Graph4Cache: A Graph Neural Network Model for Cache Prefetching

Shang Jing; Wu Zhihui; Xiao Zhiwen; Zhang Yifei

doi:10.7544/issn1000-1239.202440190

Journal of Computer Research and Development > 2024 > 61(8): 1945-1956. > DOI: 10.7544/issn1000-1239.202440190

Shang Jing, Wu Zhihui, Xiao Zhiwen, Zhang Yifei. Graph4Cache: A Graph Neural Network Model for Cache Prefetching[J]. Journal of Computer Research and Development, 2024, 61(8): 1945-1956. DOI: 10.7544/issn1000-1239.202440190

Citation:

PDF (1397 KB)

Graph4Cache: A Graph Neural Network Model for Cache Prefetching

China Mobile Information Technology Center, Beijing 100033
China Mobile Information Technology Co., Ltd., Beijing 100033

Funds: This work was supported by the National key Research and Development Program of China (2023YFB4503100), the National Natural Science Foundation of China (U23B2027), and the Strategic Research and Development Project of China Mobile (R24113FN).

More Information

Author Bio:
Shang Jing: born in 1978. PhD. Member of CCF. Her main research interests include big data, cloud computing, and databases

Wu Zhihui: born in 1978. Master. His main research interests include big data platforms, data processing, and databases

Xiao Zhiwen: born in 1993. PhD. Member of CCF. His main research interests include big data, machine learning, and cloud computing

Zhang Yifei: born in 1996. PhD. His main research interests include big data, machine learning, and cloud computing
Received Date: March 14, 2024
Revised Date: May 23, 2024
Available Online: July 04, 2024

Graphical Abstract

Abstract

Abstract

Most computing systems utilize caching to reduce data access latency, speed up data processing and balance service load. The key to cache management is to determine the appropriate data to be loaded into or discarded from the cache, as well as the appropriate timing for cache replacement, which is critical to improving cache hit rate.The existing caching schemes face with two problems: In real-time and online caching scenarios, it is difficult to discern the heat information of user access to data while ignoring the complex high-order information among data-access-sequences. In this paper, we propose a GNN-based cache prefetching network named Graph4Cache. We model a single access sequence into a directed graph (ASGraph), where virtual nodes are used to aggregate the features of all nodes in graph and represent the whole sequence. Then a cross sequence undirected graph (CSGraph) is constructed from the virtual nodes of ASGraphs to learn cross-sequence features, which greatly complements the limited item transitions in a single sequence. By fusing the information of these two graphs , we learn the high-order correlations among sequences and get abundant user intents. Experimental results on multiple public data sets demonstrate the effectiveness of this method. Graph4Cache outperforms the existing cache prediction algorithms on P@20 and MRR@20.
- graph neural network,
- cache prefetching,
- access sequence graph,
- cross sequence graph,
- cache prediction

FullText(HTML)

References (30)

References

[1]	王玉庆,杨秋松,李明树. 基于指令流访存模式预测的缓存替换策略[J]. 计算机研究与发展,2022,59(1):31−46 doi: 10.7544/issn1000-1239.20200503 Wang Yuqing, Yang Qiusong, Li Mingshu. A cache replacement policy based on instruction flow access pattern prediction[J]. Journal of Computer Research and Development, 2022, 59(1): 31−46 (in Chinese) doi: 10.7544/issn1000-1239.20200503
[2]	Lekharu A, Jain M, Sur A, et al. Deep learning model for content aware caching at MEC servers[J]. IEEE Transactions on Network and Service Management, 2022, 19(2): 1413−25 doi: 10.1109/TNSM.2021.3136439
[3]	Fan Qilin, Li Xiuhua, Li Jian, et al. PA-Cache: Evolving learning-based popularity-aware content caching in edge networks[J]. IEEE Transactions on Network and Service Management, 2021, 18(2): 1746−57 doi: 10.1109/TNSM.2021.3053645
[4]	Jiang Weiwei, Luo Jiayun. Graph neural network for traffic forecasting: A survey[J]. Expert Systems with Applications, 2022, 207: 117921. doi: 10.1016/j.eswa.2022.117921
[5]	Yu Junliang, Yin Hongzhi, Li Jundong, et al. Enhancing social recommendation with adversarial graph convolutional networks[J]. IEEE Transactions on Knowledge and Data Engineering, 2022, 34(8): 3727−39. doi: 10.1109/TKDE.2021.3111436
[6]	Wang Wen, Zhang Wei, Liu Shukai, et al. Incorporating link prediction into multi-relational item graph modeling for session-based recommendation[J]. IEEE Transactions on Knowledge and Data Engineering, 2023, 35(3): 2683−96
[7]	Gao Chen, Zheng Yu, Li Nian, et al. A survey of graph neural networks for recommender systems: Challenges, methods, and directions[J]. ACM Transactions on Recommendation System, 2023, 1(1): 1−51
[8]	Hidasi B, Karatzoglou A, Baltrunas L, et al. Session-based recommendations with recurrent neural networks[J]. arXiv preprint, arXiv: 1511.06939, 2015
[9]	Wu Shiwen, Sun Fei, Zhang Wentao, et al. Graph neural networks in recommender systems: A survey[J]. ACM Computing Surveys, 2022, 55(5): 1−37
[10]	Wu Shu, Tang Yuyuan, Zhu Yanqiao, et al. Session-based recommendation with graph neural networks[J]. Proceedings of the AAAI Conference on Artificial Intelligence, 2019, 33((1): ): 346−353 doi: 10.1609/aaai.v33i01.3301346
[11]	Pan Zhiqiang, Cai Fei, Chen Wanyu, et al. Star graph neural networks for session-based recommendation[C]//Proc of the 29th ACM Int Conf on Information & Knowledge Management. Ireland: Association for Computing Machinery. 2020[2024-03-15]. doi: 10.1145/3340531.3412014
[12]	Wang Ziyang, Wei Wei, Cong Gao, et al. Global context enhanced graph neural networks for session-based recommendation[C]//Proc of the 43rd Int ACM SIGIR Conf on Research and Development in Information Retrieval. China: Association for Computing Machinery. 2020[2024-03-15]. doi: 10.1145/3397271.3401142
[13]	Xia X, Yin H, Yu J, et al. Self-supervised hypergraph convolutional networks for session-based recommendation[J]. Proceedings of the AAAI Conference on Artificial Intelligence, 2021, 35(5): 4503−4511 doi: 10.1609/aaai.v35i5.16578
[14]	Lee B, An M, Lee S W. LRU-C: Parallelizing database I/Os for flash SSDs[J]. Proceedings of VLDB Endow, 2023, 16(9): 2364−76 doi: 10.14778/3598581.3598605
[15]	Chen Hao, Ruan Chaoyi, Li Cheng, et al. SpanDB: A fast, cost-effective LSM-tree based KV store on hybrid storage[C/OL]//Proc of the 19th USENIX Conf on File and Storage Technologies (FAST 21). 2021[2024-03-15]. www. usenix. org/conference/fast21/presentation/chen-hao
[16]	Zhang Mi, Wang Qiuping, Shen Zhirong, et al. POCache: Toward robust and configurable straggler tolerance with parity-only caching[J]. Journal of Parallel and Distributed Computing, 2022, 167(C): 157−72 doi: 10.1016/j.jpdc.2022.05.004
[17]	Liu Zaoxing, Bai Zhihao, Liu Zhenming, et al. DistCache: Provable load balancing for large-scale storage systems with distributed caching[C/OL]//Proc of the 17th USENIX Conf on File and Storage Technologies (FAST 19). 2019[2024-03-15]. www. usenix. org/conference/fast19/presentation/liu
[18]	Yang Zhong, Liu Yuanwei, Chen Yue, et al. Deep learning for latent events forecasting in content caching networks[J]. IEEE Transactions on Wireless Communications, 2022, 21(1): 413−28 doi: 10.1109/TWC.2021.3096747
[19]	Rahman G M S, Peng M, Yan S, et al. Learning based joint cache and power allocation in fog radio access networks[J]. IEEE Transactions on Vehicular Technology, 2020, 69(4): 4401−4411 doi: 10.1109/TVT.2020.2975849
[20]	Chen Yanhui, Huang Ling, Wang Changdong, et al. Hybrid-order gated graph neural network for session-based recommendation[J]. IEEE Transactions on Industrial Informatics, 2022, 18(3): 1458−1467 doi: 10.1109/TII.2021.3091435
[21]	Zangerle E, Pichl M, Gassler W, et al. #nowplaying music dataset: extracting listening behavior from Twitter[C]//Proc of the 1st Int Workshop on Internet-Scale Multimedia Management. 2014[2024-03-15]. doi: 2661714.2661719
[22]	Liu Qiao, Zeng Yifu, Mokhosi R, et al. STAMP: Short-term attention/memory priority model for session-based recommendation[C]//Proc of the 24th ACM SIGKDD Int Conf on Knowledge Discovery & Data Mining. 2018[2024-03-15]. doi: 3219819.3219950
[23]	Ding Chengxin, Zhao Zhongying, Li Chao, et al. Session-based recommendation with hypergraph convolutional networks and sequential information embeddings[J]. Expert Systems with Applications, 2023, 223: 119875 doi: 10.1016/j.eswa.2023.119875
[24]	Sarwar B, Karypis G, Konstan J, et al. Item-based collaborative filtering recommendation algorithms[C]//Proc of the 10th Int Conf on World Wide Web. 2001[2024-03-15]. doi: 10.1145/371920.372071
[25]	Rendle S, Freudenthaler C, Schmidt-Thieme L. Factorizing personalized Markov chains for next-basket recommendation[C]//Proc of the 19th Int Conf on World Wide Web. New York: ACM, 2010: 811−820
[26]	Li Jing, Ren Pengjie, Chen Zhumin, et al. Neural attentive session-based recommendation[C]//Proc of 2017 ACM on Conf on Information and Knowledge Management. [2024-03-15]. doi: 10.1145/1772690.1772773
[27]	Wang Meirui, Ren Pengjie, Mei Lei, et al. A Collaborative session-based recommendation approach with parallel memory modules[C]// Proc of the 42nd Int ACM SIGIR Conf on Research and Development in Information Retrieval. New York: ACM, 2019: 345–354
[28]	Xia Xin, Yin Hongzhi, Yu Junliang, et al. Self-supervised graph co-training for session-based recommendation[C]//Proc of the 30th ACM Int Conf on Information & Knowledge Management. New York: ACM, 2021: 2180–2190
[29]	Chen Yao, Xiong Qi, Guo Ying. Session-based recommendation: Learning multi-dimension interests via a multi-head attention graph neural network[J]. Applied Soft Computing, 2022[2024-03-15]. doi: 10.1016/j.asoc.2022.109744
[30]	Sheng Jinfang, Zhu Jiafu, Wang Bin, et al. Global and session item graph neural network for session-based recommendation[J]. Applied Intelligence, 2023, 53(10): 11737−11749 doi: 10.1007/s10489-022-04034-w