SparRL: Graph Sparsification via Deep Reinforcement Learning

Ryan Wickman, Xiaofei Zhang, Weizi Li

Keywords: graph sparsification, graph theory, machine learning, reinforcement learning

Abstract: Graph sparsification concerns data reduction where an edge-reduced graph of a similar structure is preferred. Existing methods are mostly sampling-based, which introduce high computation complexity in general and lack of flexibility for a different reduction objective. We present SparRL, the first general and effective reinforcement learning-based framework for graph sparsification. SparRL can easily adapt to different reduction goals and promise graph-size-independent complexity. Extensive experiments show that SparRL outperforms all prevailing sparsification methods in producing high-quality sparsified graphs concerning a variety of objectives. As graph representations are very versatile, SparRL carries the potential for a broad impact.

One-sentence Summary: A novel graph sparsification framework based on reinforcement learning that establishes SOTA performance measured over several tasks.

Community Implementations: [ 1 code implementation](https://www.catalyzex.com/paper/arxiv:2112.01565/code)