Rethinking Link Prediction for Directed Graphs

• URL: http://arxiv.org/abs/2502.05724v1
• Date: Sat, 08 Feb 2025 23:51:05 GMT
• Title: Rethinking Link Prediction for Directed Graphs
• Authors: Mingguo He, Yuhe Guo, Yanping Zheng, Zhewei Wei, Stephan Günnemann, Xiaokui Xiao,
• Abstract summary: Link prediction for directed graphs is a crucial task with diverse real-world applications. Recent advances in embedding methods and Graph Neural Networks (GNNs) have shown promising improvements. We propose a unified framework to assess the expressiveness of existing methods, highlighting the impact of dual embeddings and decoder design on performance.
• Score: 73.36395969796804
• License:
• Abstract: Link prediction for directed graphs is a crucial task with diverse real-world applications. Recent advances in embedding methods and Graph Neural Networks (GNNs) have shown promising improvements. However, these methods often lack a thorough analysis of embedding expressiveness and suffer from ineffective benchmarks for a fair evaluation. In this paper, we propose a unified framework to assess the expressiveness of existing methods, highlighting the impact of dual embeddings and decoder design on performance. To address limitations in current experimental setups, we introduce DirLinkBench, a robust new benchmark with comprehensive coverage and standardized evaluation. The results show that current methods struggle to achieve strong performance on the new benchmark, while DiGAE outperforms others overall. We further revisit DiGAE theoretically, showing its graph convolution aligns with GCN on an undirected bipartite graph. Inspired by these insights, we propose a novel spectral directed graph auto-encoder SDGAE that achieves SOTA results on DirLinkBench. Finally, we analyze key factors influencing directed link prediction and highlight open challenges.

Related papers

• Graph Structure Refinement with Energy-based Contrastive Learning [56.957793274727514]
  We introduce an unsupervised method based on a joint of generative training and discriminative training to learn graph structure and representation. We propose an Energy-based Contrastive Learning (ECL) guided Graph Structure Refinement (GSR) framework, denoted as ECL-GSR. ECL-GSR achieves faster training with fewer samples and memories against the leading baseline, highlighting its simplicity and efficiency in downstream tasks.
  arXiv  Detail & Related papers  (2024-12-20T04:05:09Z)
• GC4NC: A Benchmark Framework for Graph Condensation on Node Classification with New Insights [30.796414860754837]
  Graph condensation (GC) is an emerging technique designed to learn a significantly smaller graph that retains the essential information of the original graph. This paper introduces textbfGC4NC, a comprehensive framework for evaluating diverse GC methods on node classification. Our systematic evaluation offers novel insights into how condensed graphs behave and the critical design choices that drive their success.
  arXiv  Detail & Related papers  (2024-06-24T15:17:49Z)
• Link Prediction under Heterophily: A Physics-Inspired Graph Neural Network Approach [5.187216033152917]
  We introduce GRAFF-LP, an extension of GRAFF to link prediction. We evaluate its efficacy within a recent collection of heterophilic graphs.
  arXiv  Detail & Related papers  (2024-02-22T18:56:31Z)
• 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)
• Challenging the Myth of Graph Collaborative Filtering: a Reasoned and Reproducibility-driven Analysis [50.972595036856035]
  We present a code that successfully replicates results from six popular and recent graph recommendation models. We compare these graph models with traditional collaborative filtering models that historically performed well in offline evaluations. By investigating the information flow from users' neighborhoods, we aim to identify which models are influenced by intrinsic features in the dataset structure.
  arXiv  Detail & Related papers  (2023-08-01T09:31:44Z)
• Edge Directionality Improves Learning on Heterophilic Graphs [42.5099159786891]
  We introduce Directed Graph Neural Network (Dir-GNN), a novel framework for deep learning on directed graphs. Dir-GNN can be used to extend any Message Passing Neural Network (MPNN) to account for edge directionality information. We prove that Dir-GNN matches the expressivity of the Directed Weisfeiler-Lehman test, exceeding that of conventional MPNNs.
  arXiv  Detail & Related papers  (2023-05-17T18:06:43Z)
• Benchmarking Node Outlier Detection on Graphs [90.29966986023403]
  Graph outlier detection is an emerging but crucial machine learning task with numerous applications. We present the first comprehensive unsupervised node outlier detection benchmark for graphs called UNOD.
  arXiv  Detail & Related papers  (2022-06-21T01:46:38Z)
• 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)
• Modularity-Aware Graph Autoencoders for Joint Community Detection and Link Prediction [27.570978996576503]
  Graph autoencoders (GAE) and variational graph autoencoders (VGAE) emerged as powerful methods for link prediction. It is still unclear to which extent one can improve community detection with GAE and VGAE. We show that jointly addressing these two tasks with high accuracy is possible.
  arXiv  Detail & Related papers  (2022-02-02T11:07:11Z)
• Deepened Graph Auto-Encoders Help Stabilize and Enhance Link Prediction [11.927046591097623]
  Link prediction is a relatively under-studied graph learning task, with current state-of-the-art models based on one- or two-layers of shallow graph auto-encoder (GAE) architectures. In this paper, we focus on addressing a limitation of current methods for link prediction, which can only use shallow GAEs and variational GAEs. Our proposed methods innovatively incorporate standard auto-encoders (AEs) into the architectures of GAEs, where standard AEs are leveraged to learn essential, low-dimensional representations via seamlessly integrating the adjacency information and node features
  arXiv  Detail & Related papers  (2021-03-21T14:43:10Z)

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.