Enhancing Unsupervised Graph Few-shot Learning via Set Functions and Optimal Transport
This work addresses the challenge of adapting graph models to new tasks with limited labeled data, which is crucial for real-world applications where abundant labeled data is often unavailable, though it appears incremental by building on existing graph few-shot learning methods.
The paper tackles the problem of unsupervised graph few-shot learning by addressing limitations like neglecting set-level features and distribution shifts between support and query sets, resulting in a model named STAR that leverages set functions and optimal transport to improve performance across multiple datasets.
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.