{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,2,16]],"date-time":"2026-02-16T18:45:29Z","timestamp":1771267529700,"version":"3.50.1"},"publisher-location":"New York, NY, USA","reference-count":29,"publisher":"ACM","content-domain":{"domain":["dl.acm.org"],"crossmark-restriction":true},"short-container-title":[],"published-print":{"date-parts":[[2026,2,22]]},"DOI":"10.1145\/3773966.3779388","type":"proceedings-article","created":{"date-parts":[[2026,2,16]],"date-time":"2026-02-16T17:50:01Z","timestamp":1771264201000},"page":"1258-1262","update-policy":"https:\/\/doi.org\/10.1145\/crossmark-policy","source":"Crossref","is-referenced-by-count":0,"title":["Cold-Starting Podcast Ads and Promotions with Multi-Task Learning on Spotify"],"prefix":"10.1145","author":[{"ORCID":"https:\/\/orcid.org\/0009-0003-4961-1806","authenticated-orcid":false,"given":"Shivam","family":"Verma","sequence":"first","affiliation":[{"name":"Spotify, London, United Kingdom"}]},{"ORCID":"https:\/\/orcid.org\/0009-0006-2598-129X","authenticated-orcid":false,"given":"Hannes","family":"Karlbom","sequence":"additional","affiliation":[{"name":"Spotify, Stockholm, Sweden"}]},{"ORCID":"https:\/\/orcid.org\/0009-0000-5783-1110","authenticated-orcid":false,"given":"Yu","family":"Zhao","sequence":"additional","affiliation":[{"name":"Spotify, Stockholm, Sweden"}]},{"ORCID":"https:\/\/orcid.org\/0009-0007-4243-2150","authenticated-orcid":false,"given":"Nick","family":"Topping","sequence":"additional","affiliation":[{"name":"Spotify, Seattle, USA"}]},{"ORCID":"https:\/\/orcid.org\/0009-0009-2821-2682","authenticated-orcid":false,"given":"Vivian","family":"Chen","sequence":"additional","affiliation":[{"name":"Spotify, San Francisco, USA"}]},{"ORCID":"https:\/\/orcid.org\/0009-0002-3439-1882","authenticated-orcid":false,"given":"Kieran","family":"Stanley","sequence":"additional","affiliation":[{"name":"Spotify, Paris, France"}]},{"ORCID":"https:\/\/orcid.org\/0009-0003-9044-0500","authenticated-orcid":false,"given":"Bharath","family":"Rengarajan","sequence":"additional","affiliation":[{"name":"Spotify, San Francisco, USA"}]}],"member":"320","published-online":{"date-parts":[[2026,2,21]]},"reference":[{"key":"e_1_3_2_1_1_1","doi-asserted-by":"publisher","DOI":"10.1145\/3637528.3671561"},{"key":"e_1_3_2_1_2_1","doi-asserted-by":"publisher","DOI":"10.1145\/3366423.3380122"},{"key":"e_1_3_2_1_3_1","doi-asserted-by":"publisher","DOI":"10.1023\/A:1007379606734"},{"key":"e_1_3_2_1_4_1","volume-title":"GradNorm: Gradient Normalization for Adaptive Loss Balancing in Deep Multitask Networks. In International Conference on Machine Learning. PMLR, 794-803","author":"Chen Zhao","year":"2018","unstructured":"Zhao Chen, Vijay Badrinarayanan, Chen-Yu Lee, and Andrew Rabinovich. 2018. GradNorm: Gradient Normalization for Adaptive Loss Balancing in Deep Multitask Networks. In International Conference on Machine Learning. PMLR, 794-803."},{"key":"e_1_3_2_1_5_1","doi-asserted-by":"publisher","DOI":"10.1145\/2988450.2988454"},{"key":"e_1_3_2_1_6_1","doi-asserted-by":"publisher","DOI":"10.1145\/1390156.1390177"},{"key":"e_1_3_2_1_7_1","doi-asserted-by":"publisher","DOI":"10.1145\/2959100.2959190"},{"key":"e_1_3_2_1_8_1","doi-asserted-by":"publisher","DOI":"10.3389\/fdata.2023.1157899"},{"key":"e_1_3_2_1_9_1","doi-asserted-by":"publisher","DOI":"10.1145\/3640457.3688132"},{"key":"e_1_3_2_1_10_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2018.00781"},{"key":"e_1_3_2_1_11_1","doi-asserted-by":"publisher","DOI":"10.5555\/3454287.3455367"},{"key":"e_1_3_2_1_12_1","unstructured":"Xi Victoria Lin Akshat Shrivastava Liang Luo Srinivasan Iyer Mike Lewis Gargi Ghosh Luke Zettlemoyer and Armen Aghajanyan. 2024. MoMa: Efficient Early-Fusion Pre-training with Mixture of Modality-Aware Experts. arXiv:2407.21770 [cs.AI] https:\/\/arxiv.org\/abs\/2407.21770"},{"key":"e_1_3_2_1_13_1","doi-asserted-by":"publisher","DOI":"10.5555\/3294771.3294923"},{"key":"e_1_3_2_1_14_1","doi-asserted-by":"publisher","DOI":"10.1145\/3219819.3220007"},{"key":"e_1_3_2_1_15_1","doi-asserted-by":"publisher","DOI":"10.1145\/3534678.3539055"},{"key":"e_1_3_2_1_16_1","volume-title":"Proceedings of the 41st International ACM SIGIR Conference on Research and Development in Information Retrieval. ACM, 1137-1140","author":"Ma Xiao","year":"2018","unstructured":"Xiao Ma, Liqin Zhao, Guan Huang, ZhiWang, Zelin Hu, Xiaoqiang Zhu, and Kun Gai. 2018. Entire Space Multi-Task Model: An Effective Approach for Estimating Post-Click Conversion Rate. In Proceedings of the 41st International ACM SIGIR Conference on Research and Development in Information Retrieval. ACM, 1137-1140."},{"key":"e_1_3_2_1_17_1","doi-asserted-by":"publisher","DOI":"10.5555\/3326943.3326992"},{"key":"e_1_3_2_1_18_1","volume-title":"Outrageously Large Neural Networks: The Sparsely-Gated Mixture-of-Experts Layer. In International Conference on Learning Representations. https:\/\/openreview.net\/forum?id=B1ckMDqlg","author":"Shazeer Noam","year":"2017","unstructured":"Noam Shazeer, *Azalia Mirhoseini, *Krzysztof Maziarz, Andy Davis, Quoc Le, Geoffrey Hinton, and Jeff Dean. 2017. Outrageously Large Neural Networks: The Sparsely-Gated Mixture-of-Experts Layer. In International Conference on Learning Representations. https:\/\/openreview.net\/forum?id=B1ckMDqlg"},{"key":"e_1_3_2_1_19_1","doi-asserted-by":"publisher","DOI":"10.5555\/3524938.3525784"},{"key":"e_1_3_2_1_20_1","doi-asserted-by":"publisher","DOI":"10.1145\/3580305.3599881"},{"key":"e_1_3_2_1_21_1","volume-title":"Fortyfirst International Conference on Machine Learning.","author":"Tang Anke","year":"2024","unstructured":"Anke Tang, Li Shen, Yong Luo, Nan Yin, Lefei Zhang, and Dacheng Tao. 2024. Merging Multi-Task Models via Weight-Ensembling Mixture of Experts. In Fortyfirst International Conference on Machine Learning."},{"key":"e_1_3_2_1_22_1","doi-asserted-by":"publisher","DOI":"10.1145\/3383313.3412236"},{"key":"e_1_3_2_1_23_1","volume-title":"Proceedings of the 29th ACM SIGKDD Conference on Knowledge Discovery and Data Mining. ACM, 4882-4893","author":"Tang Jiaxi","unstructured":"Jiaxi Tang, Yoel Drori, Daryl Chang, Maheswaran Sathiamoorthy, Justin Gilmer, Li Wei, Xinyang Yi, Lichan Hong, and Ed H. Chi. 2023. Improving Training Stability for Multitask Ranking Models in Recommender Systems. In Proceedings of the 29th ACM SIGKDD Conference on Knowledge Discovery and Data Mining. ACM, 4882-4893."},{"key":"e_1_3_2_1_24_1","doi-asserted-by":"publisher","DOI":"10.1145\/3711896.3737190"},{"key":"e_1_3_2_1_25_1","doi-asserted-by":"publisher","DOI":"10.1145\/3564285"},{"key":"e_1_3_2_1_26_1","volume-title":"Proceedings of the 13th ACM Conference on Recommender Systems. ACM, 269-277","author":"Yi Xinyang","unstructured":"Xinyang Yi, Ji Yang, Lichan Hong, Derek Zhiyuan Cheng, Lukasz Heldt, Aditee Kumthekar, Zhe Zhao, Li Wei, and Ed H. Chi. 2019. Sampling-Bias-Corrected Neural Modeling for Large Corpus Item Recommendations. In Proceedings of the 13th ACM Conference on Recommender Systems. ACM, 269-277."},{"key":"e_1_3_2_1_27_1","first-page":"5824","article-title":"Gradient Surgery for Multi-Task Learning","volume":"33","author":"Yu Tianhe","year":"2020","unstructured":"Tianhe Yu, Saurabh Kumar, Abhishek Gupta, Sergey Levine, Karol Hausman, and Chelsea Finn. 2020. Gradient Surgery for Multi-Task Learning. Advances in Neural Information Processing Systems 33 (2020), 5824-5836.","journal-title":"Advances in Neural Information Processing Systems"},{"key":"e_1_3_2_1_28_1","doi-asserted-by":"publisher","DOI":"10.1145\/3298689.3346997"},{"key":"e_1_3_2_1_29_1","doi-asserted-by":"publisher","DOI":"10.1016\/j.neucom.2021.11.041"}],"event":{"name":"WSDM '26:The Nineteenth ACM International Conference on Web Search and Data Mining","location":"Boise ID USA","sponsor":["SIGKDD ACM Special Interest Group on Knowledge Discovery in Data","SIGWEB ACM Special Interest Group on Hypertext, Hypermedia, and Web","SIGIR ACM Special Interest Group on Information Retrieval","SIGMOD ACM Special Interest Group on Management of Data"]},"container-title":["Proceedings of the Nineteenth ACM International Conference on Web Search and Data Mining"],"original-title":[],"deposited":{"date-parts":[[2026,2,16]],"date-time":"2026-02-16T17:58:15Z","timestamp":1771264695000},"score":1,"resource":{"primary":{"URL":"https:\/\/dl.acm.org\/doi\/10.1145\/3773966.3779388"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2026,2,21]]},"references-count":29,"alternative-id":["10.1145\/3773966.3779388","10.1145\/3773966"],"URL":"https:\/\/doi.org\/10.1145\/3773966.3779388","relation":{},"subject":[],"published":{"date-parts":[[2026,2,21]]},"assertion":[{"value":"2026-02-21","order":3,"name":"published","label":"Published","group":{"name":"publication_history","label":"Publication History"}}]}}