{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,7,15]],"date-time":"2026-07-15T18:11:04Z","timestamp":1784139064400,"version":"3.55.0"},"publisher-location":"New York, NY, USA","reference-count":37,"publisher":"ACM","license":[{"start":{"date-parts":[[2026,7,19]],"date-time":"2026-07-19T00:00:00Z","timestamp":1784419200000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/creativecommons.org\/licenses\/by\/4.0\/legalcode"}],"content-domain":{"domain":["dl.acm.org"],"crossmark-restriction":true},"short-container-title":[],"published-print":{"date-parts":[[2026,7,20]]},"DOI":"10.1145\/3805712.3809630","type":"proceedings-article","created":{"date-parts":[[2026,7,15]],"date-time":"2026-07-15T17:06:26Z","timestamp":1784135186000},"page":"2253-2263","update-policy":"https:\/\/doi.org\/10.1145\/crossmark-policy","source":"Crossref","is-referenced-by-count":0,"title":["Beyond Dense Connectivity: Explicit Sparsity for Scalable Recommendation"],"prefix":"10.1145","author":[{"ORCID":"https:\/\/orcid.org\/0009-0006-3541-7596","authenticated-orcid":false,"given":"Yantao","family":"Yu","sequence":"first","affiliation":[{"name":"Alibaba International Digital Commercial Group, Hangzhou, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-4043-5119","authenticated-orcid":false,"given":"Sen","family":"Qiao","sequence":"additional","affiliation":[{"name":"Alibaba International Digital Commercial Group, Hangzhou, Zhejiang, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-5249-7037","authenticated-orcid":false,"given":"Lei","family":"Shen","sequence":"additional","affiliation":[{"name":"Alibaba International Digital Commercial Group, Hangzhou, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-7976-8642","authenticated-orcid":false,"given":"Bing","family":"Wang","sequence":"additional","affiliation":[{"name":"Alibaba International Digital Commercial Group, Hangzhou, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-3742-4910","authenticated-orcid":false,"given":"Xiaoyi","family":"Zeng","sequence":"additional","affiliation":[{"name":"Alibaba International Digital Commercial Group, Hangzhou, China"}],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"320","published-online":{"date-parts":[[2026,7,19]]},"reference":[{"key":"e_1_3_2_1_1_1","volume-title":"Estimating or propagating gradients through stochastic neurons for conditional computation. arXiv preprint arXiv:1308.3432","author":"Bengio Yoshua","year":"2013","unstructured":"Yoshua Bengio, Nicholas L\u00e9onard, and Aaron Courville. 2013. Estimating or propagating gradients through stochastic neurons for conditional computation. arXiv preprint arXiv:1308.3432 (2013)."},{"key":"e_1_3_2_1_2_1","volume-title":"Random forests. Machine learning","author":"Breiman Leo","year":"2001","unstructured":"Leo Breiman. 2001. Random forests. Machine learning, Vol. 45, 1 (2001), 5-32."},{"key":"e_1_3_2_1_3_1","doi-asserted-by":"publisher","DOI":"10.1186\/s13638-019-1478-1"},{"key":"e_1_3_2_1_4_1","doi-asserted-by":"publisher","DOI":"10.1145\/2988450.2988454"},{"key":"e_1_3_2_1_5_1","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v34i04.5768"},{"key":"e_1_3_2_1_6_1","volume-title":"Generating long sequences with sparse transformers. arXiv preprint arXiv:1904.10509","author":"Child Rewon","year":"2019","unstructured":"Rewon Child. 2019. Generating long sequences with sparse transformers. arXiv preprint arXiv:1904.10509 (2019)."},{"key":"e_1_3_2_1_7_1","first-page":"1","article-title":"Switch transformers: Scaling to trillion parameter models with simple and efficient sparsity","volume":"23","author":"Fedus William","year":"2022","unstructured":"William Fedus, Barret Zoph, and Noam Shazeer. 2022. Switch transformers: Scaling to trillion parameter models with simple and efficient sparsity. Journal of Machine Learning Research, Vol. 23, 120 (2022), 1-39.","journal-title":"Journal of Machine Learning Research"},{"key":"e_1_3_2_1_8_1","volume-title":"The lottery ticket hypothesis: Finding sparse, trainable neural networks. arXiv preprint arXiv:1803.03635","author":"Frankle Jonathan","year":"2018","unstructured":"Jonathan Frankle and Michael Carbin. 2018. The lottery ticket hypothesis: Finding sparse, trainable neural networks. arXiv preprint arXiv:1803.03635 (2018)."},{"key":"e_1_3_2_1_9_1","volume-title":"International Conference on Learning Representations.","author":"Golubeva Anna","unstructured":"Anna Golubeva, Guy Gur-Ari, and Behnam Neyshabur. [n.d.]. Are wider nets better given the same number of parameters?. In International Conference on Learning Representations."},{"key":"e_1_3_2_1_10_1","volume-title":"Stochastic optimization of sorting networks via continuous relaxations. arXiv preprint arXiv:1903.08850","author":"Grover Aditya","year":"2019","unstructured":"Aditya Grover, Eric Wang, Aaron Zweig, and Stefano Ermon. 2019. Stochastic optimization of sorting networks via continuous relaxations. arXiv preprint arXiv:1903.08850 (2019)."},{"key":"e_1_3_2_1_11_1","unstructured":"Huifeng Guo Ruiming Tang Yunming Ye Zhenguo Li and Xiuqiang He. 2017. DeepFM: a factorization-machine based neural network for CTR prediction. arXiv preprint arXiv:1703.04247 (2017)."},{"key":"e_1_3_2_1_12_1","volume-title":"International Conference on Machine Learning. PMLR, 17734-17758","author":"Hayase Tomohiro","year":"2024","unstructured":"Tomohiro Hayase and Ryo Karakida. 2024. Understanding MLP-Mixer as a wide and sparse MLP. In International Conference on Machine Learning. PMLR, 17734-17758."},{"key":"e_1_3_2_1_13_1","volume-title":"Lisa Anne Hendricks, Johannes Welbl, Aidan Clark, et al.","author":"Hoffmann Jordan","year":"2022","unstructured":"Jordan Hoffmann, Sebastian Borgeaud, Arthur Mensch, Elena Buchatskaya, Trevor Cai, Eliza Rutherford, Diego de Las Casas, Lisa Anne Hendricks, Johannes Welbl, Aidan Clark, et al., 2022. Training compute-optimal large language models (2022). arXiv preprint arXiv:2203.15556 (2022)."},{"key":"e_1_3_2_1_14_1","doi-asserted-by":"publisher","DOI":"10.1145\/3298689.3347043"},{"key":"e_1_3_2_1_15_1","volume-title":"Scaling laws for neural language models. arXiv preprint arXiv:2001.08361","author":"Kaplan Jared","year":"2020","unstructured":"Jared Kaplan, Sam McCandlish, Tom Henighan, Tom B Brown, Benjamin Chess, Rewon Child, Scott Gray, Alec Radford, Jeffrey Wu, and Dario Amodei. 2020. Scaling laws for neural language models. arXiv preprint arXiv:2001.08361 (2020)."},{"key":"e_1_3_2_1_16_1","doi-asserted-by":"publisher","DOI":"10.1145\/3705328.3748147"},{"key":"e_1_3_2_1_17_1","doi-asserted-by":"publisher","DOI":"10.1145\/3394486.3403314"},{"key":"e_1_3_2_1_18_1","volume-title":"Proceedings of the twenty-ninth international conference on international joint conferences on artificial intelligence. 3139-3145","author":"Lu Wantong","year":"2021","unstructured":"Wantong Lu, Yantao Yu, Yongzhe Chang, Zhen Wang, Chenhui Li, and Bo Yuan. 2021. A dual input-aware factorization machine for CTR prediction. In Proceedings of the twenty-ninth international conference on international joint conferences on artificial intelligence. 3139-3145."},{"key":"e_1_3_2_1_19_1","doi-asserted-by":"publisher","DOI":"10.1145\/3219819.3220007"},{"key":"e_1_3_2_1_20_1","volume-title":"Jianyu Huang, Narayanan Sundaraman, Jongsoo Park, Xiaodong Wang, Udit Gupta, Carole-Jean Wu, Alisson G Azzolini, et al.","author":"Naumov Maxim","year":"2019","unstructured":"Maxim Naumov, Dheevatsa Mudigere, Hao-Jun Michael Shi, Jianyu Huang, Narayanan Sundaraman, Jongsoo Park, Xiaodong Wang, Udit Gupta, Carole-Jean Wu, Alisson G Azzolini, et al., 2019. Deep learning recommendation model for personalization and recommendation systems. arXiv preprint arXiv:1906.00091 (2019)."},{"key":"e_1_3_2_1_21_1","doi-asserted-by":"publisher","DOI":"10.1145\/3340531.3412744"},{"key":"e_1_3_2_1_22_1","doi-asserted-by":"publisher","DOI":"10.1145\/3383313.3412488"},{"key":"e_1_3_2_1_23_1","doi-asserted-by":"publisher","DOI":"10.1145\/3357384.3357925"},{"key":"e_1_3_2_1_24_1","doi-asserted-by":"publisher","DOI":"10.1145\/3604915.3608827"},{"key":"e_1_3_2_1_25_1","doi-asserted-by":"publisher","DOI":"10.1109\/SLT.2014.7078569"},{"key":"e_1_3_2_1_26_1","doi-asserted-by":"publisher","DOI":"10.1145\/3383313.3412236"},{"key":"e_1_3_2_1_27_1","volume-title":"Mlp-mixer: An all-mlp architecture for vision. Advances in neural information processing systems","author":"Tolstikhin Ilya O","year":"2021","unstructured":"Ilya O Tolstikhin, Neil Houlsby, Alexander Kolesnikov, Lucas Beyer, Xiaohua Zhai, Thomas Unterthiner, Jessica Yung, Andreas Steiner, Daniel Keysers, Jakob Uszkoreit, et al., 2021. Mlp-mixer: An all-mlp architecture for vision. Advances in neural information processing systems, Vol. 34 (2021), 24261-24272."},{"key":"e_1_3_2_1_28_1","volume-title":"Towards Bridging Review Sparsity in Recommendation with Textual Edge Graph Representation. arXiv preprint arXiv:2508.01128","author":"Wang Leyao","year":"2025","unstructured":"Leyao Wang, Xutao Mao, Xuhui Zhan, Yuying Zhao, Bo Ni, Ryan A Rossi, Nesreen K Ahmed, and Tyler Derr. 2025. Towards Bridging Review Sparsity in Recommendation with Textual Edge Graph Representation. arXiv preprint arXiv:2508.01128 (2025)."},{"key":"e_1_3_2_1_29_1","doi-asserted-by":"publisher","DOI":"10.1145\/3442381.3450078"},{"key":"e_1_3_2_1_30_1","doi-asserted-by":"publisher","DOI":"10.1145\/3616855.3635780"},{"key":"e_1_3_2_1_31_1","volume-title":"Masknet: Introducing feature-wise multiplication to CTR ranking models by instance-guided mask. arXiv preprint arXiv:2102.07619","author":"Wang Zhiqiang","year":"2021","unstructured":"Zhiqiang Wang, Qingyun She, and Junlin Zhang. 2021a. Masknet: Introducing feature-wise multiplication to CTR ranking models by instance-guided mask. arXiv preprint arXiv:2102.07619 (2021)."},{"key":"e_1_3_2_1_32_1","volume-title":"Spark Transformer: Reactivating Sparsity in FFN and Attention. arXiv preprint arXiv:2506.06644","author":"You Chong","year":"2025","unstructured":"Chong You, Kan Wu, Zhipeng Jia, Lin Chen, Srinadh Bhojanapalli, Jiaxian Guo, Utku Evci, Jan Wassenberg, Praneeth Netrapalli, Jeremiah J Willcock, et al., 2025. Spark Transformer: Reactivating Sparsity in FFN and Attention. arXiv preprint arXiv:2506.06644 (2025)."},{"key":"e_1_3_2_1_33_1","first-page":"1466","article-title":"An Input-aware Factorization Machine for Sparse Prediction","author":"Yu Yantao","year":"2019","unstructured":"Yantao Yu, Zhen Wang, and Bo Yuan. 2019. An Input-aware Factorization Machine for Sparse Prediction.. In IJCAI. 1466-1472.","journal-title":"IJCAI."},{"key":"e_1_3_2_1_34_1","volume-title":"Wukong: Towards a scaling law for large-scale recommendation. arXiv preprint arXiv:2403.02545","author":"Zhang Buyun","year":"2024","unstructured":"Buyun Zhang, Liang Luo, Yuxin Chen, Jade Nie, Xi Liu, Daifeng Guo, Yanli Zhao, Shen Li, Yuchen Hao, Yantao Yao, et al., 2024. Wukong: Towards a scaling law for large-scale recommendation. arXiv preprint arXiv:2403.02545 (2024)."},{"key":"e_1_3_2_1_35_1","volume-title":"Deep learning for click-through rate estimation. arXiv preprint arXiv:2104.10584","author":"Zhang Weinan","year":"2021","unstructured":"Weinan Zhang, Jiarui Qin, Wei Guo, Ruiming Tang, and Xiuqiang He. 2021. Deep learning for click-through rate estimation. arXiv preprint arXiv:2104.10584 (2021)."},{"key":"e_1_3_2_1_36_1","doi-asserted-by":"publisher","DOI":"10.1145\/3292500.3330686"},{"key":"e_1_3_2_1_37_1","doi-asserted-by":"publisher","DOI":"10.1145\/3746252.3761507"}],"event":{"name":"SIGIR '26: The 49th International ACM SIGIR Conference on Research and Development in Information Retrieval","location":"Melbourne VIC Australia","sponsor":["SIGIR ACM Special Interest Group on Information Retrieval"]},"container-title":["Proceedings of the 49th International ACM SIGIR Conference on Research and Development in Information Retrieval"],"original-title":[],"deposited":{"date-parts":[[2026,7,15]],"date-time":"2026-07-15T17:33:48Z","timestamp":1784136828000},"score":1,"resource":{"primary":{"URL":"https:\/\/dl.acm.org\/doi\/10.1145\/3805712.3809630"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2026,7,19]]},"references-count":37,"alternative-id":["10.1145\/3805712.3809630","10.1145\/3805712"],"URL":"https:\/\/doi.org\/10.1145\/3805712.3809630","relation":{},"subject":[],"published":{"date-parts":[[2026,7,19]]},"assertion":[{"value":"2026-07-19","order":3,"name":"published","label":"Published","group":{"name":"publication_history","label":"Publication History"}}]}}