{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,9,24]],"date-time":"2025-09-24T00:15:02Z","timestamp":1758672902282,"version":"3.44.0"},"publisher-location":"California","reference-count":0,"publisher":"International Joint Conferences on Artificial Intelligence Organization","content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":[],"published-print":{"date-parts":[[2025,9]]},"abstract":"<jats:p>Memory-based temporal graph neural networks (MTGNN) use node memory to store historical information, enabling efficient processing of large dynamic graphs through batch parallel training, with larger batch sizes leading to increased training efficiency. However, this approach overlooks the interdependency among edges within the same batch, leading to outdated memory states and reduced training accuracy. Previous studies have attempted to mitigate this issue through methods such as measuring memory loss, overlap training, and additional compensation modules. Despite these efforts, challenges persist, including imprecise coarse-grained memory loss measurement and ineffective compensation modules. To address these challenges, we propose the Refined Batch parallel Training (RBT) framework, which accurately evaluates intra-batch information loss and optimizes batch partitioning to minimize loss, enhancing the training process's effectiveness and efficiency. RBT also includes a precise and efficient memory compensation algorithm. Experimental results demonstrate RBT's superior performance compared to existing MTGNN frameworks like TGL, ETC, and PRES in terms of training efficiency and accuracy across various dynamic graph datasets. Our code is made publicly available at https:\/\/github.com\/fengwudi\/RBT.<\/jats:p>","DOI":"10.24963\/ijcai.2025\/312","type":"proceedings-article","created":{"date-parts":[[2025,9,19]],"date-time":"2025-09-19T08:10:40Z","timestamp":1758269440000},"page":"2802-2810","source":"Crossref","is-referenced-by-count":0,"title":["Efficient Dynamic Graphs Learning with Refined Batch Parallel Training"],"prefix":"10.24963","author":[{"given":"Zhengzhao","family":"Feng","sequence":"first","affiliation":[{"name":"Zhejiang University"}]},{"given":"Rui","family":"Wang","sequence":"additional","affiliation":[{"name":"Zhejiang University"},{"name":"Hangzhou High-Tech Zone (Binjiang) Institute of Blockchain and Data Security"}]},{"given":"Longjiao","family":"Zhang","sequence":"additional","affiliation":[{"name":"Zhejiang University"}]},{"given":"Tongya","family":"Zheng","sequence":"additional","affiliation":[{"name":"High-Performance Intelligent Computing Research Center for Ultra-Large Scale Graph Data, School of Computer and Computing Science, Hangzhou City University"},{"name":"State Key Laboratory of Blockchain and Data Security, Zhejiang University"}]},{"given":"Ziqi","family":"Huang","sequence":"additional","affiliation":[{"name":"Zhejiang University"}]},{"given":"Mingli","family":"Song","sequence":"additional","affiliation":[{"name":"Zhejiang University"},{"name":"State Key Laboratory of Blockchain and Data Security, Zhejiang University"},{"name":"Hangzhou High-Tech Zone (Binjiang) Institute of Blockchain and Data Security"}]}],"member":"10584","event":{"number":"34","sponsor":["International Joint Conferences on Artificial Intelligence Organization (IJCAI)"],"acronym":"IJCAI-2025","name":"Thirty-Fourth International Joint Conference on Artificial Intelligence {IJCAI-25}","start":{"date-parts":[[2025,8,16]]},"theme":"Artificial Intelligence","location":"Montreal, Canada","end":{"date-parts":[[2025,8,22]]}},"container-title":["Proceedings of the Thirty-Fourth International Joint Conference on Artificial Intelligence"],"original-title":[],"deposited":{"date-parts":[[2025,9,23]],"date-time":"2025-09-23T11:33:41Z","timestamp":1758627221000},"score":1,"resource":{"primary":{"URL":"https:\/\/www.ijcai.org\/proceedings\/2025\/312"}},"subtitle":[],"proceedings-subject":"Artificial Intelligence Research Articles","short-title":[],"issued":{"date-parts":[[2025,9]]},"references-count":0,"URL":"https:\/\/doi.org\/10.24963\/ijcai.2025\/312","relation":{},"subject":[],"published":{"date-parts":[[2025,9]]}}}