Topology Matters: A Cautionary Case Study of Graph SSL on Neuro-Inspired Benchmarks
This is an incremental study exposing a fundamental pitfall for neuro-AI researchers applying graph SSL to connectome-like data, highlighting the need for new topology-aware objectives.
The paper tackled the problem of applying generic graph self-supervised learning (SSL) to neuro-inspired data by introducing a hierarchical SSL framework and a synthetic benchmark mimicking connectomes, revealing that invariance-based SSL models catastrophically fail, being outperformed by classical topology-aware heuristics due to an objective mismatch.
Understanding how local interactions give rise to global brain organization requires models that can represent information across multiple scales. We introduce a hierarchical self-supervised learning (SSL) framework that jointly learns node-, edge-, and graph-level embeddings, inspired by multimodal neuroimaging. We construct a controllable synthetic benchmark mimicking the topological properties of connectomes. Our four-stage evaluation protocol reveals a critical failure: the invariance-based SSL model is fundamentally misaligned with the benchmark's topological properties and is catastrophically outperformed by classical, topology-aware heuristics. Ablations confirm an objective mismatch: SSL objectives designed to be invariant to topological perturbations learn to ignore the very community structure that classical methods exploit. Our results expose a fundamental pitfall in applying generic graph SSL to connectome-like data. We present this framework as a cautionary case study, highlighting the need for new, topology-aware SSL objectives for neuro-AI research that explicitly reward the preservation of structure (e.g., modularity or motifs).