arXivDaily arXiv每日学术速递 周一至周五更新
arXiv 2201.13410cs.LGcs.DS
收藏

Weisfeiler和Leman Go Infinite:谱预着色和组合预着色

Weisfeiler and Leman Go Infinite: Spectral and Combinatorial Pre-Colorings

Technion – Israel Institute of Technology(以色列理工学院)

Or Feldman, Amit Boyarski, Shai Feldman, Dani Kogan, Avi Mendelson, Chaim Baskin

摘要:

图的同构测试通常通过比较图的不变量来实现。在表达能力和计算效率之间提供良好折衷的两种流行替代方案是组合的(即,通过Weisfeiler-Leman(WL)检验获得)和谱不变量。虽然后者的确切功率仍然是一个悬而未决的问题,但当使用统一预着色的标准配置时,前者经常因其有限的功率而受到批评。这一缺陷阻碍了消息传递图神经网络(MPGNNs)的应用,其表达能力是由WL测试的上限。放松均匀预着色的假设,我们表明,可以无限地增加WL测试的表达能力。接下来,我们提出了一种基于光谱特征的高效预着色方法,可以证明它可以提高vanilla WL测试的表达能力。上述主张伴随着大量的合成和真实数据实验。复制我们实验的代码可以在https://github.com/TPFI22/Spectral-and-Combinatorial上找到。

英文摘要:

Graph isomorphism testing is usually approached via the comparison of graph invariants. Two popular alternatives that offer a good trade-off between expressive power and computational efficiency are combinatorial (i.e., obtained via the Weisfeiler-Leman (WL) test) and spectral invariants. While the exact power of the latter is still an open question, the former is regularly criticized for its limited power, when a standard configuration of uniform pre-coloring is used. This drawback hinders the applicability of Message Passing Graph Neural Networks (MPGNNs), whose expressive power is upper bounded by the WL test. Relaxing the assumption of uniform pre-coloring, we show that one can increase the expressive power of the WL test ad infinitum. Following that, we propose an efficient pre-coloring based on spectral features that provably increase the expressive power of the vanilla WL test. The above claims are accompanied by extensive synthetic and real data experiments. The code to reproduce our experiments is available at https://github.com/TPFI22/Spectral-and-Combinatorial

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。

↑