{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,3,25]],"date-time":"2026-03-25T14:30:26Z","timestamp":1774449026444,"version":"3.50.1"},"reference-count":69,"publisher":"Association for Computing Machinery (ACM)","issue":"1","content-domain":{"domain":["dl.acm.org"],"crossmark-restriction":true},"short-container-title":["ACM Trans. Inf. Syst."],"published-print":{"date-parts":[[2026,1,31]]},"abstract":"<jats:p>Dense Information Retrieval (IR) systems rely on neural networks to embed documents and queries within a latent low-dimensional space. Among the Dense IR approaches, bi-encoders are particularly popular, as they achieve state-of-the-art performance and allow for efficient encoding of documents and queries. Nevertheless, using this class of systems, by construction, all the documents and queries are represented using the same set of dimensions. In this article, we introduce the Manifold Clustering (MC) hypothesis which states that, for each query, there exists a query-dependent manifold of the original embedding space where the query and documents relevant to it cluster more effectively. We empirically validate the MC hypothesis showing that it is possible to find a query-dependent linear subspace of the original embedding space where high retrieval effectiveness is achieved. To find such subspaces, we propose the Dimension IMportance Estimators (DIMEs), a class of models that associate an importance score with each dimension of an embedding and can be used to project the dense representations only on the most important dimensions. We first demonstrate the effectiveness of the DIMEs by proposing an oracle DIME which employs annotated documents and induces performance improvements as big as +184% in terms of AP. To demonstrate the practical applicability of the DIMEs beyond the oracle, we also propose a set of DIMEs based on pseudo-relevance and active feedback that induce improvement as big as +49.6% in terms of AP and +55.9% in terms of nDCG@10. The effectiveness of such DIMEs not only empirically supports the MC hypothesis, but illustrates an actual strategy to outperform the state-of-the-art that does not require any form of retraining, fine-tuning or re-indexing and can be efficiently implemented at retrieval time.<\/jats:p>","DOI":"10.1145\/3765619","type":"journal-article","created":{"date-parts":[[2025,9,2]],"date-time":"2025-09-02T13:17:56Z","timestamp":1756819076000},"page":"1-34","update-policy":"https:\/\/doi.org\/10.1145\/crossmark-policy","source":"Crossref","is-referenced-by-count":1,"title":["Getting off the DIME: Dimension Pruning via Dimension Importance Estimation for Dense Information Retrieval"],"prefix":"10.1145","volume":"44","author":[{"ORCID":"https:\/\/orcid.org\/0000-0002-5070-2049","authenticated-orcid":false,"given":"Guglielmo","family":"Faggioli","sequence":"first","affiliation":[{"name":"Department of Information Engineering, University of Padua, Padova, Italy"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-9219-6239","authenticated-orcid":false,"given":"Nicola","family":"Ferro","sequence":"additional","affiliation":[{"name":"Department of Information Engineering, University of Padua, Padova, Italy"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-7189-4724","authenticated-orcid":false,"given":"Raffaele","family":"Perego","sequence":"additional","affiliation":[{"name":"Consiglio Nazionale delle Ricerche, Istituto di Scienza e Tecnologie dell\u2019Informazione \u201cAlessandro Faedo\u201d, Pisa, Italy"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-7427-1001","authenticated-orcid":false,"given":"Nicola","family":"Tonellotto","sequence":"additional","affiliation":[{"name":"Department of Information Engineering, University of Pisa, Pisa, Italy"}],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"320","published-online":{"date-parts":[[2025,10,14]]},"reference":[{"key":"e_1_3_2_2_2","volume-title":"Probability Models for Information Retrieval Based on Divergence from Randomness","author":"Amati Giambattista","year":"2003","unstructured":"Giambattista Amati. 2003. Probability Models for Information Retrieval Based on Divergence from Randomness. Ph.D. Dissertation. University of Glasgow, UK. Retrieved from http:\/\/theses.gla.ac.uk\/1570\/"},{"key":"e_1_3_2_3_2","doi-asserted-by":"publisher","DOI":"10.1145\/582415.582416"},{"key":"e_1_3_2_4_2","doi-asserted-by":"publisher","DOI":"10.1145\/2911451.2914671"},{"key":"e_1_3_2_5_2","doi-asserted-by":"publisher","DOI":"10.1145\/3077136.3080839"},{"key":"e_1_3_2_6_2","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2013.50"},{"key":"e_1_3_2_7_2","doi-asserted-by":"publisher","DOI":"10.1145\/3345001"},{"key":"e_1_3_2_8_2","doi-asserted-by":"publisher","unstructured":"Trevor J. Bihl Kenneth W. Bauer Jr. and Michael A. Temple. 2016. Feature selection for RF fingerprinting with multiple discriminant analysis and using ZigBee device emissions. IEEE Transactions on Information Forensics and Security 11 8 (2016) 1862\u20131874. DOI: 10.1109\/TIFS.2016.2561902","DOI":"10.1109\/TIFS.2016.2561902"},{"key":"e_1_3_2_9_2","doi-asserted-by":"publisher","DOI":"10.1145\/956863.956866"},{"key":"e_1_3_2_10_2","volume-title":"International Conference on Learning Representations","author":"Cai Xingyu","year":"2021","unstructured":"Xingyu Cai, Jiaji Huang, Yuchen Bian, and Kenneth Church. 2021. Isotropy in the contextual embedding space: Clusters and manifolds. In Proceedings of the International Conference on Learning Representations. Retrieved from https:\/\/openreview.net\/forum?id=xYGNO86OWDH"},{"key":"e_1_3_2_11_2","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2023.emnlp-main.762"},{"key":"e_1_3_2_12_2","doi-asserted-by":"crossref","unstructured":"Nick Craswell Bhaskar Mitra Emine Yilmaz and Daniel Campos. 2021. Overview of the TREC 2020 deep learning track. arXiv:2102.07662. Retrieved from https:\/\/arxiv.org\/abs\/2102.07662","DOI":"10.6028\/NIST.SP.1266.deep-overview"},{"key":"e_1_3_2_13_2","doi-asserted-by":"crossref","unstructured":"Nick Craswell Bhaskar Mitra Emine Yilmaz Daniel Campos and Ellen M. Voorhees. 2020. Overview of the TREC 2019 deep learning track. arXiv:2003.07820. Retrieved from https:\/\/arxiv.org\/abs\/2003.07820","DOI":"10.6028\/NIST.SP.1266.deep-overview"},{"key":"e_1_3_2_14_2","doi-asserted-by":"publisher","unstructured":"J. Shane Culpepper Guglielmo Faggioli Nicola Ferro and Oren Kurland. 2022. Topic difficulty: Collection and query formulation effects. ACM Transactions on Information Systems 40 1 Article 19 (2022) 1\u201336. DOI: 10.1145\/3470563","DOI":"10.1145\/3470563"},{"key":"e_1_3_2_15_2","doi-asserted-by":"publisher","DOI":"10.1145\/3477495.3531755"},{"key":"e_1_3_2_16_2","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/n19-1423"},{"key":"e_1_3_2_17_2","doi-asserted-by":"publisher","DOI":"10.1016\/j.procs.2020.04.167"},{"key":"e_1_3_2_18_2","doi-asserted-by":"publisher","DOI":"10.3390\/app11199075"},{"key":"e_1_3_2_19_2","doi-asserted-by":"publisher","DOI":"10.18653\/V1\/P16-1035"},{"key":"e_1_3_2_20_2","doi-asserted-by":"publisher","DOI":"10.1145\/3578337.3605136"},{"key":"e_1_3_2_21_2","volume-title":"Proceedings of the 47th International ACM SIGIR Conference on Research and Development in Information Retrieval (SIGIR \u201924)","author":"Faggioli Guglielmo","year":"2024","unstructured":"Guglielmo Faggioli, Nicola Ferro, Raffaele Perego, and Nicola Tonellotto. 2024. Dimension importance estimation for dense information retrieval. In Proceedings of the 47th International ACM SIGIR Conference on Research and Development in Information Retrieval (SIGIR \u201924). ACM."},{"key":"e_1_3_2_22_2","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-72113-8_8"},{"key":"e_1_3_2_23_2","doi-asserted-by":"publisher","unstructured":"Guglielmo Faggioli Oleg Zendel J. Shane Culpepper Nicola Ferro and Falk Scholer. 2022. sMARE: A new paradigm to evaluate and understand query performance prediction methods. Information Retrieval Journal 25 2 (2022) 94\u2013122. DOI: 10.1007\/S10791-022-09407-W","DOI":"10.1007\/S10791-022-09407-W"},{"key":"e_1_3_2_24_2","doi-asserted-by":"publisher","DOI":"10.1145\/3404835.3463098"},{"key":"e_1_3_2_25_2","doi-asserted-by":"publisher","DOI":"10.1145\/2970398.2970433"},{"key":"e_1_3_2_26_2","doi-asserted-by":"publisher","DOI":"10.1145\/2970398.2970433"},{"key":"e_1_3_2_27_2","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2021.conll-1.7"},{"key":"e_1_3_2_28_2","doi-asserted-by":"publisher","DOI":"10.1145\/3404835.3462891"},{"key":"e_1_3_2_29_2","unstructured":"Gautier Izacard Mathilde Caron Lucas Hosseini Sebastian Riedel Piotr Bojanowski Armand Joulin and Edouard Grave. 2021. Towards unsupervised dense information retrieval with contrastive learning. arXiv:2112.09118. Retrieved from https:\/\/arxiv.org\/abs\/2112.09118"},{"key":"e_1_3_2_30_2","doi-asserted-by":"publisher","DOI":"10.1109\/TBDATA.2019.2921572"},{"key":"e_1_3_2_31_2","doi-asserted-by":"publisher","DOI":"10.1109\/MIPRO.2015.7160458"},{"key":"e_1_3_2_32_2","doi-asserted-by":"publisher","DOI":"10.1162\/TACL_A_00405"},{"key":"e_1_3_2_33_2","volume-title":"Proceedings of the Advances in Neural Information Processing Systems 35: Annual Conference on Neural Information Processing Systems 2022 (NeurIPS \u201922)","author":"Kusupati Aditya","year":"2022","unstructured":"Aditya Kusupati, Gantavya Bhatt, Aniket Rege, Matthew Wallingford, Aditya Sinha, Vivek Ramanujan, William Howard-Snyder, Kaifeng Chen, Sham M. Kakade, Prateek Jain, et al. 2022. Matryoshka representation learning. In Proceedings of the Advances in Neural Information Processing Systems 35: Annual Conference on Neural Information Processing Systems 2022 (NeurIPS \u201922). Sanmi Koyejo, S. Mohamed, A. Agarwal, Danielle Belgrave, K. Cho, and A. Oh (Eds.). Retrieved from http:\/\/papers.nips.cc\/paper_files\/paper\/2022\/hash\/c32319f4868da7613d78af9993100e42-Abstract-Conference.html"},{"key":"e_1_3_2_34_2","doi-asserted-by":"publisher","DOI":"10.1145\/2983323.2983876"},{"key":"e_1_3_2_35_2","doi-asserted-by":"publisher","unstructured":"Hang Li Ahmed Mourad Shengyao Zhuang Bevan Koopman and Guido Zuccon. 2023. Pseudo relevance feedback with deep language models and dense retrievers: Successes and pitfalls. ACM Transactions on Information Systems 41 3 Article 62 (2023) 1\u201340. DOI: 10.1145\/3570724","DOI":"10.1145\/3570724"},{"key":"e_1_3_2_36_2","doi-asserted-by":"publisher","unstructured":"Jundong Li Kewei Cheng Suhang Wang Fred Morstatter Robert P. Trevino Jiliang Tang and Huan Liu. 2018. Feature selection: A data perspective. ACM Computing Surveys 50 6 Article 94 (2018) 1\u201345. DOI: 10.1145\/3136625","DOI":"10.1145\/3136625"},{"key":"e_1_3_2_37_2","unstructured":"Xianming Li Zongxi Li Jing Li Haoran Xie and Qing Li. 2024. 2D Matryoshka sentence embeddings. arXiv:2402.14776. Retrieved from https:\/\/arxiv.org\/abs\/2402.14776"},{"key":"e_1_3_2_38_2","doi-asserted-by":"publisher","DOI":"10.18653\/V1\/2023.FINDINGS-EMNLP.423"},{"key":"e_1_3_2_39_2","unstructured":"Sheng-Chieh Lin Jheng-Hong Yang and Jimmy Lin. 2020. Distilling dense representations for ranking using tightly-coupled teachers. axXiv:2010.11386. Retrieved from https:\/\/arxiv.org\/abs\/2010.11386"},{"key":"e_1_3_2_40_2","doi-asserted-by":"publisher","DOI":"10.1145\/3341981.3344224"},{"key":"e_1_3_2_41_2","doi-asserted-by":"publisher","DOI":"10.1162\/tacl_a_00369"},{"key":"e_1_3_2_42_2","doi-asserted-by":"crossref","unstructured":"Sean MacAvaney and Luca Soldaini. 2023. One-shot labeling for automatic relevance estimation. arXiv:2302.11266. Retrieved from https:\/\/arxiv.org\/abs\/2302.11266","DOI":"10.1145\/3539618.3592032"},{"key":"e_1_3_2_43_2","doi-asserted-by":"publisher","DOI":"10.1145\/3539618.3591992"},{"key":"e_1_3_2_44_2","doi-asserted-by":"publisher","DOI":"10.1145\/3404835.3463262"},{"key":"e_1_3_2_45_2","doi-asserted-by":"publisher","DOI":"10.5555\/3524938.3525561"},{"key":"e_1_3_2_46_2","volume-title":"Proceedings of the Workshop on Cognitive Computation: Integrating Neural and Symbolic Approaches 2016 Co-Located with the 30th Annual Conference on Neural Information Processing Systems (NIPS \u201916)CEUR Workshop Proceedings, Vol","volume":"1773","author":"Nguyen Tri","year":"2016","unstructured":"Tri Nguyen, Mir Rosenberg, Xia Song, Jianfeng Gao, Saurabh Tiwary, Rangan Majumder, and Li Deng. 2016. MS MARCO: A human generated MAchine Reading COmprehension dataset. In Proceedings of the Workshop on Cognitive Computation: Integrating Neural and Symbolic Approaches 2016 Co-Located with the 30th Annual Conference on Neural Information Processing Systems (NIPS \u201916). Tarek Richard Besold, Antoine Bordes, Artur S. d\u2019Avila Garcez, and Greg Wayne (Eds.), CEUR Workshop Proceedings, Vol. 1773, CEUR-WS.org. Retrieved from https:\/\/ceur-ws.org\/Vol-1773\/CoCoNIPS_2016_paper9.pdf"},{"key":"e_1_3_2_47_2","unstructured":"Rodrigo Frassetto Nogueira and Kyunghyun Cho. 2019. Passage re-ranking with BERT. axXiv:1901.04085. Retrieved from http:\/\/arxiv.org\/abs\/1901.04085"},{"key":"e_1_3_2_48_2","unstructured":"OpenAI. 2023. ChatGPT [Large Language Model]. Retrieved December 2023 from https:\/\/chatgpt.com\/"},{"key":"e_1_3_2_49_2","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2005.159"},{"key":"e_1_3_2_50_2","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-99736-6_27"},{"key":"e_1_3_2_51_2","volume-title":"Proceedings of the International Conference on Learning Representations","author":"Pope Phil","year":"2021","unstructured":"Phil Pope, Chen Zhu, Ahmed Abdelkader, Micah Goldblum, and Tom Goldstein. 2021. The intrinsic dimension of images and its impact on learning. In Proceedings of the International Conference on Learning Representations. Retrieved from https:\/\/openreview.net\/forum?id=XJk19XzGq2J"},{"key":"e_1_3_2_52_2","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-72240-1_34"},{"key":"e_1_3_2_53_2","doi-asserted-by":"publisher","DOI":"10.1109\/ACCESS.2019.2902640"},{"key":"e_1_3_2_54_2","volume-title":"The SMART Retrieval System: Experiments in Automatic Document Processing","author":"Rocchio Jr Joseph John","year":"1971","unstructured":"Joseph John Rocchio Jr. 1971. Relevance feedback in information retrieval. The SMART Retrieval System: Experiments in Automatic Document Processing."},{"key":"e_1_3_2_55_2","doi-asserted-by":"publisher","unstructured":"Irene Rodr\u00edguez-Luj\u00e1n Ram\u00f3n Huerta Charles Elkan and Carlos. Santa Cruz. 2010. Quadratic programming feature selection. Journal of Machine Learning Research 11 (2010) 1491\u20131516. DOI: 10.5555\/1756006.1859900","DOI":"10.5555\/1756006.1859900"},{"key":"e_1_3_2_56_2","doi-asserted-by":"publisher","DOI":"10.1145\/3269206.3269277"},{"key":"e_1_3_2_57_2","unstructured":"Dwaipayan Roy Debjyoti Paul Mandar Mitra and Utpal Garain. 2016. Using word embeddings for automatic query expansion. axXiv:1606.07608. Retrieved from http:\/\/arxiv.org\/abs\/1606.07608"},{"key":"e_1_3_2_58_2","doi-asserted-by":"publisher","DOI":"10.1002\/9781118491683"},{"key":"e_1_3_2_59_2","doi-asserted-by":"publisher","DOI":"10.1007\/11875581_123"},{"key":"e_1_3_2_60_2","doi-asserted-by":"publisher","DOI":"10.1145\/3626772.3657707"},{"key":"e_1_3_2_61_2","unstructured":"Kari Torkkola. 2003. Feature extraction by non-parametric mutual information maximization. Journal of Machine Learning Research 3 (2003) 1415\u20131438. Retrieved from http:\/\/jmlr.org\/papers\/v3\/torkkola03a.html"},{"key":"e_1_3_2_62_2","doi-asserted-by":"publisher","DOI":"10.2307\/3001913"},{"key":"e_1_3_2_63_2","volume-title":"Information Retrieval","author":"van Rijsbergen C. J.","year":"1979","unstructured":"C. J. van Rijsbergen. 1979. Information Retrieval. Butterworth."},{"key":"e_1_3_2_64_2","doi-asserted-by":"publisher","unstructured":"Ellen Voorhees. 2005. Overview of the TREC 2004 Robust Retrieval Track. Special Publication (NIST SP) National Institute of Standards and Technology Gaithersburg MD [online]. Retrieved from 10.6028\/NIST.SP.500-261","DOI":"10.6028\/NIST.SP.500-261"},{"key":"e_1_3_2_65_2","volume-title":"9th International Conference on Learning Representations (ICLR \u201921), Virtual Event","author":"Xiong Lee","year":"2021","unstructured":"Lee Xiong, Chenyan Xiong, Ye Li, Kwok-Fung Tang, Jialin Liu, Paul N. Bennett, Junaid Ahmed, and Arnold Overwijk. 2021. Approximate nearest neighbor negative contrastive learning for dense text retrieval. In Proceedings of the 9th International Conference on Learning Representations (ICLR \u201921), Virtual Event. OpenReview.net. Retrieved from https:\/\/openreview.net\/forum?id=zeFrfgyZln"},{"key":"e_1_3_2_66_2","doi-asserted-by":"publisher","DOI":"10.1145\/2970398.2970405"},{"key":"e_1_3_2_67_2","doi-asserted-by":"publisher","DOI":"10.1145\/3404835.3463039"},{"key":"e_1_3_2_68_2","doi-asserted-by":"publisher","DOI":"10.1016\/j.patcog.2015.02.025"},{"key":"e_1_3_2_69_2","doi-asserted-by":"publisher","DOI":"10.1145\/3404835.3462880"},{"key":"e_1_3_2_70_2","doi-asserted-by":"publisher","DOI":"10.1145\/3477495.3531994"}],"container-title":["ACM Transactions on Information Systems"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/dl.acm.org\/doi\/pdf\/10.1145\/3765619","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,10,14]],"date-time":"2025-10-14T18:31:07Z","timestamp":1760466667000},"score":1,"resource":{"primary":{"URL":"https:\/\/dl.acm.org\/doi\/10.1145\/3765619"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2025,10,14]]},"references-count":69,"journal-issue":{"issue":"1","published-print":{"date-parts":[[2026,1,31]]}},"alternative-id":["10.1145\/3765619"],"URL":"https:\/\/doi.org\/10.1145\/3765619","relation":{},"ISSN":["1046-8188","1558-2868"],"issn-type":[{"value":"1046-8188","type":"print"},{"value":"1558-2868","type":"electronic"}],"subject":[],"published":{"date-parts":[[2025,10,14]]},"assertion":[{"value":"2024-08-07","order":0,"name":"received","label":"Received","group":{"name":"publication_history","label":"Publication History"}},{"value":"2025-08-16","order":2,"name":"accepted","label":"Accepted","group":{"name":"publication_history","label":"Publication History"}},{"value":"2025-10-14","order":3,"name":"published","label":"Published","group":{"name":"publication_history","label":"Publication History"}}]}}