arXivDaily arXiv每日学术速递 周一至周五更新
arXiv 2402.06445cs.LG
收藏

深度均衡算法推理器

The Deep Equilibrium Algorithmic Reasoner

University of Cambridge(剑桥大学);MediaTek Research(联发科研究院)

Dobrik Georgiev, Pietro Liò, Davide Buffelli

AI总结:

针对神经算法推理依赖循环架构、需逐步对齐算法迭代的问题,本文提出直接求解均衡点来训练 GNN,并通过实验验证了该方法的有效性。

摘要:

近期关于神经算法推理的研究表明,图神经网络(GNN)能够学习执行经典算法。然而,此类工作始终采用循环架构,即 GNN 的每次迭代都与算法的一次迭代相对应。由于算法的解通常是一个均衡点,我们推测并通过实验验证:可以通过直接寻找均衡点来训练网络解决算法问题。需要注意的是,这种方法并不要求将 GNN 的每次迭代与算法的某一步相匹配。

英文摘要:

Recent work on neural algorithmic reasoning has demonstrated that graph neural networks (GNNs) could learn to execute classical algorithms. Doing so, however, has always used a recurrent architecture, where each iteration of the GNN aligns with an algorithm's iteration. Since an algorithm's solution is often an equilibrium, we conjecture and empirically validate that one can train a network to solve algorithmic problems by directly finding the equilibrium. Note that this does not require matching each GNN iteration with a step of the algorithm.

机构、总结、中文摘要均由AI分析而来,可能存在错误,请以论文正文为准。

↑