Subgraph Generation for Generalizing on Out-of-Distribution Links
Graphs Neural Networks (GNNs) demonstrate high-performance on the link prediction (LP) task. However, these models often rely on all dataset samples being drawn from the same distribution. In addition, graph generative models (GGMs) show a pronounced ability to generate novel output graphs. Despite this, GGM applications remain largely limited to domain-specific tasks. To bridge this gap, we propose FLEX as a GGM framework which leverages two mechanism: (1) structurally-conditioned graph generation, and (2) adversarial co-training between an auto-encoder and GNN. As such, FLEX ensures structural-alignment between sample distributions to enhance link-prediction performance in out-of-distribution (OOD) scenarios. Notably, FLEX does not require expert knowledge to function in different OOD scenarios. Numerous experiments are conducted in synthetic and real-world OOD settings to demonstrate FLEX's performance-enhancing ability, with further analysis for understanding the effects of graph data augmentation on link structures. The source code is available here: https://github.com/revolins/FlexOOD.
Code (0)
등록된 구현이 없습니다.
Tasks
Data AugmentationGraph GenerationLink PredictionSimilar Papers 제목 키워드 기반
Deep Generative Models for Subgraph Prediction
Graph Neural Networks (GNNs) are important across different domains, such as social network analysis and recommendation systems, due to their ability to model complex relational data. This paper introduces subgraph queri…
Bayesian OptimizationGraph LearningLink PredictionNode Classification+2Subgraph Federated Learning with Missing Neighbor Generation
Graphs have been widely used in data mining and machine learning due to their unique representation of real-world objects and their interactions. As graphs are getting bigger and bigger nowadays, it is common to see thei…
Federated LearningGraph MiningIntelliGraphs: Datasets for Benchmarking Knowledge Graph Generation
Knowledge Graph Embedding (KGE) models are used to learn continuous representations of entities and relations. A key task in the literature is predicting missing links between entities. However, Knowledge Graphs are not …
BenchmarkingGraph EmbeddingGraph GenerationKnowledge Graph Embedding+2FedGT: Federated Node Classification with Scalable Graph Transformer
Graphs are widely used to model relational data. As graphs are getting larger and larger in real-world scenarios, there is a trend to store and compute subgraphs in multiple local systems. For example, recently proposed …
ClassificationFederated LearningNode ClassificationOnline ClusteringProbabilistic Receiver Architecture Combining BP, MF, and EP for Multi-Signal Detection
Receiver algorithms which combine belief propagation (BP) with the mean field (MF) approximation are well-suited for inference of both continuous and discrete random variables. In wireless scenarios involving detection o…
graph construction