{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,8,25]],"date-time":"2026-08-25T20:23:31Z","timestamp":1787689411942,"version":"build-2784847793"},"publisher-location":"New York, NY, USA","reference-count":52,"publisher":"ACM","funder":[{"name":"National Science Foundation","award":["IIS-2412008"],"award-info":[{"award-number":["IIS-2412008"]}]}],"content-domain":{"domain":["dl.acm.org"],"crossmark-restriction":true},"short-container-title":[],"published-print":{"date-parts":[[2026,8,9]]},"DOI":"10.1145\/3770854.3780253","type":"proceedings-article","created":{"date-parts":[[2026,7,31]],"date-time":"2026-07-31T12:07:40Z","timestamp":1785499660000},"page":"645-656","update-policy":"https:\/\/doi.org\/10.1145\/crossmark-policy","source":"Crossref","is-referenced-by-count":0,"title":["Efficiently Learning Branching Networks for Multitask Algorithmic Reasoning"],"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, MA, USA"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-6878-097X","authenticated-orcid":false,"given":"Zhenshuo","family":"Zhang","sequence":"additional","affiliation":[{"name":"Northeastern University, Boston, MA, USA"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-1718-294X","authenticated-orcid":false,"given":"Minxuan","family":"Duan","sequence":"additional","affiliation":[{"name":"Northeastern University, Boston, MA, USA"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-3467-8931","authenticated-orcid":false,"given":"Edgar","family":"Dobriban","sequence":"additional","affiliation":[{"name":"University of Pennsylvania, Philadelphia, PA, 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, MA, USA"}],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"320","published-online":{"date-parts":[[2026,4,20]]},"reference":[{"key":"e_1_3_2_2_1_1","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-540-77004-6_12"},{"key":"e_1_3_2_2_2_1","volume-title":"meet Neural Algorithmic Reasoners''. In: arXiv preprint arXiv:2406","author":"Bounsi W.","year":"2024","unstructured":"W. Bounsi, B. Ibarz, A. Dudzik, J. B. Hamrick, L. Markeeva, A. Vitvitskyi, R. Pascanu, and P. Veli?kovi?. ''Transformers meet Neural Algorithmic Reasoners''. In: arXiv preprint arXiv:2406.09308 (2024) (9)."},{"key":"e_1_3_2_2_3_1","unstructured":"N. Chen Y. Li J. Tang and J. Li. ''GraphWiz: An Instruction-Following Language Model for Graph Problems''. In: KDD (2024) (2 3 6 9)."},{"key":"e_1_3_2_2_4_1","volume-title":"Introduction to algorithms","author":"Cormen T. H.","year":"2022","unstructured":"T. H. Cormen, C. E. Leiserson, R. L. Rivest, and C. Stein. Introduction to algorithms. MIT press, 2022 (9)."},{"key":"e_1_3_2_2_5_1","unstructured":"B. Fatemi J. Halcrow and B. Perozzi. ''Talk like a Graph: Encoding Graphs for Large Language Models''. In: ICLR. 2023 (1 3 6 9)."},{"key":"e_1_3_2_2_6_1","unstructured":"E. A. Feigenbaum and J. Feldman. ''Computers and thought.'' In: (1963) (1)."},{"key":"e_1_3_2_2_7_1","first-page":"27503","article-title":"Efficiently identifying task groupings for multi-task learning","volume":"34","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 34 (2021), pp. 27503-27516 (5, 7).","journal-title":"NeurIPS"},{"key":"e_1_3_2_2_8_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) (6)."},{"key":"e_1_3_2_2_9_1","volume-title":"The Second Learning on Graphs Conference. 2023 (3).","author":"Georgiev D. G.","unstructured":"D. G. Georgiev, P. Lio, J. Bachurski, J. Chen, T. Shi, and L. Giusti. ''Beyond erdosrenyi: Generalization in algorithmic reasoning on graphs''. In: The Second Learning on Graphs Conference. 2023 (3)."},{"key":"e_1_3_2_2_10_1","unstructured":"P. Guo C.-Y. Lee and D. Ulbricht. ''Learning to branch for multi-task learning''. In: ICML. PMLR. 2020 (3 5-9)."},{"key":"e_1_3_2_2_11_1","unstructured":"H. Hazimeh Z. Zhao A. Chowdhery M. Sathiamoorthy Y. Chen R. Mazumder L. Hong and E. Chi. ''Dselect-k: Differentiable selection in the mixture of experts with applications to multi-task learning''. In: NeurIPS (2021) (5 9)."},{"key":"e_1_3_2_2_12_1","unstructured":"E. J. Hu Y. Shen P. Wallis Z. Allen-Zhu Y. Li S. Wang L. Wang and W. Chen. ''Lora: Low-rank adaptation of large language models''. In: ICLR (2021) (4 6 7)."},{"key":"e_1_3_2_2_13_1","unstructured":"B. Ibarz V. Kurin G. Papamakarios K. Nikiforou M. Bennani R. Csord\u00e1s A. J. Dudzik M. Bo\u0161njak A. Vitvitskyi Y. Rubanova A. Deac B. Bevilacqua Y. Ganin C. Blundell and P. Veli?kovi?. ''A generalist neural algorithmic learner''. In: Learning on graphs conference. 2022 (2 7 9)."},{"key":"e_1_3_2_2_14_1","volume-title":"International conference on machine learning (2022)","author":"Ilyas A.","unstructured":"A. Ilyas, S. M. Park, L. Engstrom, G. Leclerc, and A. Madry. ''Datamodels: Predicting predictions from training data''. In: International conference on machine learning (2022) (2)."},{"key":"e_1_3_2_2_15_1","first-page":"2","article-title":"Neural tangent kernel: Convergence and generalization in neural networks","volume":"31","author":"Jacot A.","year":"2018","unstructured":"A. Jacot, F. Gabriel, and C. Hongler. ''Neural tangent kernel: Convergence and generalization in neural networks''. In: NeurIPS 31 (2018) (2, 4).","journal-title":"NeurIPS"},{"key":"e_1_3_2_2_16_1","doi-asserted-by":"publisher","DOI":"10.1090\/conm\/026\/737400"},{"key":"e_1_3_2_2_17_1","doi-asserted-by":"publisher","DOI":"10.1145\/2623330.2623706"},{"key":"e_1_3_2_2_18_1","doi-asserted-by":"crossref","unstructured":"D. Li H. Ju A. Sharma and H. R. Zhang. ''Boosting multitask learning on graphs through higher-order task affinities''. In: KDD. 2023 (4 5).","DOI":"10.1145\/3580305.3599265"},{"key":"e_1_3_2_2_19_1","first-page":"4","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) (4, 9).","journal-title":"Transactions on Machine Learning Research ("},{"key":"e_1_3_2_2_20_1","unstructured":"D. Li A. Sharma and H. R. Zhang. ''Scalable Multitask Learning Using Gradient based Estimation of Task Affinity''. In: KDD. 2024 (4 6-8)."},{"key":"e_1_3_2_2_21_1","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2024.findings-emnlp.321"},{"key":"e_1_3_2_2_22_1","doi-asserted-by":"crossref","unstructured":"D. Li Z. Zhang L. Wang and H. R. Zhang. ''Efficient Ensemble for Fine-tuning Language Models on Multiple Datasets''. In: ACL (2025) (9).","DOI":"10.18653\/v1\/2025.acl-long.1231"},{"key":"e_1_3_2_2_23_1","doi-asserted-by":"publisher","DOI":"10.1038\/s42256-023-00749-8"},{"key":"e_1_3_2_2_24_1","doi-asserted-by":"crossref","unstructured":"Y. Lu A. Kumar S. Zhai Y. Cheng T. Javidi and R. Feris. ''Fully-adaptive feature sharing in multi-task networks with applications in person attribute classification''. In: CVPR. 2017 (9).","DOI":"10.1109\/CVPR.2017.126"},{"key":"e_1_3_2_2_25_1","volume-title":"International Conference on Machine Learning. 2024 .","author":"de Luca A. B.","unstructured":"A. B. de Luca and K. Fountoulakis. ''Simulation of Graph Algorithms with Looped Transformers''. In: International Conference on Machine Learning. 2024 ."},{"key":"e_1_3_2_2_26_1","unstructured":"Z. Luo X. Song H. Huang J. Lian C. Zhang J. Jiang and X. Xie. ''Graph instruct: Empowering large language models with graph understanding and reasoning capability''. In: arXiv preprint arXiv:2403.04483 (2024) (9)."},{"key":"e_1_3_2_2_27_1","doi-asserted-by":"crossref","unstructured":"J. Ma Z. Zhao X. Yi J. Chen L. Hong and E. H. Chi. ''Modeling task relationships in multi-task learning with multi-gate mixture-of-experts''. In: KDD. 2018 (5 7 9).","DOI":"10.1145\/3219819.3220007"},{"key":"e_1_3_2_2_28_1","unstructured":"L. Markeeva S. McLeish B. Ibarz W. Bounsi O. Kozlova A. Vitvitskyi C. Blundell T. Goldstein A. Schwarzschild and P. Veli?kovi?. ''The CLRS-Text Algorithmic Reasoning Language Benchmark''. In: arXiv preprint arXiv:2406.04229 (2024) (3 6 7 9)."},{"key":"e_1_3_2_2_29_1","unstructured":"L. M\u00fcller D. Kusuma B. Bonet and C. Morris. ''Towards Principled Graph Transformers''. In: NeurIPS (2024) (2-4 6-9)."},{"key":"e_1_3_2_2_30_1","volume-title":"Deep Learning for Code Workshop. 2022 (2).","author":"Nye M.","unstructured":"M. Nye, A. J. Andreassen, G. Gur-Ari, H. Michalewski, J. Austin, D. Bieber, D. Dohan, A. Lewkowycz, M. Bosma, D. Luan, C. Sutton, and A. Odena. ''Show YourWork: Scratchpads for Intermediate Computation with Language Models''. In: Deep Learning for Code Workshop. 2022 (2)."},{"key":"e_1_3_2_2_31_1","unstructured":"S. M. Park K. Georgiev A. Ilyas G. Leclerc and A. Madry. ''Trak: Attributing model behavior at scale''. In: ICML (2023) (2)."},{"key":"e_1_3_2_2_32_1","unstructured":"B. Perozzi B. Fatemi D. Zelle A. Tsitsulin M. Kazemi R. Al-Rfou and J. Halcrow. ''Let your graph do the talking: Encoding structured data for llms''. In: arXiv preprint arXiv:2402.05862 (2024) (9)."},{"key":"e_1_3_2_2_33_1","unstructured":"S. Ruder. ''An Overview of Multi-Task Learning in Deep Neural Networks''. In: arXiv preprint arXiv:1706.05098 (2017) (7 8)."},{"issue":"27","key":"e_1_3_2_2_34_1","first-page":"79","article-title":"Artificial Intelligence: A modern approach","volume":"25","author":"Russell S.","year":"1995","unstructured":"S. Russell and P. Norvig. ''Artificial Intelligence: A modern approach''. In: Artificial Intelligence. Prentice-Hall, Egnlewood Cliffs 25.27 (1995), pp. 79-80 (1).","journal-title":"Artificial Intelligence. Prentice-Hall, Egnlewood Cliffs"},{"key":"e_1_3_2_2_35_1","doi-asserted-by":"crossref","unstructured":"C. Sanford B. Fatemi E. Hall A. Tsitsulin M. Kazemi J. Halcrow B. Perozzi and V. Mirrokni. ''Understanding transformer reasoning capabilities via graph algorithms''. In: NeurIPS (2024) (1).","DOI":"10.52202\/079017-2490"},{"key":"e_1_3_2_2_36_1","volume-title":"International Conference on Learning Representations (2024)","author":"Tang J.","unstructured":"J. Tang, Q. Zhang, Y. Li, N. Chen, and J. Li. ''Grapharena: Evaluating and exploring large language models on graph computation''. In: International Conference on Learning Representations (2024) (9)."},{"key":"e_1_3_2_2_37_1","doi-asserted-by":"crossref","unstructured":"Y. Tian H. Song Z. Wang H. Wang Z. Hu F. Wang N. V. Chawla and P. Xu. ''Graph neural prompting with large language models''. In: AAAI. 2024 (9).","DOI":"10.1609\/aaai.v38i17.29875"},{"key":"e_1_3_2_2_38_1","doi-asserted-by":"publisher","DOI":"10.1109\/ICDM.2006.70"},{"key":"e_1_3_2_2_39_1","doi-asserted-by":"crossref","unstructured":"S. Vandenhende S. Georgoulis B. De Brabandere and L. Van Gool. ''Branched multi-task networks: Deciding what layers to share''. In: BMVC (2020) (9).","DOI":"10.5244\/C.34.59"},{"key":"e_1_3_2_2_40_1","first-page":"1","article-title":"The CLRS algorithmic reasoning benchmark","volume":"2022","author":"P.","unstructured":"P. Veli?kovi?, A. P. Badia, D. Budden, R. Pascanu, A. Banino, M. Dashevskiy, R. Hadsell, and C. Blundell. ''The CLRS algorithmic reasoning benchmark''. In: ICML. 2022 (1-3, 6, 7, 9).","journal-title":"ICML."},{"issue":"7","key":"e_1_3_2_2_41_1","first-page":"1","article-title":"Neural algorithmic reasoning","volume":"2","author":"Blundell P.","year":"2021","unstructured":"P. Veli?kovi? and C. Blundell. ''Neural algorithmic reasoning''. In: Patterns 2.7 (2021) (1, 3).","journal-title":"Patterns"},{"key":"e_1_3_2_2_42_1","volume-title":"International Conference on Learning Representations. 2018 (6, 7).","author":"P.","unstructured":"P. Veli?kovi?, G. Cucurull, A. Casanova, A. Romero, P. Li\u00f2, and Y. Bengio. ''Graph Attention Networks''. In: International Conference on Learning Representations. 2018 (6, 7)."},{"key":"e_1_3_2_2_43_1","unstructured":"P. Veli?kovi? R. Ying M. Padovano R. Hadsell and C. Blundell. ''Neural execution of graph algorithms''. In: ICLR (2020) (7 8)."},{"key":"e_1_3_2_2_44_1","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2022.emnlp-main.174"},{"key":"e_1_3_2_2_45_1","doi-asserted-by":"crossref","unstructured":"H. Wang S. Feng T. He Z. Tan X. Han and Y. Tsvetkov. ''Can Language Models Solve Graph Problems in Natural Language?'' In: NeurIPS (2023) (1 9).","DOI":"10.52202\/075280-1345"},{"key":"e_1_3_2_2_46_1","doi-asserted-by":"publisher","DOI":"10.1109\/TKDE.2016.2518687"},{"key":"e_1_3_2_2_47_1","unstructured":"S. Wu H. R. Zhang and C. R\u00e9. ''Understanding and improving information transfer in multi-task learning''. In: ICLR (2020) (9)."},{"issue":"113","key":"e_1_3_2_2_48_1","first-page":"1","article-title":"high-dimensional asymptotics for quantifying heterogeneous transfers","volume":"26","author":"Yang F.","year":"2025","unstructured":"F. Yang, H. R. Zhang, S. Wu, C. R\u00e9, and W. J. Su. ''Precise high-dimensional asymptotics for quantifying heterogeneous transfers''. In: Journal of Machine Learning Research 26.113 (2025), pp. 1-88 (9).","journal-title":"Journal of Machine Learning Research"},{"key":"e_1_3_2_2_49_1","doi-asserted-by":"crossref","unstructured":"J. Yang and J. Leskovec. ''Overlapping community detection at scale: a nonnegative matrix factorization approach''. In: WSDM. 2013 (6 8).","DOI":"10.1145\/2433396.2433471"},{"key":"e_1_3_2_2_50_1","doi-asserted-by":"publisher","DOI":"10.1145\/2939672.2939804"},{"key":"e_1_3_2_2_51_1","unstructured":"X. Zhang A. Bosselut M. Yasunaga H. Ren P. Liang C. D. Manning and J. Leskovec. ''Greaselm: Graph reasoning enhanced language models for question answering''. In: ICLR (2022) (9)."},{"key":"e_1_3_2_2_52_1","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2025.emnlp-main.832"}],"event":{"name":"KDD '26: The 32nd ACM SIGKDD Conference on Knowledge Discovery and Data Mining","location":"Jeju Island Republic of Korea","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 32nd ACM SIGKDD Conference on Knowledge Discovery and Data Mining V.1"],"original-title":[],"link":[{"URL":"https:\/\/dl.acm.org\/doi\/pdf\/10.1145\/3770854.3780253","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,8,25]],"date-time":"2026-08-25T20:02:15Z","timestamp":1787688135000},"score":1,"resource":{"primary":{"URL":"https:\/\/dl.acm.org\/doi\/10.1145\/3770854.3780253"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2026,4,20]]},"references-count":52,"alternative-id":["10.1145\/3770854.3780253","10.1145\/3770854"],"URL":"https:\/\/doi.org\/10.1145\/3770854.3780253","relation":{},"subject":[],"published":{"date-parts":[[2026,4,20]]},"assertion":[{"value":"2026-04-20","order":3,"name":"published","label":"Published","group":{"name":"publication_history","label":"Publication History"}}]}}