Skip to yearly menu bar Skip to main content


Poster

Structural Fairness-aware Active Learning for Graph Neural Networks

Haoyu Han · Xiaorui Liu · Li Ma · MohamadAli Torkamani · Hui Liu · Jiliang Tang · Makoto Yamada

Halle B #38
[ ]
Fri 10 May 1:45 a.m. PDT — 3:45 a.m. PDT

Abstract:

Graph Neural Networks (GNNs) have seen significant achievements in semi-supervised node classification. Yet, their efficacy often hinges on access to high-quality labeled node samples, which may not always be available in real-world scenarios. While active learning is commonly employed across various domains to pinpoint and label high-quality samples based on data features, graph data present unique challenges due to their intrinsic structures that render nodes non-i.i.d. Furthermore, biases emerge from the positioning of labeled nodes; for instance, nodes closer to the labeled counterparts often yield better performance. To better leverage graph structure and mitigate structural bias in active learning, we present a unified optimization framework (SCARCE), which is also easily incorporated with node features. Extensive experiments demonstrate that the proposed method not only improves the GNNs performance but also paves the way for more fair results.

Chat is not available.