$R^2$-CoD: Understanding Text-Graph Complementarity in Relational Reasoning via Knowledge Co-Distillation
This work provides insights into text-graph interplay for relational reasoning in NLP, which is incremental as it builds on prior research on dual complementarity.
The paper tackled the problem of understanding how text and graph representations complement each other in relational reasoning tasks, and through an analysis-driven approach with knowledge co-distillation, it uncovered interpretable patterns of alignment and divergence in their integration.
Relational reasoning lies at the core of many NLP tasks, drawing on complementary signals from text and graphs. While prior research has investigated how to leverage this dual complementarity, a detailed and systematic understanding of text-graph interplay and its effect on hybrid models remains underexplored. We take an analysis-driven approach to investigate text-graph representation complementarity via a unified architecture that supports knowledge co-distillation (CoD). We explore five tasks involving relational reasoning that differ in how text and graph structures encode the information needed to solve that task. By tracking how these dual representations evolve during training, we uncover interpretable patterns of alignment and divergence, and provide insights into when and why their integration is beneficial.