Research map / Graph learning / GNN architectures
Graph Lottery Ticket Automated
Read the paperCheck your idea against 108,967 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 an automated framework for finding Graph Lottery Tickets (sparse subgraphs and sparse GNN weights) to reduce the cost of training and inference of GNNs on large graphs.
Problem
Training and inference of GNNs on large graphs are resource-intensive, and existing Graph Lottery Ticket identification relies on costly, manually tuned procedures.
Approach
Automates the identification of graph lottery tickets so that the sparse graph and sparse model can be found without extensive manual hyperparameter tuning, extending the lottery ticket hypothesis to GNNs.
Experimental setup
Builds on: Graph Lottery Ticket hypothesis
Closest papers by meaning
- A Unified Lottery Ticket Hypothesis for Graph Neural Networks (ICML 2021 · similarity 0.95)
- Searching Lottery Tickets in Graph Neural Networks: A Dual Perspective (ICLR 2023 · similarity 0.95)
- Fast Track to Winning Tickets: Repowering One-Shot Pruning for Graph Neural Networks (AAAI 2025 · similarity 0.93)
- TEDDY: Trimming Edges with Degree-based Discrimination Strategy (ICLR 2024 · similarity 0.92)
- Weisfeiler and Leman Go Gambling: Why Expressive Lottery Tickets Win (ICML 2025 · similarity 0.90)
- GDeR: Safeguarding Efficiency, Balancing, and Robustness via Prototypical Graph Pruning (NeurIPS 2024 · similarity 0.87)
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.