AI Paper Atlas

Research map / Graph learning / GNN architectures

Holographic Node Representations: Pre-training Task-Agnostic Node Embeddings

Beatrice Bevilacqua, Joshua Robinson, Jure Leskovec, Bruno Ribeiro

ICLR 2025 · Graph learning › GNN architectures · approach: Graph structure learning

Read the paperCheck your idea against 137,217 papers

AI-extracted summary. Written by AI from the paper's abstract only. Numbers and claims can be wrong or missing context, so check the paper before you cite or build on it.

Proposes Holographic Node Representations, task-agnostic pre-trained node embeddings for GNNs intended to work across node-, link-, and higher-order tasks.

Problem

General-purpose pre-trained GNNs lag other domains because existing GNN architectures are tailored to specific task orders (node-level, link-level, or higher-order), lacking suitable generalist node representations.

Approach

Pre-trains node embeddings that are task-agnostic so a single set of representations can serve node-level, link-level, and higher-order graph tasks, rather than architectures fixed to one task order.

Closest papers by meaning

Writing a paper in this area? scime draft is a free LaTeX editor with AI included, real-time co-authors and a check of your references and venue rules before you submit. It also imports OpenAI Prism projects.

Open scime draft

Get the next scime Dispatch and a monthly field update

Free. We send a confirmation link first; every email has a one-click unsubscribe. Privacy