paper-with-me

Papers

Topology Matters: A Cautionary Case Study of Graph SSL on Neuro-Inspired Benchmarks

2026-02-03 · May Kristine Jonson Carlon, Su Myat Noe, Haojiong Wang, Yasuo Kuniyoshi arxiv

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).

📄 PDF Abstract BibTeX arXiv:2602.03217

Code (0)

등록된 구현이 없습니다.

Tasks

Self-Supervised Learning

Similar Papers 제목 키워드 기반

Data Leakage and Deceptive Performance: A Critical Examination of Credit Card Fraud Detection Methodologies

2025-06-03 · Khizar Hayat, Baptiste Magnier

This study critically examines the methodological rigor in credit card fraud detection research, revealing how fundamental evaluation flaws can overshadow algorithmic sophistication. Through deliberate experimentation wi…

Fraud Detection

Structural Invariance Matters: Rethinking Graph Rewiring through Graph Metrics

2025-10-23 · Alexandre Benoit, Catherine Aitken, Yu He arxiv

Graph rewiring has emerged as a key technique to alleviate over-squashing in Graph Neural Networks (GNNs) and Graph Transformers by modifying the graph topology to improve information flow. While effective, rewiring inhe…

Node Classification

TearingNet: Point Cloud Autoencoder to Learn Topology-Friendly Representations

2020-06-17 · CVPR 2021 1 · Jiahao Pang, Duanshun Li, Dong Tian

Topology matters. Despite the recent success of point cloud processing with geometric deep learning, it remains arduous to capture the complex topologies of point cloud data with a learning model. Given a point cloud dat…

PLASMA: A Layout-Aware Benchmark Reveals Memory Layout Matters for Graph-based ANNS on GPU

2025-08-21 · Yutaro Oguri, Mai Nishimura, Yusuke Matsui arxiv

We propose a $\textbf{P}$latform for $\textbf{L}$ayout-$\textbf{A}$ware $\textbf{S}$earch and $\textbf{M}$emory $\textbf{A}$rrangement ($\textbf{PLASMA}$), a unified evaluation framework for graph-based Approximate Neare…

Studying Topology of Time Lines Graph leads to an alternative approach to the Newcomb's Paradox

2019-10-15 · Giuseppe Giacopelli

The Newcomb's paradox is one of the most known paradox in Game Theory about the Oracles. We will define the graph associated to the time lines of the Game. After this Studying its topology and using only the Expected Uti…