{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,8,21]],"date-time":"2025-08-21T16:49:34Z","timestamp":1755794974694,"version":"3.44.0"},"publisher-location":"New York, NY, USA","reference-count":44,"publisher":"ACM","license":[{"start":{"date-parts":[[2025,7,20]],"date-time":"2025-07-20T00:00:00Z","timestamp":1752969600000},"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":[[2025,7,20]]},"DOI":"10.1145\/3690624.3709295","type":"proceedings-article","created":{"date-parts":[[2025,4,4]],"date-time":"2025-04-04T18:44:43Z","timestamp":1743792283000},"page":"1020-1031","update-policy":"https:\/\/doi.org\/10.1145\/crossmark-policy","source":"Crossref","is-referenced-by-count":0,"title":["On the Support Vector Effect in DNNs: Rethinking Data Selection and Attribution"],"prefix":"10.1145","author":[{"ORCID":"https:\/\/orcid.org\/0009-0001-4170-9695","authenticated-orcid":false,"given":"Syed Hasan Amin","family":"Mahmood","sequence":"first","affiliation":[{"name":"Purdue University, West Lafayette, IN, USA"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-7364-139X","authenticated-orcid":false,"given":"Ming","family":"Yin","sequence":"additional","affiliation":[{"name":"Purdue University, West Lafayette, IN, USA"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-1314-3126","authenticated-orcid":false,"given":"Rajiv","family":"Khanna","sequence":"additional","affiliation":[{"name":"Purdue University, West Lafayette, IN, USA"}],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"320","published-online":{"date-parts":[[2025,7,20]]},"reference":[{"key":"e_1_3_2_1_1_1","volume-title":"Uncertain Gradient Lower Bounds. In International Conference on Learning Representations.","author":"Ash Jordan T","year":"2020","unstructured":"Jordan T Ash, Chicheng Zhang, Akshay Krishnamurthy, John Langford, and Alekh Agarwal. 2020. Deep Batch Active Learning by Diverse, Uncertain Gradient Lower Bounds. In International Conference on Learning Representations."},{"key":"e_1_3_2_1_2_1","volume-title":"Influence Functions in Deep Learning Are Fragile. In International Conference on Learning Representations.","author":"Basu Samyadeep","year":"2020","unstructured":"Samyadeep Basu, Phil Pope, and Soheil Feizi. 2020. Influence Functions in Deep Learning Are Fragile. In International Conference on Learning Representations."},{"key":"e_1_3_2_1_3_1","doi-asserted-by":"publisher","DOI":"10.1080\/00401706.1980.10486199"},{"key":"e_1_3_2_1_4_1","article-title":"Adaptive subgradient methods for online learning and stochastic optimization","volume":"12","author":"Duchi John","year":"2011","unstructured":"John Duchi, Elad Hazan, and Yoram Singer. 2011. Adaptive subgradient methods for online learning and stochastic optimization. Journal of machine learning research, Vol. 12, 7 (2011).","journal-title":"Journal of machine learning research"},{"key":"e_1_3_2_1_5_1","first-page":"2881","article-title":"What neural networks memorize and why: Discovering the long tail via influence estimation","volume":"33","author":"Feldman Vitaly","year":"2020","unstructured":"Vitaly Feldman and Chiyuan Zhang. 2020. What neural networks memorize and why: Discovering the long tail via influence estimation. Advances in Neural Information Processing Systems, Vol. 33 (2020), 2881--2891.","journal-title":"Advances in Neural Information Processing Systems"},{"key":"e_1_3_2_1_6_1","volume-title":"International Conference on Machine Learning. PMLR, 3304--3314","author":"Fu Fangcheng","year":"2020","unstructured":"Fangcheng Fu, Yuzheng Hu, Yihan He, Jiawei Jiang, Yingxia Shao, Ce Zhang, and Bin Cui. 2020. Don't waste your bits! squeeze activations and gradients for deep neural networks via tinyscript. In International Conference on Machine Learning. PMLR, 3304--3314."},{"key":"e_1_3_2_1_7_1","volume-title":"International Conference on Machine Learning. PMLR","author":"Gunasekar Suriya","year":"2018","unstructured":"Suriya Gunasekar, Jason Lee, Daniel Soudry, and Nathan Srebro. 2018. Characterizing implicit bias in terms of optimization geometry. In International Conference on Machine Learning. PMLR, 1832--1841."},{"key":"e_1_3_2_1_8_1","unstructured":"Kazuaki Hanawa Sho Yokoi Satoshi Hara and Kentaro Inui. 2021. Evaluation of Similarity-based Explanations. In ICLR."},{"key":"e_1_3_2_1_9_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2016.90"},{"key":"e_1_3_2_1_10_1","volume-title":"Proceedings of the 39th International Conference on Machine Learning (Proceedings of Machine Learning Research","volume":"9587","author":"Ilyas Andrew","year":"2022","unstructured":"Andrew Ilyas, Sung Min Park, Logan Engstrom, Guillaume Leclerc, and Aleksander Madry. 2022. Datamodels: Understanding Predictions with Data and Data with Predictions. In Proceedings of the 39th International Conference on Machine Learning (Proceedings of Machine Learning Research, Vol. 162). PMLR, 9525--9587."},{"key":"e_1_3_2_1_11_1","first-page":"31796","article-title":"Orient: Submodular mutual information measures for data subset selection under distribution shift","volume":"35","author":"Karanam Athresh","year":"2022","unstructured":"Athresh Karanam, Krishnateja Killamsetty, Harsha Kokel, and Rishabh Iyer. 2022. Orient: Submodular mutual information measures for data subset selection under distribution shift. Advances in Neural Information Processing Systems, Vol. 35 (2022), 31796--31808.","journal-title":"Advances in Neural Information Processing Systems"},{"key":"e_1_3_2_1_12_1","volume-title":"Proceedings of the Twenty-Second International Conference on Artificial Intelligence and Statistics (Proceedings of Machine Learning Research","volume":"3390","author":"Khanna Rajiv","year":"2019","unstructured":"Rajiv Khanna, Been Kim, Joydeep Ghosh, and Sanmi Koyejo. 2019. Interpreting Black Box Predictions using Fisher Kernels. In Proceedings of the Twenty-Second International Conference on Artificial Intelligence and Statistics (Proceedings of Machine Learning Research, Vol. 89), Kamalika Chaudhuri and Masashi Sugiyama (Eds.). PMLR, 3382--3390."},{"key":"e_1_3_2_1_13_1","volume-title":"International Conference on Machine Learning. PMLR, 5464--5474","author":"Killamsetty Krishnateja","year":"2021","unstructured":"Krishnateja Killamsetty, Sivasubramanian Durga, Ganesh Ramakrishnan, Abir De, and Rishabh Iyer. 2021a. Grad-match: Gradient matching based data subset selection for efficient deep model training. In International Conference on Machine Learning. PMLR, 5464--5474."},{"key":"e_1_3_2_1_14_1","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v35i9.16988"},{"key":"e_1_3_2_1_15_1","volume-title":"Advances in Neural Information Processing Systems","volume":"29","author":"Kim Been","year":"2016","unstructured":"Been Kim, Rajiv Khanna, and Oluwasanmi O Koyejo. 2016. Examples are not enough, learn to criticize! criticism for interpretability. Advances in Neural Information Processing Systems, Vol. 29 (2016)."},{"key":"e_1_3_2_1_16_1","volume-title":"Adam: A method for stochastic gradient descent. In ICLR.","author":"Kingma Diederik P","year":"2015","unstructured":"Diederik P Kingma and Jimmy Lei Ba. 2015. Adam: A method for stochastic gradient descent. In ICLR."},{"key":"e_1_3_2_1_17_1","volume-title":"The Eleventh International Conference on Learning Representations.","author":"Kirichenko Polina","year":"2023","unstructured":"Polina Kirichenko, Pavel Izmailov, and Andrew Gordon Wilson. 2023. Last Layer Re-Training is Sufficient for Robustness to Spurious Correlations. In The Eleventh International Conference on Learning Representations."},{"key":"e_1_3_2_1_18_1","volume-title":"International conference on machine learning. PMLR","author":"Koh Pang Wei","year":"2017","unstructured":"Pang Wei Koh and Percy Liang. 2017. Understanding black-box predictions via influence functions. In International conference on machine learning. PMLR, 1885--1894."},{"key":"e_1_3_2_1_19_1","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV48922.2021.00986"},{"key":"e_1_3_2_1_20_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.01167"},{"key":"e_1_3_2_1_21_1","volume-title":"Gradient Descent Maximizes the Margin of Homogeneous Neural Networks. In International Conference on Learning Representations.","author":"Lyu Kaifeng","year":"2019","unstructured":"Kaifeng Lyu and Jian Li. 2019. Gradient Descent Maximizes the Margin of Homogeneous Neural Networks. In International Conference on Learning Representations."},{"key":"e_1_3_2_1_22_1","first-page":"12978","article-title":"Gradient descent on two-layer nets: Margin maximization and simplicity bias","volume":"34","author":"Lyu Kaifeng","year":"2021","unstructured":"Kaifeng Lyu, Zhiyuan Li, Runzhe Wang, and Sanjeev Arora. 2021. Gradient descent on two-layer nets: Margin maximization and simplicity bias. Advances in Neural Information Processing Systems, Vol. 34, 12978--12991.","journal-title":"Advances in Neural Information Processing Systems"},{"key":"e_1_3_2_1_23_1","volume-title":"International Conference on Machine Learning. PMLR, 6950--6960","author":"Mirzasoleiman Baharan","year":"2020","unstructured":"Baharan Mirzasoleiman, Jeff Bilmes, and Jure Leskovec. 2020. Coresets for data-efficient training of machine learning models. In International Conference on Machine Learning. PMLR, 6950--6960."},{"key":"e_1_3_2_1_24_1","volume-title":"International conference on machine learning. PMLR, 2545--2553","author":"Mukkamala Mahesh Chandra","year":"2017","unstructured":"Mahesh Chandra Mukkamala and Matthias Hein. 2017. Variants of rmsprop and adagrad with logarithmic regret bounds. In International conference on machine learning. PMLR, 2545--2553."},{"key":"e_1_3_2_1_25_1","volume-title":"The 22nd International Conference on Artificial Intelligence and Statistics. PMLR, 3051--3059","author":"Nacson Mor Shpigel","year":"2019","unstructured":"Mor Shpigel Nacson, Nathan Srebro, and Daniel Soudry. 2019. Stochastic gradient descent on separable data: Exact convergence with a fixed learning rate. In The 22nd International Conference on Artificial Intelligence and Statistics. PMLR, 3051--3059."},{"key":"e_1_3_2_1_26_1","unstructured":"Behnam Neyshabur. 2017. Implicit Regularization in Deep Learning. arxiv: 1709.01953 [cs.LG]"},{"key":"e_1_3_2_1_27_1","volume-title":"Advances in Neural Information Processing Systems","volume":"28","author":"Neyshabur Behnam","year":"2015","unstructured":"Behnam Neyshabur, Russ R Salakhutdinov, and Nati Srebro. 2015. Path-sgd: Path-normalized optimization in deep neural networks. Advances in Neural Information Processing Systems, Vol. 28 (2015)."},{"key":"e_1_3_2_1_28_1","first-page":"26422","article-title":"The effectiveness of feature attribution methods and its correlation with automatic evaluation scores","volume":"34","author":"Nguyen Giang","year":"2021","unstructured":"Giang Nguyen, Daeyoung Kim, and Anh Nguyen. 2021. The effectiveness of feature attribution methods and its correlation with automatic evaluation scores. Advances in Neural Information Processing Systems, Vol. 34 (2021), 26422--26436.","journal-title":"Advances in Neural Information Processing Systems"},{"key":"e_1_3_2_1_29_1","volume-title":"Proceedings of the 40th International Conference on Machine Learning (Proceedings of Machine Learning Research","volume":"27113","author":"Park Sung Min","year":"2023","unstructured":"Sung Min Park, Kristian Georgiev, Andrew Ilyas, Guillaume Leclerc, and Aleksander Madry. 2023. TRAK: Attributing Model Behavior at Scale. In Proceedings of the 40th International Conference on Machine Learning (Proceedings of Machine Learning Research, Vol. 202). PMLR, 27074--27113."},{"key":"e_1_3_2_1_30_1","first-page":"20596","article-title":"Deep learning on a data diet: Finding important examples early in training","volume":"34","author":"Paul Mansheej","year":"2021","unstructured":"Mansheej Paul, Surya Ganguli, and Gintare Karolina Dziugaite. 2021. Deep learning on a data diet: Finding important examples early in training. Advances in Neural Information Processing Systems, Vol. 34 (2021), 20596--20607.","journal-title":"Advances in Neural Information Processing Systems"},{"key":"e_1_3_2_1_31_1","volume-title":"International Conference on Machine Learning. PMLR, 17848--17869","author":"Pooladzandi Omead","year":"2022","unstructured":"Omead Pooladzandi, David Davini, and Baharan Mirzasoleiman. 2022. Adaptive second order coresets for data-efficient machine learning. In International Conference on Machine Learning. PMLR, 17848--17869."},{"key":"e_1_3_2_1_32_1","first-page":"19920","article-title":"Estimating training data influence by tracing gradient descent","volume":"33","author":"Pruthi Garima","year":"2020","unstructured":"Garima Pruthi, Frederick Liu, Satyen Kale, and Mukund Sundararajan. 2020. Estimating training data influence by tracing gradient descent. Advances in Neural Information Processing Systems, Vol. 33 (2020), 19920--19930.","journal-title":"Advances in Neural Information Processing Systems"},{"key":"e_1_3_2_1_33_1","volume-title":"Advances in Neural Information Processing Systems","volume":"32","author":"Qian Qian","year":"2019","unstructured":"Qian Qian and Xiaoyuan Qian. 2019. The implicit bias of adagrad on separable data. Advances in Neural Information Processing Systems, Vol. 32 (2019)."},{"key":"e_1_3_2_1_34_1","volume-title":"Theoretical and Practical Perspectives on what Influence Functions Do. Advances in Neural Information Processing Systems","author":"Schioppa Andrea","year":"2023","unstructured":"Andrea Schioppa, Katja Filippova, Ivan Titov, and Polina Zablotskaia. 2023. Theoretical and Practical Perspectives on what Influence Functions Do. Advances in Neural Information Processing Systems (2023)."},{"key":"e_1_3_2_1_35_1","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v36i8.20791"},{"key":"e_1_3_2_1_36_1","volume-title":"International Conference on Machine Learning. PMLR, 3067--3075","author":"Shalev-Shwartz Shai","year":"2017","unstructured":"Shai Shalev-Shwartz, Ohad Shamir, and Shaked Shammah. 2017. Failures of gradient-based deep learning. In International Conference on Machine Learning. PMLR, 3067--3075."},{"key":"e_1_3_2_1_37_1","doi-asserted-by":"publisher","DOI":"10.5555\/3291125.3309632"},{"key":"e_1_3_2_1_38_1","first-page":"23347","article-title":"Representer point selection via local jacobian expansion for post-hoc classifier explanation of deep neural networks and ensemble models","volume":"34","author":"Sui Yi","year":"2021","unstructured":"Yi Sui, Ga Wu, and Scott Sanner. 2021. Representer point selection via local jacobian expansion for post-hoc classifier explanation of deep neural networks and ensemble models. Advances in Neural Information Processing Systems, Vol. 34 (2021), 23347--23358.","journal-title":"Advances in Neural Information Processing Systems"},{"key":"e_1_3_2_1_39_1","volume-title":"International conference on machine learning. PMLR, 6105--6114","author":"Tan Mingxing","year":"2019","unstructured":"Mingxing Tan and Quoc Le. 2019. Efficientnet: Rethinking model scaling for convolutional neural networks. In International conference on machine learning. PMLR, 6105--6114."},{"key":"e_1_3_2_1_40_1","volume-title":"International Conference on Machine Learning. PMLR, 10849--10858","author":"Wang Bohan","year":"2021","unstructured":"Bohan Wang, Qi Meng, Wei Chen, and Tie-Yan Liu. 2021. The implicit bias for adaptive optimization algorithms on homogeneous neural networks. In International Conference on Machine Learning. PMLR, 10849--10858."},{"key":"e_1_3_2_1_41_1","volume-title":"Towards Sustainable Learning: Coresets for Data-efficient Deep Learning. International Conference on Machine Learning (ICML)","author":"Yang Yu","year":"2023","unstructured":"Yu Yang, Hao Kang, and Baharan Mirzasoleiman. 2023. Towards Sustainable Learning: Coresets for Data-efficient Deep Learning. International Conference on Machine Learning (ICML) (2023)."},{"key":"e_1_3_2_1_42_1","volume-title":"Ian En-Hsu Yen, and Pradeep K Ravikumar","author":"Yeh Chih-Kuan","year":"2018","unstructured":"Chih-Kuan Yeh, Joon Kim, Ian En-Hsu Yen, and Pradeep K Ravikumar. 2018. Representer point selection for explaining deep neural networks. Advances in Neural Information Processing Systems, Vol. 31 (2018)."},{"key":"e_1_3_2_1_43_1","first-page":"32285","article-title":"First is Better Than Last for Language Data Influence","volume":"35","author":"Yeh Chih-Kuan","year":"2022","unstructured":"Chih-Kuan Yeh, Ankur Taly, Mukund Sundararajan, Frederick Liu, and Pradeep Ravikumar. 2022. First is Better Than Last for Language Data Influence. Advances in Neural Information Processing Systems, Vol. 35 (2022), 32285--32298.","journal-title":"Advances in Neural Information Processing Systems"},{"key":"e_1_3_2_1_44_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2018.00068"}],"event":{"name":"KDD '25: The 31st ACM SIGKDD Conference on Knowledge Discovery and Data Mining","sponsor":["SIGMOD ACM Special Interest Group on Management of Data","SIGKDD ACM Special Interest Group on Knowledge Discovery in Data"],"location":"Toronto ON Canada","acronym":"KDD '25"},"container-title":["Proceedings of the 31st ACM SIGKDD Conference on Knowledge Discovery and Data Mining V.1"],"original-title":[],"link":[{"URL":"https:\/\/dl.acm.org\/doi\/10.1145\/3690624.3709295","content-type":"unspecified","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/dl.acm.org\/doi\/pdf\/10.1145\/3690624.3709295","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,8,16]],"date-time":"2025-08-16T15:46:18Z","timestamp":1755359178000},"score":1,"resource":{"primary":{"URL":"https:\/\/dl.acm.org\/doi\/10.1145\/3690624.3709295"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2025,7,20]]},"references-count":44,"alternative-id":["10.1145\/3690624.3709295","10.1145\/3690624"],"URL":"https:\/\/doi.org\/10.1145\/3690624.3709295","relation":{},"subject":[],"published":{"date-parts":[[2025,7,20]]},"assertion":[{"value":"2025-07-20","order":3,"name":"published","label":"Published","group":{"name":"publication_history","label":"Publication History"}}]}}