Enhancing Unsupervised Graph Few-shot Learning via Set Functions and Optimal Transport

2025-01-10

AI Summary

Graph few-shot learning suffers from distributional shifts between support and query sets, lack of set-level representations, overreliance on base-class annotations, and limitations of instance-level modeling. Method: This paper proposes STAR, an unsupervised framework that jointly leverages DeepSets—an unsupervised set function—to learn task-level feature representations and Wasserstein-distance-based optimal transport to align support and query set distributions, eliminating dependence on supervised pretraining or extensive base-class labels. Contribution/Results: Theoretical analysis demonstrates STAR’s enhanced capacity to capture task-related dependencies and improve generalization. Empirically, STAR achieves significant improvements over state-of-the-art methods across multiple graph few-shot benchmarks, validating its effectiveness in modeling task structure and enabling cross-distribution transfer under fully unsupervised settings.

Technology Category

• Machine Learning: Graph-based Machine Learning
• Search and Optimization: Learning to Search
• Reasoning under Uncertainty: Graphical Models

Application Category

• Graph Algorithms and Modeling for the Web: Graph embeddings and representation learning for Web-related graphs
• Search and Retrieval-Augmented AI: Web learning to rank, online learning, and counterfactual learning for ranking
• Semantics and Knowledge: Scalable techniques for the creation, curation, publication, maintenance, and consumption of large, Web-based, structured, reusable, knowledge graphs and ontologies

Abstract

Graph few-shot learning has garnered significant attention for its ability to rapidly adapt to downstream tasks with limited labeled data, sparking considerable interest among researchers. Recent advancements in graph few-shot learning models have exhibited superior performance across diverse applications. Despite their successes, several limitations still exist. First, existing models in the meta-training phase predominantly focus on instance-level features within tasks, neglecting crucial set-level features essential for distinguishing between different categories. Second, these models often utilize query sets directly on classifiers trained with support sets containing only a few labeled examples, overlooking potential distribution shifts between these sets and leading to suboptimal performance. Finally, previous models typically require necessitate abundant labeled data from base classes to extract transferable knowledge, which is typically infeasible in real-world scenarios. To address these issues, we propose a novel model named STAR, which leverages Set funcTions and optimAl tRansport for enhancing unsupervised graph few-shot learning. Specifically, STAR utilizes expressive set functions to obtain set-level features in an unsupervised manner and employs optimal transport principles to align the distributions of support and query sets, thereby mitigating distribution shift effects. Theoretical analysis demonstrates that STAR can capture more task-relevant information and enhance generalization capabilities. Empirically, extensive experiments across multiple datasets validate the effectiveness of STAR. Our code can be found here.

Problem

• Few-shot Learning
• Unsupervised Learning
• Data Dependency

Innovation

• STAR model
• Optimal Transport
• Unsupervised Few-shot Learning