{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,10,20]],"date-time":"2026-10-20T16:53:45Z","timestamp":1792515225114,"version":"4.5.0"},"publisher-location":"New York, NY, USA","reference-count":62,"publisher":"ACM","license":[{"start":{"date-parts":[[2024,8,24]],"date-time":"2024-08-24T00:00:00Z","timestamp":1724457600000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/creativecommons.org\/licenses\/by\/4.0\/"}],"content-domain":{"domain":["dl.acm.org"],"crossmark-restriction":true},"short-container-title":[],"published-print":{"date-parts":[[2024,8,25]]},"DOI":"10.1145\/3637528.3671835","type":"proceedings-article","created":{"date-parts":[[2024,8,25]],"date-time":"2024-08-25T00:54:55Z","timestamp":1724547295000},"page":"1542-1553","update-policy":"https:\/\/doi.org\/10.1145\/crossmark-policy","source":"Crossref","is-referenced-by-count":8,"title":["Scalable Multitask Learning Using Gradient-based Estimation of Task Affinity"],"prefix":"10.1145","author":[{"ORCID":"https:\/\/orcid.org\/0009-0001-6187-5367","authenticated-orcid":false,"given":"Dongyue","family":"Li","sequence":"first","affiliation":[{"name":"Northeastern University, Boston, USA"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0009-0002-5252-7376","authenticated-orcid":false,"given":"Aneesh","family":"Sharma","sequence":"additional","affiliation":[{"name":"Google, Mountain View, USA"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0009-0005-9118-8516","authenticated-orcid":false,"given":"Hongyang R.","family":"Zhang","sequence":"additional","affiliation":[{"name":"Northeastern University, Boston, USA"}],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"320","published-online":{"date-parts":[[2024,8,24]]},"reference":[{"key":"e_1_3_2_2_1_1","doi-asserted-by":"publisher","DOI":"10.1145\/1411509.1411513"},{"key":"e_1_3_2_2_2_1","doi-asserted-by":"crossref","unstructured":"D. Aloise A. Deshpande P. Hansen and P. Popat. \"NP-hardness of Euclidean sum-of-squares clustering\". In: Machine learning (2009) (6).","DOI":"10.1007\/s10994-009-5103-0"},{"key":"e_1_3_2_2_3_1","volume-title":"Conference on Innovations in Theoretical Computer Science. 2015 (3, 6).","author":"Awasthi P.","unstructured":"P. Awasthi, A. S. Bandeira, M. Charikar, R. Krishnaswamy, S. Villar, and R. Ward. \"Relax, no need to round: Integrality of clustering formulations\". In: Conference on Innovations in Theoretical Computer Science. 2015 (3, 6)."},{"key":"e_1_3_2_2_4_1","unstructured":"A. Ayman A. Mukhopadhyay and A. Laszka. \"Task Grouping for Automated Multi-Task Machine Learning via Task Affinity Prediction\". In: arXiv preprint arXiv:2310.16241 (2023) (3)."},{"key":"e_1_3_2_2_5_1","volume-title":"AAAI Practical-DL Workshop (2023)","author":"Azorin R.","unstructured":"R. Azorin, M. Gallo, A. Finamore, D. Rossi, and P. Michiardi. ?\" It's a Match!\"--A Benchmark of Task Affinity Scores for Joint Learning\". In: AAAI Practical-DL Workshop (2023) (3)."},{"key":"e_1_3_2_2_6_1","doi-asserted-by":"crossref","unstructured":"S. H. Bach V. Sanh Z.-X. Yong A. Webson C. Raffel N. V. Nayak A. Sharma T. Kim M. S. Bari T. Fevry et al. ?Promptsource: An integrated development environment and repository for natural language prompts\". In: arXiv preprint arXiv:2202.01279 (2022) (4 7).","DOI":"10.18653\/v1\/2022.acl-demo.9"},{"key":"e_1_3_2_2_7_1","doi-asserted-by":"publisher","DOI":"10.1109\/ICIP.2019.8803726"},{"key":"e_1_3_2_2_8_1","doi-asserted-by":"publisher","DOI":"10.1145\/775047.775111"},{"key":"e_1_3_2_2_9_1","doi-asserted-by":"publisher","DOI":"10.1214\/15-AOS1388"},{"key":"e_1_3_2_2_10_1","first-page":"794","volume-title":"International conference on machine learning. PMLR.","author":"Chen Z.","year":"2018","unstructured":"Z. Chen, V. Badrinarayanan, C.-Y. Lee, and A. Rabinovich. \"Gradnorm: Gradient normalization for adaptive loss balancing in deep multitask networks\". In: International conference on machine learning. PMLR. 2018, pp. 794--803 (3)."},{"key":"e_1_3_2_2_11_1","volume-title":"Auxiliary task update decomposition: The good, the bad and the neutral","author":"Dery L. M.","year":"2021","unstructured":"L. M. Dery, Y. Dauphin, and D. Grangier. \"Auxiliary task update decomposition: The good, the bad and the neutral\". In: ICLR (2021) (3)."},{"key":"e_1_3_2_2_12_1","volume-title":"Efficiently identifying task groupings for multi-task learning","author":"Fifty C.","year":"2021","unstructured":"C. Fifty, E. Amid, Z. Zhao, T. Yu, R. Anil, and C. Finn. \"Efficiently identifying task groupings for multi-task learning\". In: NeurIPS (2021) (1, 3, 8)."},{"key":"e_1_3_2_2_13_1","unstructured":"F. Frasca E. Rossi D. Eynard B. Chamberlain M. Bronstein and F. Monti. \"Sign: Scalable inception graph neural networks\". In: arXiv preprint arXiv:2004.11198 (2020) (4 7)."},{"key":"e_1_3_2_2_14_1","volume-title":"Learning to branch for multi-task learning","author":"Guo P.","year":"2020","unstructured":"P. Guo, C.-Y. Lee, and D. Ulbricht. \"Learning to branch for multi-task learning\". In: ICML. 2020 (3)."},{"key":"e_1_3_2_2_15_1","doi-asserted-by":"publisher","DOI":"10.1007\/978-0-387-84858-7"},{"key":"e_1_3_2_2_16_1","doi-asserted-by":"crossref","unstructured":"T. Hospedales A. Antoniou P. Micaelli and A. Storkey. \"Meta-learning in neural networks: A survey\". In: IEEE transactions on pattern analysis and machine intelligence (2021) (12).","DOI":"10.1109\/TPAMI.2021.3079209"},{"key":"e_1_3_2_2_17_1","first-page":"9201","volume-title":"International Conference on Machine Learning. PMLR.","author":"Huang L.-K.","year":"2022","unstructured":"L.-K. Huang, J. Huang, Y. Rong, Q. Yang, and Y. Wei. \"Frustratingly easy transferability estimation\". In: International Conference on Machine Learning. PMLR. 2022, pp. 9201--9225 (3)."},{"key":"e_1_3_2_2_18_1","first-page":"693","volume-title":"Joint European Conference on Machine Learning and Knowledge Discovery in Databases. Springer.","author":"Ibrahim S.","year":"2022","unstructured":"S. Ibrahim, N. Ponomareva, and R. Mazumder. \"Newer is not always better: Rethinking transferability metrics, their peculiarities, stability and performance\". In: Joint European Conference on Machine Learning and Knowledge Discovery in Databases. Springer. 2022, pp. 693--709 (3)."},{"key":"e_1_3_2_2_19_1","volume-title":"Datamodels: Predicting predictions from training data","author":"Ilyas A.","year":"2022","unstructured":"A. Ilyas, S. M. Park, L. Engstrom, G. Leclerc, and A. Madry. \"Datamodels: Predicting predictions from training data\". In: ICML (2022) (3)."},{"key":"e_1_3_2_2_20_1","doi-asserted-by":"publisher","DOI":"10.1090\/conm\/026\/737400"},{"key":"e_1_3_2_2_21_1","volume-title":"Generalization in graph neural networks: Improved pac-bayesian bounds on graph diffusion","author":"Ju H.","year":"2023","unstructured":"H. Ju, D. Li, A. Sharma, and H. R. Zhang. \"Generalization in graph neural networks: Improved pac-bayesian bounds on graph diffusion\". In: AISTATS. 2023 (3)."},{"key":"e_1_3_2_2_22_1","first-page":"10431","volume-title":"International Conference on Machine Learning. PMLR.","author":"Ju H.","year":"2022","unstructured":"H. Ju, D. Li, and H. R. Zhang. \"Robust fine-tuning of deep neural networks with hessian-based generalization guarantees\". In: International Conference on Machine Learning. PMLR. 2022, pp. 10431--10461 (3)."},{"key":"e_1_3_2_2_23_1","unstructured":"H. Ju D. Li and H. R. Zhang. \"Noise Stability Optimization for Flat Minima with Tight Convergence Rates\". In: arXiv preprint arXiv:2306.08553 (2023) (3)."},{"key":"e_1_3_2_2_24_1","volume-title":"Understanding black-box predictions via influence functions","author":"Koh P. W.","year":"2017","unstructured":"P. W. Koh and P. Liang. \"Understanding black-box predictions via influence functions\". In: ICML. 2017 (3)."},{"key":"e_1_3_2_2_25_1","doi-asserted-by":"publisher","DOI":"10.1145\/3580305.3599265"},{"key":"e_1_3_2_2_26_1","first-page":"2","article-title":"Identification of Negative Transfers in Multitask Learning Using Surrogate Models","author":"Li D.","year":"2023","unstructured":"D. Li, H. Nguyen, and H. R. Zhang. \"Identification of Negative Transfers in Multitask Learning Using Surrogate Models\". In: Transactions on Machine Learning Research (2023) (2, 3).","journal-title":"Transactions on Machine Learning Research ("},{"key":"e_1_3_2_2_27_1","first-page":"27249","article-title":"Improved regularization and robustness for fine-tuning in neural networks","volume":"34","author":"Li D.","year":"2021","unstructured":"D. Li and H. Zhang. \"Improved regularization and robustness for fine-tuning in neural networks\". In: Advances in Neural Information Processing Systems 34 (2021), pp. 27249--27262 (3).","journal-title":"Advances in Neural Information Processing Systems"},{"key":"e_1_3_2_2_28_1","volume-title":"Auto-lambda: Disentangling dynamic task relationships","author":"Liu S.","year":"2022","unstructured":"S. Liu, S. James, A. J. Davison, and E. Johns. \"Auto-lambda: Disentangling dynamic task relationships\". In: TMLR (2022) (3, 8)."},{"key":"e_1_3_2_2_29_1","doi-asserted-by":"crossref","unstructured":"S. Lloyd. \"Least squares quantization in PCM\". In: IEEE transactions on information theory (1982) (2).","DOI":"10.1109\/TIT.1982.1056489"},{"key":"e_1_3_2_2_30_1","unstructured":"S. Longpre L. Hou T. Vu A. Webson H. W. Chung Y. Tay D. Zhou Q. V. Le B. Zoph J. Wei et al. \"The flan collection: Designing data and methods for effective instruction tuning\". In: arXiv preprint arXiv:2301.13688 (2023) (1 2 7)."},{"key":"e_1_3_2_2_31_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2017.126"},{"key":"e_1_3_2_2_32_1","doi-asserted-by":"publisher","DOI":"10.1145\/3219819.3220007"},{"key":"e_1_3_2_2_33_1","volume-title":"Fine-Tuning Language Models with Just Forward Passes","author":"Malladi S.","year":"2023","unstructured":"S. Malladi, T. Gao, E. Nichani, A. Damian, J. D. Lee, D. Chen, and S. Arora. \"Fine-Tuning Language Models with Just Forward Passes\". In: NeurIPS (2023) ( ."},{"key":"e_1_3_2_2_34_1","first-page":"23610","volume-title":"International Conference on Machine Learning. PMLR.","author":"Malladi S.","year":"2023","unstructured":"S. Malladi, A. Wettig, D. Yu, D. Chen, and S. Arora. \"A kernel-based view of language model fine-tuning\". In: International Conference on Machine Learning. PMLR. 2023, pp. 23610--23641 (2)."},{"key":"e_1_3_2_2_35_1","unstructured":"A. Ng M. Jordan and Y. Weiss. \"On spectral clustering: Analysis and an algorithm\". In: Advances in neural information processing systems 14 (2001) ( ."},{"key":"e_1_3_2_2_36_1","first-page":"7294","volume-title":"International Conference on Machine Learning. PMLR.","author":"Nguyen C.","year":"2020","unstructured":"C. Nguyen, T. Hassner, M. Seeger, and C. Archambeau. \"Leep: A newmeasure to evaluate transferability of learned representations\". In: International Conference on Machine Learning. PMLR. 2020, pp. 7294--7305 (3)."},{"key":"e_1_3_2_2_37_1","unstructured":"A. Nippani D. Li H. Ju H. Koutsopoulos and H. Zhang. \"Graph Neural Networks for Road Safety Modeling: Datasets and Evaluations for Accident Analysis\". In: Advances in Neural Information Processing Systems 36 (2023) (2)."},{"key":"e_1_3_2_2_38_1","doi-asserted-by":"publisher","DOI":"10.1109\/SFCS.2000.892068"},{"key":"e_1_3_2_2_39_1","volume-title":"Trak: Attributing model behavior at scale","author":"Park S. M.","year":"2023","unstructured":"S. M. Park, K. Georgiev, A. Ilyas, G. Leclerc, and A. Madry. \"Trak: Attributing model behavior at scale\". In: ICML (2023) (3)."},{"key":"e_1_3_2_2_40_1","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2019.00149"},{"key":"e_1_3_2_2_41_1","unstructured":"A. Roberts C. Raffel K. Lee M. Matena N. Shazeer P. J. Liu S. Narang W. Li and Y. Zhou. \"Exploring the limits of transfer learning with a unified text-to-text transformer\". In: (2019) (7)."},{"key":"e_1_3_2_2_42_1","unstructured":"A. Royer T. Blankevoort and B. Ehteshami Bejnordi. \"Scalarization for multitask and multi-domain learning at scale\". In: NeurIPS (2023) (3)."},{"key":"e_1_3_2_2_43_1","unstructured":"O. Sener and V. Koltun. \"Multi-task learning as multi-objective optimization\". In: Advances in neural information processing systems 31 (2018) (3)."},{"key":"e_1_3_2_2_44_1","volume-title":"ICML DMLR Workshop (2023)","author":"Sherif A.","unstructured":"A. Sherif, A. Abid, M. Elattar, and M. ElHelw. \"STG-MTL: Scalable Task Grouping For Multi-Task Learning Using Data Maps\". In: ICML DMLR Workshop (2023) (3)."},{"key":"e_1_3_2_2_45_1","volume-title":"Federated multi-task learning","author":"Smith V.","year":"2017","unstructured":"V. Smith, C.-K. Chiang, M. Sanjabi, and A. S. Talwalkar. \"Federated multi-task learning\". In: NeurIPS (2017) (2)."},{"key":"e_1_3_2_2_46_1","unstructured":"T. Standley A. Zamir D. Chen L. Guibas J. Malik and S. Savarese. \"Which tasks should be learned together in multi-task learning\"\" In: ICML. 2020 (1 3 ."},{"issue":"127","key":"e_1_3_2_2_47_1","first-page":"1","article-title":"Graph clustering with graph neural networks","volume":"24","author":"Tsitsulin A.","year":"2023","unstructured":"A. Tsitsulin, J. Palowitch, B. Perozzi, and E. M\u00fcller. \"Graph clustering with graph neural networks\". In: Journal of Machine Learning Research 24.127 (2023), pp. 1--21 (3).","journal-title":"Journal of Machine Learning Research"},{"key":"e_1_3_2_2_48_1","volume-title":"deciding what layers to share","author":"Vandenhende S.","year":"2019","unstructured":"S. Vandenhende, S. Georgoulis, B. De Brabandere, and L. Van Gool. \"Branched multi-task networks: deciding what layers to share\". In: BMCV (2019) (3)."},{"key":"e_1_3_2_2_49_1","volume-title":"Spot: Better frozen model adaptation through soft prompt transfer","author":"Vu T.","year":"2021","unstructured":"T. Vu, B. Lester, N. Constant, R. Al-Rfou, and D. Cer. \"Spot: Better frozen model adaptation through soft prompt transfer\". In: ACL (2021) (1, 3)."},{"key":"e_1_3_2_2_50_1","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2020.emnlp-main.635"},{"key":"e_1_3_2_2_51_1","unstructured":"A.Wang Y. Pruksachatkun N. Nangia A. Singh J. Michael F. Hill O. Levy and S. Bowman. \"Superglue: A stickier benchmark for general-purpose language understanding systems\". In: Advances in neural information processing systems 32 (2019) (4 7)."},{"key":"e_1_3_2_2_52_1","volume-title":"NTK-approximating MLP fusion for efficient language model fine-tuning","author":"Wei T.","year":"2023","unstructured":"T.Wei, Z. Guo, Y. Chen, and J. He. \"NTK-approximating MLP fusion for efficient language model fine-tuning\". In: ICML. 2023 (2)."},{"key":"e_1_3_2_2_53_1","first-page":"10410","volume-title":"International Conference on Machine Learning. PMLR.","author":"Wu S.","year":"2020","unstructured":"S. Wu, H. Zhang, G. Valiant, and C. R\u00e9. \"On the generalization effects of linear transformations in data augmentation\". In: International Conference on Machine Learning. PMLR. 2020, pp. 10410--10420 (1)."},{"key":"e_1_3_2_2_54_1","volume-title":"International Conference on Learning Representations. 2020 (1, 2).","author":"Wu S.","unstructured":"S. Wu, H. R. Zhang, and C. R\u00e9. \"Understanding and Improving Information Transfer in Multi-Task Learning\". In: International Conference on Learning Representations. 2020 (1, 2)."},{"key":"e_1_3_2_2_55_1","unstructured":"F. Yang H. R. Zhang S. Wu C. R\u00e9 and W. J. Su. \"Precise High-Dimensional Asymptotics for Quantifying Heterogeneous Transfers\". In: arXiv preprint arXiv:2010.11750 (2020) (1)."},{"key":"e_1_3_2_2_56_1","volume-title":"KDD Workshop on Mining Data Semantics. 2012 (4, 7).","author":"Yang J.","unstructured":"J. Yang and J. Leskovec. \"Defining and evaluating network communities based on ground-truth\". In: KDD Workshop on Mining Data Semantics. 2012 (4, 7)."},{"key":"e_1_3_2_2_57_1","doi-asserted-by":"publisher","DOI":"10.1145\/2433396.2433471"},{"key":"e_1_3_2_2_58_1","volume-title":"Fine-tuning pre-trained language model with weak supervision: A contrastive-regularized self-training approach","author":"Yu Y.","year":"2020","unstructured":"Y. Yu, S. Zuo, H. Jiang,W. Ren, T. Zhao, and C. Zhang. \"Fine-tuning pre-trained language model with weak supervision: A contrastive-regularized self-training approach\". In: NAACL-HLT (2020) (4)."},{"key":"e_1_3_2_2_59_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2018.00391"},{"key":"e_1_3_2_2_60_1","doi-asserted-by":"publisher","DOI":"10.1109\/TKDE.2021.3070203"},{"key":"e_1_3_2_2_61_1","volume-title":"Large language models are human-level prompt engineers","author":"Zhou Y.","year":"2023","unstructured":"Y. Zhou, A. I. Muresanu, Z. Han, K. Paster, S. Pitis, H. Chan, and J. Ba. \"Large language models are human-level prompt engineers\". In: ICLR (2023) (7)."},{"key":"e_1_3_2_2_62_1","volume-title":"Transfer learning of graph neural networks with ego-graph information maximization","author":"Zhu Q.","year":"2021","unstructured":"Q. Zhu, C. Yang, Y. Xu, H. Wang, C. Zhang, and J. Han. \"Transfer learning of graph neural networks with ego-graph information maximization\". In: NeurIPS (2021) (2)."}],"event":{"name":"KDD '24: The 30th ACM SIGKDD Conference on Knowledge Discovery and Data Mining","location":"Barcelona Spain","acronym":"KDD '24","sponsor":["SIGMOD ACM Special Interest Group on Management of Data","SIGKDD ACM Special Interest Group on Knowledge Discovery in Data"]},"container-title":["Proceedings of the 30th ACM SIGKDD Conference on Knowledge Discovery and Data Mining"],"original-title":[],"link":[{"URL":"https:\/\/dl.acm.org\/doi\/10.1145\/3637528.3671835","content-type":"unspecified","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/dl.acm.org\/doi\/pdf\/10.1145\/3637528.3671835","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,6,18]],"date-time":"2025-06-18T20:04:14Z","timestamp":1750277054000},"score":1,"resource":{"primary":{"URL":"https:\/\/dl.acm.org\/doi\/10.1145\/3637528.3671835"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2024,8,24]]},"references-count":62,"alternative-id":["10.1145\/3637528.3671835","10.1145\/3637528"],"URL":"https:\/\/doi.org\/10.1145\/3637528.3671835","relation":{},"subject":[],"published":{"date-parts":[[2024,8,24]]},"assertion":[{"value":"2024-08-24","order":3,"name":"published","label":"Published","group":{"name":"publication_history","label":"Publication History"}}]}}