mlsanityData to 7 Oct 2026

LibAUC: A Deep Learning Library for X-Risk Optimization

arXiv 2306.03065 ↗First posted 5 Jun 2023cs.LG cs.AI math.OCcited by 15

Not on the map. Why?

Abstract (arXiv)

This paper introduces the award-winning deep learning (DL) library called LibAUC for implementing state-of-the-art algorithms towards optimizing a family of risk functions named X-risks. X-risks refer to a family of compositional functions in which the loss function of each data point is defined in a way that contrasts the data point with a large number of others. They have broad applications in AI for solving classical and emerging problems, including but not limited to classification for imbalanced data (CID), learning to rank (LTR), and contrastive learning of representations (CLR). The motivation of developing LibAUC is to address the convergence issues of existing libraries for solving these problems. In particular, existing libraries may not converge or require very large mini-batch sizes in order to attain good performance for these problems, due to the usage of the standard mini-batch technique in the empirical risk minimization (ERM) framework. Our library is for deep X-risk optimization (DXO) that has achieved great success in solving a variety of tasks for CID, LTR and CLR. The contributions of this paper include: (1) It introduces a new mini-batch based pipeline for implementing DXO algorithms, which differs from existing DL pipeline in the design of controlled data samplers and dynamic mini-batch losses; (2) It provides extensive benchmarking experiments for ablation studies and comparison with existing libraries. The LibAUC library features scalable performance for millions of items to be contrasted, faster and better convergence than existing libraries for optimizing X-risks, seamless PyTorch deployment and versatile APIs for various loss optimization. Our library is available to the open source community at https://github.com/Optimization-AI/LibAUC, to facilitate further academic research and industrial applications.

Key facts. Cited by 15 papers in the map (data through 7 Oct 2026). Builds on 39 of its 66 references that are in the map. First posted on arXiv 5 Jun 2023.

Builds on

39 of 66 references.

References · 39

  1. 2017Attention Is All You Needcited by 59,932
  2. 2015Deep Residual Learning for Image Recognitioncited by 51,809
  3. 2014Adam: A Method for Stochastic Optimizationcited by 36,960
  4. 2021Learning Transferable Visual Models From Natural Language Supervisioncited by 33,456
  5. 2019PyTorch: An Imperative Style, High-Performance Deep Learning Librarycited by 20,160
  6. 2020A Simple Framework for Contrastive Learning of Visual Representationscited by 11,979
  7. 2016Densely Connected Convolutional Networkscited by 6,691
  8. 2020Open Graph Benchmark: Datasets for Machine Learning on Graphscited by 2,148
  9. 2019CheXpert: A Large Chest Radiograph Dataset with Uncertainty Labels and Expert Comparisoncited by 1,410
  10. 2017Neural Collaborative Filteringcited by 1,108
  11. 2019On the Variance of the Adaptive Learning Rate and Beyondcited by 763
  12. 2016MS-Celeb-1M: A Dataset and Benchmark for Large-Scale Face Recognitioncited by 621
27 more
  1. 2020DeeperGCN: All You Need to Train Deeper GCNscited by 249
  2. 2022AUC Maximization in the Era of Big Data and AI: A Surveycited by 100
  3. 2020Smooth-AP: Smoothing the Path Towards Large-Scale Image Retrievalcited by 98
  4. 2014Stochastic Compositional Gradient Descent: Algorithms for Minimizing Compositions of Expected-Value Functionscited by 93
  5. 2020Large-scale Robust Deep AUC Maximization: A New Surrogate Loss and Empirical Studies on Medical Image Classificationcited by 84
  6. 2021DIG: A Turnkey Library for Diving into Graph Deep Learning Researchcited by 76
  7. 2019Stochastic AUC Maximization with Deep Neural Networkscited by 61
  8. 2019Optimizing Rank-based Metrics with Blackbox Differentiationcited by 58
  9. 2018Two-Player Games for Efficient Non-Convex Constrained Optimizationcited by 55
  10. 2018A Single Time-Scale Stochastic Approximation Method for Nested Stochastic Optimizationcited by 53
  11. 2021Recall@k Surrogate Loss with Large Batches and Similarity Mixupcited by 49
  12. 2016Accelerating Stochastic Composition Optimizationcited by 46
  13. 2020Advanced Graph and Sequence Neural Networks for Molecular Property Prediction and Drug Discoverycited by 46
  14. 2022Provable Stochastic Optimization for Global Contrastive Learning: Small Batch Does Not Harm Performancecited by 40
  15. 2021NeuralNDCG: Direct Optimisation of a Ranking Metric via Differentiable Relaxation of Sortingcited by 39
  16. 2021Pooling Architecture Search for Graph Classificationcited by 36
  17. 2021Stochastic Optimization of Areas Under Precision-Recall Curves with Provable Convergencecited by 34
  18. 2018TF-Ranking: Scalable TensorFlow Library for Learning-to-Rankcited by 32
  19. 2022When AUC meets DRO: Optimizing Partial AUC for Deep Learning with Non-Convex Convergence Guaranteecited by 29
  20. 2022Finite-Sum Coupled Compositional Stochastic Optimization: Theory and Applicationscited by 27
  21. 2023Not All Semantics are Created Equal: Contrastive Self-supervised Learning with Automatic Temperature Individualizationcited by 25
  22. 2022Large-scale Stochastic Optimization of NDCG Surrogates for Deep Learning with Provable Convergencecited by 21
  23. 2022Multi-block-Single-probe Variance Reduced Estimator for Coupled Compositional Optimizationcited by 16
  24. 2021Momentum Accelerates the Convergence of Stochastic AUPRC Maximizationcited by 14
  25. 2022Benchmarking Deep AUROC Optimization: Loss Functions and Algorithmic Choicescited by 10
  26. 2021Performance or Trust? Why Not Both. Deep AUC Maximization with Self-Supervised Learning for COVID-19 Chest X-ray Classificationscited by 4
  27. 2023Provable Multi-instance Deep AUC Maximization with Stochastic Poolingcited by 3

Built on by

Cited by year (2026 to 7 Oct)

Citing papers per year: 2023: 2; 2024: 6; 2025: 5; 2026: 2.

15 papers.

Sort:

By area:

  1. 2024AUCSeg: AUC-oriented Pixel-level Long-tail Semantic Segmentationcited by 18
  2. 2024AASIST3: KAN-Enhanced AASIST Speech Deepfake Detection using SSL Features and Additional Regularization for the ASVspoof 2024 Challengecited by 8
  3. 2025Improved Rates of Differentially Private Nonconvex-Strongly-Concave Minimax Optimizationcited by 5
  4. 2023DRAUC: An Instance-wise Distributionally Robust AUC Optimization Frameworkcited by 3
  5. 2025DACTYL: Diverse Adversarial Corpus of Texts Yielded from Large Language Modelscited by 3
  6. 2024On Discriminative Probabilistic Modeling for Self-Supervised Representation Learningcited by 2
  7. 2024Which LLMs are Difficult to Detect? A Detailed Analysis of Potential Factors Contributing to Difficulties in LLM Text Detectioncited by 2
  8. 2024Boosting Few-Shot Learning with Disentangled Self-Supervised Learning and Meta-Learning for Medical Image Classificationcited by 1
  9. 2025Discriminative Finetuning of Generative Large Language Models without Reward Models and Human Preference Datacited by 1
  10. 2023AUC-mixup: Deep AUC Maximization with Mixupcited by 0
  11. 2024Efficient line search for optimizing Area Under the ROC Curve in gradient descentcited by 0
  12. 2025FairPOT: Balancing AUC Performance and Fairness with Proportional Optimal Transportcited by 0
3 more
  1. 2025Early GVHD Prediction in Liver Transplantation via Multi-Modal Deep Learning on Imbalanced EHR Datacited by 0
  2. 2026Rethinking Benchmarks for Differentially Private Image Classificationcited by 0
  3. 2026Team DACTYL at PAN 2026: Bayesian Data Mixing and Empirical X-risk Minimization for AI-text Detectioncited by 0