arXivDaily arXiv每日学术速递 周一至周五更新
arXiv 2402.14367cs.LGcs.SI
收藏

频繁子图挖掘的表示学习

Representation Learning for Frequent Subgraph Mining

Yale University(耶鲁大学);Tsinghua University(清华大学);Stanford University(斯坦福大学);University of Illinois at Urbana-Champaign(伊利诺伊大学厄巴纳-香槟分校)

Rex Ying, Tianyu Fu, Andrew Wang, Jiaxuan You, Yu Wang, Jure Leskovec

AI总结:

本文提出神经方法 SPMiner,结合图神经网络、序嵌入空间与高效搜索策略,在大图中快速、可扩展地近似挖掘频繁子图,并能识别远超精确枚举规模上限的大型模体。

摘要:

识别频繁子图(也称为网络模体)对于分析和预测现实世界网络的性质至关重要。然而,寻找大型常见模体仍然是一个具有挑战性的问题,这不仅因为其子图计数子程序是 NP 难问题,还因为可能的子图模式数量呈指数增长。在此,我们提出了 Subgraph Pattern Miner(SPMiner),这是一种新颖的神经方法,用于在大规模目标图中近似寻找频繁子图。SPMiner 结合了图神经网络、序嵌入空间和高效的搜索策略,以识别目标图中出现最频繁的网络子图模式。SPMiner 首先将目标图分解为许多重叠的子图,然后将每个子图编码到序嵌入空间中。随后,SPMiner 在序嵌入空间中使用单调游走来识别频繁模体。与现有方法和可能的神经替代方案相比,SPMiner 更准确、更快速且更具可扩展性。对于 5 节点和 6 节点模体,我们表明 SPMiner 几乎可以完美地识别最频繁的模体,同时比精确枚举方法快 100 倍。此外,SPMiner 还可以可靠地识别频繁的 10 节点模体,这远远超出了精确枚举方法的规模限制。最后,我们表明 SPMiner 可以找到高达 20 节点的大型模体,其频率比当前近似方法找到的模体高 10 到 100 倍。

英文摘要:

Identifying frequent subgraphs, also called network motifs, is crucial in analyzing and predicting properties of real-world networks. However, finding large commonly-occurring motifs remains a challenging problem not only due to its NP-hard subroutine of subgraph counting, but also the exponential growth of the number of possible subgraphs patterns. Here we present Subgraph Pattern Miner (SPMiner), a novel neural approach for approximately finding frequent subgraphs in a large target graph. SPMiner combines graph neural networks, order embedding space, and an efficient search strategy to identify network subgraph patterns that appear most frequently in the target graph. SPMiner first decomposes the target graph into many overlapping subgraphs and then encodes each subgraph into an order embedding space. SPMiner then uses a monotonic walk in the order embedding space to identify frequent motifs. Compared to existing approaches and possible neural alternatives, SPMiner is more accurate, faster, and more scalable. For 5- and 6-node motifs, we show that SPMiner can almost perfectly identify the most frequent motifs while being 100x faster than exact enumeration methods. In addition, SPMiner can also reliably identify frequent 10-node motifs, which is well beyond the size limit of exact enumeration approaches. And last, we show that SPMiner can find large up to 20 node motifs with 10-100x higher frequency than those found by current approximate methods.

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。

↑