeddings of large attributed graphs and supporting multiple downstream learning tasks. We develop a graph embedding method, which is based on extending deep metric and unbiased contrastive learning techniques to 1) work with attributed graphs, 2) enabling a mini-batch based approach, and 3) achieving scalability. Based on a multi-class tuplet loss function, we present two algorithms -- DMT for semi-supervised learning and DMAT-i for the unsupervised case. Analyzing our methods, we provide a generalization bound for the downstream node classification task and for the first time relate tuplet loss to contrastive learning. Through extensive experiments, we show high scalability of representation construction, and in applying the method for three downstream tasks (node clustering, node classification, and link prediction) better consistency over any single existing method.

Related papers

• Unsupervised Multiplex Graph Learning with Complementary and Consistent Information [20.340977728674698]
  Unsupervised multiplex graph learning (UMGL) has been shown to achieve significant effectiveness for different downstream tasks. Previous methods usually overlook the issues in practical applications, i.e., the out-of-sample issue and the noise issue. We propose an effective and efficient method to explore both complementary and consistent information.
  arXiv  Detail & Related papers  (2023-08-03T08:24:08Z)
• SimTeG: A Frustratingly Simple Approach Improves Textual Graph Learning [131.04781590452308]
  We present SimTeG, a frustratingly Simple approach for Textual Graph learning. We first perform supervised parameter-efficient fine-tuning (PEFT) on a pre-trained LM on the downstream task. We then generate node embeddings using the last hidden states of finetuned LM.
  arXiv  Detail & Related papers  (2023-08-03T07:00:04Z)
• Localized Contrastive Learning on Graphs [110.54606263711385]
  We introduce a simple yet effective contrastive model named Localized Graph Contrastive Learning (Local-GCL) In spite of its simplicity, Local-GCL achieves quite competitive performance in self-supervised node representation learning tasks on graphs with various scales and properties.
  arXiv  Detail & Related papers  (2022-12-08T23:36:00Z)
• GraphLearner: Graph Node Clustering with Fully Learnable Augmentation [76.63963385662426]
  Contrastive deep graph clustering (CDGC) leverages the power of contrastive learning to group nodes into different clusters. We propose a Graph Node Clustering with Fully Learnable Augmentation, termed GraphLearner. It introduces learnable augmentors to generate high-quality and task-specific augmented samples for CDGC.
  arXiv  Detail & Related papers  (2022-12-07T10:19:39Z)
• GraphCoCo: Graph Complementary Contrastive Learning [65.89743197355722]
  Graph Contrastive Learning (GCL) has shown promising performance in graph representation learning (GRL) without the supervision of manual annotations. This paper proposes an effective graph complementary contrastive learning approach named GraphCoCo to tackle the above issue.
  arXiv  Detail & Related papers  (2022-03-24T02:58:36Z)
• A Comprehensive Analytical Survey on Unsupervised and Semi-Supervised Graph Representation Learning Methods [4.486285347896372]
  This survey aims to evaluate all major classes of graph embedding methods. We organized graph embedding techniques using a taxonomy that includes methods from manual feature engineering, matrix factorization, shallow neural networks, and deep graph convolutional networks. We designed experiments on top of PyTorch Geometric and DGL libraries and run experiments on different multicore CPU and GPU platforms.
  arXiv  Detail & Related papers  (2021-12-20T07:50:26Z)
• Bayesian Graph Contrastive Learning [55.36652660268726]
  We propose a novel perspective of graph contrastive learning methods showing random augmentations leads to encoders. Our proposed method represents each node by a distribution in the latent space in contrast to existing techniques which embed each node to a deterministic vector. We show a considerable improvement in performance compared to existing state-of-the-art methods on several benchmark datasets.
  arXiv  Detail & Related papers  (2021-12-15T01:45:32Z)
• Effective and Efficient Graph Learning for Multi-view Clustering [173.8313827799077]
  We propose an effective and efficient graph learning model for multi-view clustering. Our method exploits the view-similar between graphs of different views by the minimization of tensor Schatten p-norm. Our proposed algorithm is time-economical and obtains the stable results and scales well with the data size.
  arXiv  Detail & Related papers  (2021-08-15T13:14:28Z)
• Multiple Graph Learning for Scalable Multi-view Clustering [26.846642220480863]
  We propose an efficient multiple graph learning model via a small number of anchor points and tensor Schatten p-norm minimization. Specifically, we construct a hidden and tractable large graph by anchor graph for each view. We develop an efficient algorithm, which scales linearly with the data size, to solve our proposed model.
  arXiv  Detail & Related papers  (2021-06-29T13:10:56Z)
• Learning an Interpretable Graph Structure in Multi-Task Learning [18.293397644865454]
  We present a novel methodology to jointly perform multi-task learning and infer intrinsic relationship among tasks by an interpretable and sparse graph. Our graph is learned simultaneously with model parameters of each task, thus it reflects the critical relationship among tasks in the specific prediction problem.
  arXiv  Detail & Related papers  (2020-09-11T18:58:14Z)
• Hierarchical and Unsupervised Graph Representation Learning with Loukas's Coarsening [9.12816196758482]
  We propose a novel for unsupervised graph representation learning with attributed graphs. We show that our algorithm is competitive with state of the art among unsupervised representation learning methods.
  arXiv  Detail & Related papers  (2020-07-07T12:04:38Z)

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.