<?xml version="1.0" encoding="utf-8" standalone="yes"?><rss version="2.0" xmlns:atom="http://www.w3.org/2005/Atom"><channel><title>Graph Learning on Abhiraj Bibhar</title><link>https://abhiraj.pages.dev/tags/graph-learning/</link><description>Recent content in Graph Learning on Abhiraj Bibhar</description><generator>Hugo</generator><language>en</language><lastBuildDate>Sat, 01 Feb 2025 00:00:00 +0000</lastBuildDate><atom:link href="https://abhiraj.pages.dev/tags/graph-learning/index.xml" rel="self" type="application/rss+xml"/><item><title>A Survey of Explainability Methods for Graph Neural Networks</title><link>https://abhiraj.pages.dev/publications/survey-explainability-graph-neural-networks/</link><pubDate>Sat, 01 Feb 2025 00:00:00 +0000</pubDate><guid>https://abhiraj.pages.dev/publications/survey-explainability-graph-neural-networks/</guid><description>&lt;h2 id="abstract"&gt;Abstract&lt;/h2&gt;&#10;&lt;p&gt;Graph neural networks (GNNs) are increasingly deployed in high-stakes settings, yet the tools available for explaining their predictions lag behind those for standard deep networks. This survey organizes the growing landscape of GNN explainability methods along three axes — instance-level versus model-level, perturbation-based versus gradient-based, and faithfulness versus plausibility — and evaluates each family against a consistent set of faithfulness benchmarks.&lt;/p&gt;</description></item></channel></rss>