拓扑至关重要:图SSL在神经启发基准上的警示案例研究
Topology Matters: A Cautionary Case Study of Graph SSL on Neuro-Inspired Benchmarks
AI总结:
本文提出一个分层SSL框架,揭示了通用图SSL在连接体数据上的局限性,强调需设计拓扑感知的SSL目标以保持结构。
摘要:
理解局部相互作用如何导致全局大脑组织需要能够跨多个尺度表示信息的模型。我们介绍了一个分层自监督学习(SSL)框架,该框架联合学习节点、边和图级别的嵌入,受多模态神经成像启发。我们构建了一个可控的合成基准,模仿连接体的拓扑特性。我们的四阶段评估协议揭示了一个关键失败:基于不变性的SSL模型本质上与基准的拓扑特性不匹配,并被经典、拓扑感知的启发式方法惨败。消融分析证实了客观不匹配:设计为对拓扑扰动不变的SSL目标学习忽略了经典方法利用的社区结构。我们的结果揭示了在连接体样数据上应用通用图SSL的根本性陷阱。我们提出此框架作为警示案例研究,强调了对神经AI研究而言,需要新的、拓扑感知的SSL目标,这些目标明确奖励结构的保持(例如模ularity或motifs).
英文摘要:
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).
机构、总结、中文摘要均由AI分析而来,可能存在错误,请以论文正文为准。