{"list":"other","total":55,"rows":[{"id":"1512.03385","title":"Deep Residual Learning for Image Recognition","created":"2015-12-10","cited_by_count":52096},{"id":"1405.0312","title":"Microsoft COCO: Common Objects in Context","created":"2014-05-01","cited_by_count":17608},{"id":"1910.01108","title":"DistilBERT, a distilled version of BERT: smaller, faster, cheaper and lighter","created":"2019-10-02","cited_by_count":4307},{"id":"1805.07836","title":"Generalized Cross Entropy Loss for Training Deep Neural Networks with Noisy Labels","created":"2018-05-20","cited_by_count":997},{"id":"1712.09482","title":"Robust Loss Functions under Label Noise for Deep Neural Networks","created":"2017-12-27","cited_by_count":443},{"id":"2009.14119","title":"Asymmetric Loss For Multi-Label Classification","created":"2020-09-29","cited_by_count":381},{"id":"2304.07288","title":"Cross-Entropy Loss Functions: Theoretical Analysis and Applications","created":"2023-04-14","cited_by_count":210},{"id":"1307.5101","title":"Large-scale Multi-label Learning with Missing Labels","created":"2013-07-18","cited_by_count":58},{"id":"1810.11671","title":"A no-regret generalization of hierarchical softmax to extreme multi-label classification","created":"2018-10-27","cited_by_count":52},{"id":"1608.04802","title":"Scalable Learning of Non-Decomposable Objectives","created":"2016-08-16","cited_by_count":41},{"id":"2102.07113","title":"Comprehensive Comparative Study of Multi-Label Classification Methods","created":"2021-02-14","cited_by_count":38},{"id":"2310.14774","title":"Principled Approaches for Learning to Defer with Multiple Experts","created":"2023-10-23","cited_by_count":38},{"id":"1609.00288","title":"A Unified View of Multi-Label Performance Measures","created":"2016-09-01","cited_by_count":36},{"id":"2310.14772","title":"Predictor-Rejector Multi-Class Abstention: Theoretical Analysis and Algorithms","created":"2023-10-23","cited_by_count":36},{"id":"2301.09044","title":"Learning to Reject with a Fixed Predictor: Application to Decontextualization","created":"2023-01-22","cited_by_count":32},{"id":"2310.14770","title":"Theoretically Grounded Loss Functions and Algorithms for Score-Based Multi-Class Abstention","created":"2023-10-23","cited_by_count":32},{"id":"2403.19494","title":"Regression with Multi-Expert Deferral","created":"2024-03-28","cited_by_count":29},{"id":"2307.02035","title":"Ranking with Abstention","created":"2023-07-05","cited_by_count":27},{"id":"2407.13732","title":"Realizable $H$-Consistent and Bayes-Consistent Loss Functions for Learning to Defer","created":"2024-07-18","cited_by_count":26},{"id":"2405.05968","title":"A Universal Growth Rate for Learning with Smooth Surrogate Losses","created":"2024-05-09","cited_by_count":24},{"id":"2108.10566","title":"sigmoidF1: A Smooth F1 Score Surrogate Loss for Multilabel Classification","created":"2021-08-24","cited_by_count":23},{"id":"2407.07140","title":"Cardinality-Aware Set Prediction and Top-$k$ Classification","created":"2024-07-09","cited_by_count":23},{"id":"2407.13746","title":"Multi-Label Learning with Stronger Consistency Guarantees","created":"2024-07-18","cited_by_count":22},{"id":"1410.6776","title":"Online and Stochastic Gradient Methods for Non-decomposable Loss Functions","created":"2014-10-24","cited_by_count":21},{"id":"2403.19480","title":"$H$-Consistency Guarantees for Regression","created":"2024-03-28","cited_by_count":21},{"id":"2401.16549","title":"Deep Learning for Multi-Label Learning: A Comprehensive Survey","created":"2024-01-29","cited_by_count":19},{"id":"1505.06812","title":"Optimizing Non-decomposable Performance Measures: A Tale of Two Classes","created":"2015-05-26","cited_by_count":18},{"id":"2009.07801","title":"Convex Calibrated Surrogates for the Multi-Label F-Measure","created":"2020-09-16","cited_by_count":18},{"id":"2407.13722","title":"Enhanced $H$-Consistency Bounds","created":"2024-07-18","cited_by_count":18},{"id":"1310.4849","title":"On the Bayes-optimality of F-measure maximizers","created":"2013-10-17","cited_by_count":16},{"id":"2506.20650","title":"Mastering Multiple-Expert Routing: Realizable $H$-Consistency and Strong Guarantees for Learning to Defer","created":"2025-06-25","cited_by_count":16},{"id":"2502.10381","title":"Balancing the Scales: A Theoretical and Algorithmic Framework for Learning from Imbalanced Data","created":"2025-02-14","cited_by_count":15},{"id":"1504.07272","title":"Surrogate regret bounds for generalized classification performance metrics","created":"2015-04-27","cited_by_count":14},{"id":"2011.07805","title":"Multi-label classification: do Hamming loss and subset accuracy really conflict with each other?","created":"2020-11-16","cited_by_count":14},{"id":"2210.09695","title":"Consistent Multiclass Algorithms for Complex Metrics and Constraints","created":"2022-10-18","cited_by_count":13},{"id":"2510.26706","title":"Budgeted Multiple-Expert Deferral","created":"2025-10-30","cited_by_count":13},{"id":"1806.00640","title":"Binary Classification with Karmic, Threshold-Quasi-Concave Metrics","created":"2018-06-02","cited_by_count":11},{"id":"1802.00086","title":"Optimizing Non-decomposable Measures with Deep Networks","created":"2018-01-31","cited_by_count":10},{"id":"1905.12511","title":"Calibrated Surrogate Maximization of Linear-fractional Utility in Binary Classification","created":"2019-05-29","cited_by_count":10},{"id":"2105.05026","title":"Rethinking and Reweighting the Univariate Losses for Multi-Label Ranking: Consistency and Generalization","created":"2021-05-10","cited_by_count":9},{"id":"2512.23947","title":"Improved Balanced Classification with Theoretically Grounded Loss Functions","created":"2025-12-30","cited_by_count":9},{"id":"1912.00965","title":"AP-Perf: Incorporating Generic Performance Metrics in Differentiable Learning","created":"2019-12-02","cited_by_count":8},{"id":"2512.22886","title":"Theory and Algorithms for Learning with Multi-Class Abstention and Multi-Expert Deferral","created":"2025-12-28","cited_by_count":8},{"id":"2511.15816","title":"Beyond Tsybakov: Model Margin Noise and $\\mathcal{H}$-Consistency Bounds","created":"2025-11-19","cited_by_count":7},{"id":"2512.22880","title":"Fundamental Novel Consistency Theory: $H$-Consistency Bounds","created":"2025-12-28","cited_by_count":6},{"id":"2512.23133","title":"Principled Algorithms for Optimizing Generalized Metrics in Binary Classification","created":"2025-12-29","cited_by_count":6},{"id":"2103.00396","title":"A Minimax Probability Machine for Non-Decomposable Performance Measures","created":"2021-02-28","cited_by_count":4},{"id":"2305.05248","title":"Towards Understanding Generalization of Macro-AUC in Multi-label Learning","created":"2023-05-09","cited_by_count":4},{"id":"2401.16594","title":"Consistent algorithms for multi-label classification with macro-at-$k$ metrics","created":"2024-01-29","cited_by_count":4},{"id":"2602.17554","title":"A Theoretical Framework for Modular Learning of Robust Generative Models","created":"2026-02-19","cited_by_count":4},{"id":"1501.00287","title":"Consistent Classification Algorithms for Multi-class Non-Decomposable Performance Metrics","created":"2015-01-01","cited_by_count":2},{"id":"2403.18301","title":"Selective Mixup Fine-Tuning for Optimizing Non-Decomposable Objectives","created":"2024-03-27","cited_by_count":2},{"id":"2406.14743","title":"A General Online Algorithm for Optimizing Complex Performance Metrics","created":"2024-06-20","cited_by_count":2},{"id":"2604.27723","title":"Optimized Deferral for Imbalanced Settings","created":"2026-04-30","cited_by_count":2},{"id":"2604.27742","title":"Linear-Core Surrogates: Smooth Loss Functions with Linear Rates for Classification and Structured Prediction","created":"2026-04-30","cited_by_count":2}],"next_cursor":null}