$R^2$-CoD: Understanding Text-Graph Complementarity in Relational Reasoning via Knowledge Co-Distillation

TL;DR

This paper investigates how text and graph representations complement each other in relational reasoning tasks, using a unified architecture with knowledge co-distillation to analyze their interplay and effects on model performance.

Contribution

It provides a systematic analysis of text-graph complementarity in relational reasoning, revealing patterns of alignment and divergence during training with a novel co-distillation approach.

Findings

Identifies when and why text-graph integration improves performance

Tracks evolution of dual representations during training

Provides interpretability insights into representation alignment

Abstract

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.