Leap: Inductive Link Prediction via Learnable TopologyAugmentation

• URL: http://arxiv.org/abs/2503.03331v1
• Date: Wed, 05 Mar 2025 10:03:59 GMT
• Title: Leap: Inductive Link Prediction via Learnable TopologyAugmentation
• Authors: Ahmed E. Samy, Zekarias T. Kefato, Sarunas Girdzijauskas,
• Abstract summary: We propose LEAP, an inductive link prediction method based on LEArnable toPology augmentation.<n>Experiments on seven real-world homogeneous and heterogeneous graphs demonstrate that LEAP significantly surpasses SOTA methods.
• Score: 1.6619898690991983
• License: http://creativecommons.org/licenses/by/4.0/
• Abstract: Link prediction is a crucial task in many downstream applications of graph machine learning. To this end, Graph Neural Network (GNN) is a widely used technique for link prediction, mainly in transductive settings, where the goal is to predict missing links between existing nodes. However, many real-life applications require an inductive setting that accommodates for new nodes, coming into an existing graph. Thus, recently inductive link prediction has attracted considerable attention, and a multi-layer perceptron (MLP) is the popular choice of most studies to learn node representations. However, these approaches have limited expressivity and do not fully capture the graph's structural signal. Therefore, in this work we propose LEAP, an inductive link prediction method based on LEArnable toPology augmentation. Unlike previous methods, LEAP models the inductive bias from both the structure and node features, and hence is more expressive. To the best of our knowledge, this is the first attempt to provide structural contexts for new nodes via learnable augmentation in inductive settings. Extensive experiments on seven real-world homogeneous and heterogeneous graphs demonstrates that LEAP significantly surpasses SOTA methods. The improvements are up to 22\% and 17\% in terms of AUC and average precision, respectively. The code and datasets are available on GitHub (https://github.com/AhmedESamy/LEAP/)

Related papers

• Graph Spring Neural ODEs for Link Sign Prediction [49.71046810937725]
  We propose a novel message-passing layer architecture called Graph Spring Network (GSN) modeled after spring forces.<n>We show that our method achieves accuracy close to the state-of-the-art methods with node generation time speedup factors of up to 28,000 on large graphs.
  arXiv  Detail & Related papers  (2024-12-17T13:50:20Z)
• Link Prediction with Physics-Inspired Graph Neural Networks [4.748336065254026]
  This article focuses on the valuable task of link prediction under heterophily. It is an interesting problem for recommendation systems, social network analysis, and other applications. We show that GRAFF-LP effectively discriminates existing from non-existing edges by learning implicitly to separate the edge gradients.
  arXiv  Detail & Related papers  (2024-02-22T18:56:31Z)
• Inductive Link Prediction in Knowledge Graphs using Path-based Neural Networks [1.3735277588793995]
  SiaILP is a path-based model for inductive link prediction using siamese neural networks. Our model achieves several new state-of-the-art performances in link prediction tasks using inductive versions of WN18RR, FB15k-237, and Nell995.
  arXiv  Detail & Related papers  (2023-12-16T02:26:09Z)
• Label Deconvolution for Node Representation Learning on Large-scale Attributed Graphs against Learning Bias [75.44877675117749]
  We propose an efficient label regularization technique, namely Label Deconvolution (LD), to alleviate the learning bias by a novel and highly scalable approximation to the inverse mapping of GNNs. Experiments demonstrate LD significantly outperforms state-of-the-art methods on Open Graph datasets Benchmark.
  arXiv  Detail & Related papers  (2023-09-26T13:09:43Z)
• 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)
• Disentangling Node Attributes from Graph Topology for Improved Generalizability in Link Prediction [5.651457382936249]
  Our proposed method, UPNA, solves the inductive link prediction problem by learning a function that takes a pair of node attributes and predicts the probability of an edge. UPNA can be applied to various pairwise learning tasks and integrated with existing link prediction models to enhance their generalizability and bolster graph generative models.
  arXiv  Detail & Related papers  (2023-07-17T22:19:12Z)
• How Neural Processes Improve Graph Link Prediction [35.652234989200956]
  We propose a meta-learning approach with graph neural networks for link prediction: Neural Processes for Graph Neural Networks (NPGNN) NPGNN can perform both transductive and inductive learning tasks and adapt to patterns in a large new graph after training with a small subgraph.
  arXiv  Detail & Related papers  (2021-09-30T07:35:13Z)
• Integrating Transductive And Inductive Embeddings Improves Link Prediction Accuracy [24.306445780189005]
  In inductive graph embedding models, emphviz., graph neural networks (GNNs) have become increasingly accurate at link prediction (LP) in online social networks. We demonstrate that, for a wide variety of GNN variants, node representation vectors obtained from Node2Vec serve as high quality input features to GNNs.
  arXiv  Detail & Related papers  (2021-08-23T12:24:20Z)
• Uniting Heterogeneity, Inductiveness, and Efficiency for Graph Representation Learning [68.97378785686723]
  graph neural networks (GNNs) have greatly advanced the performance of node representation learning on graphs. A majority class of GNNs are only designed for homogeneous graphs, leading to inferior adaptivity to the more informative heterogeneous graphs. We propose a novel inductive, meta path-free message passing scheme that packs up heterogeneous node features with their associated edges from both low- and high-order neighbor nodes.
  arXiv  Detail & Related papers  (2021-04-04T23:31:39Z)
• CatGCN: Graph Convolutional Networks with Categorical Node Features [99.555850712725]
  CatGCN is tailored for graph learning when the node features are categorical. We train CatGCN in an end-to-end fashion and demonstrate it on semi-supervised node classification.
  arXiv  Detail & Related papers  (2020-09-11T09:25:17Z)
• Inductive Link Prediction for Nodes Having Only Attribute Information [21.714834749122137]
  In attributed graphs, both the structure and attribute information can be utilized for link prediction. We propose a model called DEAL, which consists of three components: two node embedding encoders and one alignment mechanism. Our proposed model significantly outperforms existing inductive link prediction methods, and also outperforms the state-of-the-art methods on transductive link prediction.
  arXiv  Detail & Related papers  (2020-07-16T00:51:51Z)
• Learning to Extrapolate Knowledge: Transductive Few-shot Out-of-Graph Link Prediction [69.1473775184952]
  We introduce a realistic problem of few-shot out-of-graph link prediction. We tackle this problem with a novel transductive meta-learning framework. We validate our model on multiple benchmark datasets for knowledge graph completion and drug-drug interaction prediction.
  arXiv  Detail & Related papers  (2020-06-11T17:42:46Z)

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.