Certified graph neural networks against label and structure poisoning
Certifying Graph Neural Networks Against Label and Structure Poisoning
Translation in progress — untranslated text is omitted.
The study proposes a semi-supervised framework, ST-GPA, for certifying graph neural networks against label poisoning and structure poisoning under conditions of sparse labels and sparse structure in graph data. The method supplements each graph partition with pseudo-labels and synthetic edges, can adapt to different architectures and scale to a large number of partitions. On multiple benchmarks, ST-GPA consistently and significantly improves robustness guarantees against label and structure poisoning while maintaining strong clean accuracy.
- Graph neural networks lack provable robustness guarantees against label flipping and structural poisoning at training time; the partition-and-aggregate certification that is mainstream in the image domain fails when applied directly to graphs, due to the sparsity of labels and edges.
- Propose ST-GPA: hash graph labels or edges into partitions, on each sparse partition use label propagation co-training and GNN self-training to generate pseudo-labels, use confidence-based link prediction to generate pseudo-edges, then train a GNN base classifier and take majority vote to provide certification.
- On datasets such as Cora-ML and PubMed, the authors claim ST-GPA restores ensemble clean accuracy to about 70%–80% and improves certified accuracy; on binary Cora-ML with 10% label perturbation, certified accuracy is 36.2%, higher than LabelCert's 32.6% (Table 4).
- The authors note that the semi-supervised component relies on homophily, and heterophilous graphs require new methods; link prediction is expensive on large, dense graphs, and structural certification is difficult to scale to ogbn-arxiv; certificate tightness is only roughly checked via non-adaptive transfer attacks.
Related papers
Both use: Amazon-Photo
Both use: Cora-ML
Show 1 more papers
Both use: CiteSeer