arXivDaily arXiv每日学术速递 周一至周五更新
arXiv 2407.20871cs.LG
收藏

共邻居编码模式:一种用于动态链路预测的低成本结构编码方法

Co-Neighbor Encoding Schema: A Light-cost Structure Encoding Method for Dynamic Link Prediction

Beihang University(北京航空航天大学);Zhongguancun Laboratory(中关村实验室);School of Transportation Science and Engineering, Beihang University(北京航空航天大学交通科学与工程学院)

Ke Cheng, Linzhi Peng, Junchen Ye, Leilei Sun, Bowen Du

AI总结:

针对时序图结构编码因高阶子图构建导致计算耗时的问题,提出基于哈希表内存的低成本共邻居编码模式(CNES)及动态图学习框架CNE-N,通过避免冗余计算和生成长短时结构编码,在十三个数据集上验证了高效性。

摘要:

结构编码已被证明是区分图中链路的关键特征。然而,随着图的演化,时序图中的结构编码不断变化,由于高阶子图构建,重复计算此类特征可能非常耗时。我们开发了共邻居编码模式(CNES)来解决这一问题。CNES不再按链路重新计算特征,而是将信息存储在内存中以避免冗余计算。此外,与现有的存储节点隐藏状态的基于内存的动态图学习方法不同,我们引入了基于哈希表的内存来压缩邻接矩阵,从而通过并行向量计算高效地构建和更新结构特征。此外,CNES引入了时间多样化内存,为具有不同结构信息的邻居生成长期和短期结构编码。我们提出了一种动态图学习框架——共邻居编码网络(CNE-N),该框架使用了上述技术。在十三个公开数据集上的大量实验验证了所提方法的有效性和高效性。

英文摘要:

Structure encoding has proven to be the key feature to distinguishing links in a graph. However, Structure encoding in the temporal graph keeps changing as the graph evolves, repeatedly computing such features can be time-consuming due to the high-order subgraph construction. We develop the Co-Neighbor Encoding Schema (CNES) to address this issue. Instead of recomputing the feature by the link, CNES stores information in the memory to avoid redundant calculations. Besides, unlike the existing memory-based dynamic graph learning method that stores node hidden states, we introduce a hashtable-based memory to compress the adjacency matrix for efficient structure feature construction and updating with vector computation in parallel. Furthermore, CNES introduces a Temporal-Diverse Memory to generate long-term and short-term structure encoding for neighbors with different structural information. A dynamic graph learning framework, Co-Neighbor Encoding Network (CNE-N), is proposed using the aforementioned techniques. Extensive experiments on thirteen public datasets verify the effectiveness and efficiency of the proposed method.

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。

↑