Constructing Structured Decision Sources for Consensus-Based Pseudo-Label Learning

Key points

• We address this problem by con structing decision sources through controlled changes to within-class structure.1
• Starting from a shared graph representation, we vary center granularity and neighborhood mixing, reproduce each resulting source to test its stability, and select a complementary subset using node pair coassignment.1
• On the public fixed splits of Cora, CiteSeer, and PubMed, evaluated with five random seeds, the constructed sources improve fixed-budget training pseudo-label precision by 1.19 to 4.39 percentage points over three conventionally initialized GCN sources.1
• These results identify source construction rather than model count alone as an important design problem for consensus-based pseudo-label learning.1

Sources (1)

• [1]Constructing Structured Decision Sources for Consensus-Based Pseudo-Label Learning
  arXiv (AI, ML, NLP, CV, robotics, multi-agent) · Oct 8, 10:00 AM

  Consensus can make pseudo-label learning more reliable, but only when its predictors contribute genuinely different evidence.

  We address this problem by con structing decision sources through controlled changes to within-class structure.

Extractive summary: sentences quoted from the sources.