Reading List

Conference ordering: AAAI (Feb), SDM (Apr) ICLR (May), CVPR (Jun), ICML (Jul), KDD (Aug), IJCAI (Aug), ICCV (Oct), ICDM (Nov), NeurIPS (Dec)

Imbalanced data

Representation learning

  1. Momentum Contrast for Unsupervised Visual Representation Learning, CVPR 2020 [MoCo]
  2. A Simple Framework for Contrastive Learning of Visual Representations, ICML 2020 [SimCLR]
  3. Bootstrap Your Own Latent A New Approach to Self-Supervised Learning, NeurIPS 2020 [BYOL]
  4. [Aug 7] Self-Supervised Relational Reasoning for Representation Learning, NeurIPS 2020
  5. Unsupervised Learning of Visual Features by Contrasting Cluster Assignments, NeurIPS, 2020. [SwAV]
  6. VIME: Extending the Success of Self- and Semi-supervised Learning to Tabular Domain. NeurIPS 2020
  7. Exploring Simple Siamese Representation Learning, CVPR 2021 [SimSiam]
  8. Barlow Twins: Self-Supervised Learning via Redundancy Reduction, ICML 2021 [BT]
  9. Whitening for Self-Supervised Representation Learning, ICML 2021 [W-MSE]
  10. [Aug 14] SubTab: Subsetting Features of Tabular Data for Self-Supervised Representation Learning. NeurIPS 2021
  11. SCARF: Self-supervised Contrastive Learning Using Random Feature Corruption, ICLR 2022
  12. Semantic-Aware Auto-Encoders for Self-supervised Representation Learning, CVPR 2022
  13. On Embeddings for Numerical Features in Tabular Deep Learning. NeurIPS 2022

Theses

Representation learning, continued

  1. [Aug 21, starting 2 per TR discussion at 3:30pm] VICReg: Variance-invariance-convariance regularization for self-supervised learning, ICLR 2022
  2. Masked autoencoders are scalable vision learners, CVPR 2022 [MAE]
  3. SimMIM: A simple framework for masked image modeling, CVPR 2022
  4. SAINT: Improved neural networks for tabular data via row attention and contrastive pre-training, NeurIPS Tabular Representation Workshop 2022

SEP forecasting

  1. [Aug 28] Richardson et al. (2018). Prediction of Solar Energetic Particle Event Peak Proton Intensity Using a Simple Algorithm Based on CME Speed and Direction and Observations of Associated Solar Phenomena, Space Weather.
  2. Boubrahimi, S. F., Aydin, B., Martens, P., & Angryk, R. (2017). On the prediction of >100 MeV solar energetic particle events using GOES satellite data In 2017 IEEE International Conference on Big Data (Big Data) (pp. 2533-2542). IEEE.
  3. Kahler, S. W., & Ling, A. G. (2018). Forecasting Solar Energetic Particle (SEP) events with Flare X-ray peak ratios. Journal of Space Weather and Space Climate, 8, A47.
  4. K.N. Kim, S.A. Sin, K.A. Song, J.H. Kong (2018). A technique for prediction of SPEs from solar radio flux by statistical analysis, ANN and GA Astro-phys. Space Sci., 363 (8) , p. 170
  5. [Sep 4] Inceoglu, F. et al. (2018). Using machine learning methods to forecast if solar flares will be associated with CMEs and SEPs. The Astrophysical Journal, 861(2), 128.
  6. Aminalragia-Giamini, S. et al. (2021). Solar energetic particle event occurrence prediction using solar flare soft X-ray measurements and machine learning. Journal of Space Weather and Space Climate, 11, 59.
  7. Lavasa, E. et al. (2021). Assessing the predictability of solar energetic particles with the use of machine learning techniques. Solar Physics, 296(7), 107.
  8. Kasapis, S., Zhao, L., Chen, Y., Wang, X., Bobra, M., & Gombosi, T. (2022). Interpretable machine learning to forecast SEP events for solar cycle 23. Space Weather, 20(2), e2021SW002842.

Imbalanced or representation learning, continued

  1. [Sep 11, starting 1 per TR discussion at 3:30pm] Self-supervised Learning is More Robust to Dataset Imbalance, ICLR 2022
  2. data2vec: A General Framework for Self-supervised Learning in Speech, Vision and Language, ICML 2022
  3. Masked Siamese Networks for Label-Efficient Learning, ECCV 2022 [MSN]
  4. The hidden uniform cluster prior in self-supervised learning, ICLR 2023 -- imbalanced
  5. Divide and contrast: Self-supervised learning from uncurated data, ICCV 2021 [DnC] -- imbalanced
  6. Improving contrastive learning on imbalanced data via open-world sampling, NeurIPS 2021
  8. Representation learning with contrastive predictive coding, arXiv 2018, 6k+ citations [CPC]
  9. Unsupervised scalable representation learning for multivariate time series, NeurIPS 2019 [T-Loss]
  10. Unsupervised Representation Learning for Time Series with Temporal Neighborhood Coding, ICLR 2021 [TNC]
  11. A Transformer-based Framework for Multivariate Time Series Representation Learning, KDD 2021
  12. Time-Series Representation Learning via Temporal and Contextual Contrasting, IJCAI 2021 [TS-TCC]
  13. TS2Vec: Towards Universal Representation of Time Series, AAAI 2022
  14. Dynamic Sparse Network for Time Series Classification: Learning What to "See" NeurIPS 2022
  15. Self-Supervised Contrastive Pre-Training For Time Series via Time-Frequency Consistency. NeurIPS 2022 [TF-C]
  16. --starting the week of 11/13, one paper discussion per week on Tue---
  17. CLOCS: Contrastive Learning of Cardiac Signals Across Space, Time, and Patients. ICML 2021
  18. --pausing on 11/18
  19. --restarting on 1/30/24, one paper discussion on Tue---
  20. CoST: Contrastive learning of disentangled seasonaltrend representations for time series forecasting, ICLR 2022
  22. Rank-N-Contrast: Learning Continuous Representations for Regression, NeurIPS 2023
  23. Improving Deep Regression with Ordinal Entropy, ICLR 2023
  25. Distilling Virtual Examples for Long-Tailed Recognition, ICCV 2021 [DiVE]
  26. CUDA: Curriculum of data augmentation for long-tailed recognition, ICLR 2023
  28. TabNet: Attentive Interpretable Tabular Learning, AAAI 2021
  29. ---restarting in April 2024
  30. Local Contrastive Feature Learning for Tabular Data, CIKM 2022
  31. Learning Enhanced Representation for Tabular Data via Neighborhood Propagation, NeurIPS 2022
  33. ConR: Contrastive Regularizer for Deep Imbalanced Regression, ICLR 2024 [ConR]
  34. Simplifying Neural Network Training Under Class Imbalance, NeurIPS 2023.
  35. How Re-sampling Helps for Long-Tail Learning? NeurIPS 2023. [CSA: Context-shift augmentation, use Grad-CAM to identifying context, which is used to augment minority samples]
  36. SimPer: Simple Self-Supervised Learning of Periodic Targets, ICLR 2023
  38. -- resuming in July 2024 --
  39. Sharpness-aware Minimization for Efficiently Improving Generalization, ICLR 2021 [SAM]
  40. Class-Conditional Sharpness-Aware Minimization for Deep Long-Tailed Recognition, CVPR 2023
  41. Deep Imbalanced Regression via Hierarchical Classification Adjustment, CVPR 2024 [HCA]
  42. Bag of Tricks for Long-Tailed Visual Recognition with Deep Convolutional Neural Networks, AAAI 2018
  43. Attend and Diagnose: Clinical Time Series Analysis Using Attention Models, AAAI 2021
  44. Attention-Based Autoregression for Accurate and Efficient Multivariate Time Series Forecasting, SDM 2021
  45. FCC: Feature Clusters Compression for Long-Tailed Visual Recognition, CVPR 2023
  46. Long-Tailed Recognition by Mutual Information Maximization between Latent Features and Ground-Truth Labels. ICML 2023
  47. Balanced Product of Calibrated Experts for Long-Tailed Recognition, CVPR 2023
  48. DeiT-LT: Distillation Strikes Back for Vision Transformer Training on Long-Tailed Datasets, CVPR 2024
  50. No One Left Behind: Improving the Worst Categories in Long-Tailed Learning, CVPR 2023
  51. Curvature-Balanced Feature Manifold Learning for Long-Tailed Classification, CVPR 2023
  52. SuperDisco: Super-Class Discovery Improves Visual Recognition for the Long-Tail, CVPR 2023
  53. Towards Realistic Long-Tailed Semi-Supervised Learning: Consistency is All You Need, CVPR 2023
  54. Transfer Knowledge from Head to Tail: Uncertainty Calibration under Long-tailed Distribution, CVPR 2023
  56. Enhancing Class-Imbalanced Learning with Pre-Trained Guidance through Class-Conditional Knowledge Distillation, ICML 2024
  57. Distribution Alignment Optimization through Neural Collapse for Long-tailed Classification, ICML 2024
  59. -- resuming in Mar 2025 --
  60. Two Fists, One Heart: Multi-Objective Optimization Based Strategy Fusion for Long-tailed Learning, ICML 2024
  61. Pareto Deep Long-Tailed Recognition: A Conflict-Averse Solution, ICLR 2024
  63. Gradient Surgery for Multi-Task Learning, NeurIPS 2020 [PCGrad]
  64. Conflict-Averse Gradient Descent for Multi-task Learning, NeurIPS 2021 [CAGrad]
  66. Escaping Saddle Points for Effective Generalization on Class-Imbalanced Data, NeurIPS 2022
  67. ImbSAM: A closer look at sharpness-aware minimization in class imbalanced recognition, ICCV 2023 [ImbSAM]
  68. Towards Efficient and Scalable Sharpness-Aware Minimization, CVPR 2022
  69. Sharpness-Aware Training for Free, NeurIPS 2022
  71. Gradnorm: Gradient normalization for adaptive loss balancing in deep multitask networks, ICML 2018 [GradNorm]
  72. Just pick a sign: Optimizing deep multitask models with sign dropout, NeurIPS 2020 [GradDrop]
  73. Gradient Vaccine: Investigating and Improving Multi-task Optimization in Massively Multilingual Models, ICLR 2021 [GradVac]
  74. RotoGrad: Gradient homogenization in multitask learning, ICLR 2022 [RotoGrad]
  75. Recon: Reducing Conflicting Gradients From the Root For Multi-Task Learning, ICLR 2023 [Recon]
  77. Exploring Weight Balancing on Long-Tailed Recognition Problem, ICLR 2024
  78. Kill Two Birds with One Stone: Rethinking Data Augmentation for Deep Long-tailed Learning, ICLR 2024
  80. Self-adaptive Extreme Penalized Loss for Imbalanced Time Series Prediction, IJCAI 2024
  82. Revive Re-weighting in Imbalanced Learning by Density Ratio Estimation, NeurIPS 2024
  83. Neural Collapse To Multiple Centers For Imbalanced Data, NeurIPS 2024
  85. Temperature Schedules for self-supervised contrastive methods on long-tail data, ICLR 2023
  87. Feature Directions Matter: Long-Tailed Learning via Rotated Balanced Representation. ICML 2023
  88. Neural Collapse in Deep Linear Networks: From Balanced to Imbalanced Data. ICML 2023
  89. Wrapped Cauchy Distributed Angular Softmax for Long-Tailed Visual Recognition. ICML 2023
  91. A Unified Generalization Analysis of Re-Weighting and Logit-Adjustment for Imbalanced Learning, NeurIPS 2023
  92. Enhancing Minority Classes by Mixing: An Adaptative Optimal Transport Approach for Long-tailed Classification. NeurIPS 2023.
  93. Generalized test utilities for long-tail performance in extreme multi-label classification. NeurIPS 2023.
  94. Leave No Stone Unturned: Mine Extra Knowledge for Imbalanced Facial Expression Recognition. NeurIPS 2023.
  96. DUEL: Duplicate Elimination on Active Memory for Self-Supervised Class-Imbalanced Learning, aaai 2024
  97. Robust Visual Recognition with Class-Imbalanced Open-World Noisy Data, aaai 2024
  98. Toward Robustness in Multi-Label Classification: A Data Augmentation Strategy against Imbalance and Noise, aaai 2024
  99. BaCon: Boosting Imbalanced Semi-supervised Learning via Balanced Feature-Level Contrastive Learning, aaai 2024
  103. "Why Should I Trust You?" Explaining the Predictions of Any Classifier, KDD 2016 [LIME]
  104. A Unified Approach to Interpreting Model Predictions NeurIPS 2017 [SHAP]
  105. Grad-CAM: Visual Explanations from Deep Networks via Gradient-Based Localization, ICCV 2017
  107. Imbalanced Mixed Linear Regression. NeurIPS 2023.
  108. Variational Imbalanced Regression: Fair Uncertainty Quantification via Probabilistic Smoothing, NeurIPS 2023.
  109. TimesURL: Self-Supervised Contrastive Learning for Universal Time Series Representation Learning, aaai 2024
  110. MSGNet: Learning Multi-Scale Inter-series Correlations for Multivariate Time Series Forecasting, aaai 2024
  111. Latent Diffusion Transformer for Probabilistic Time Series Forecasting. aaai 2024
  112. HDMixer: Hierarchical Dependency with Extendable Patch for Multivariate Time Series Forecasting. aaai 2024
  113. CGS-Mask: Making Time Series Predictions Intuitive for All, aaai 2024
  115. Self-Supervised Representation Learning with Meta Comprehensive Regularization. aaai 2024
  116. Measuring Self-Supervised Representation Quality for Downstream Classification Using Discriminative Features, aaai 2024
  118. Density-Based Prototypical Contrastive Learning on Visual Representations, big data 2023
  119. Autoencoders and Generative Adversarial Networks for Imbalanced Sequence Classification, big data 2023
  121. Contrastive Learning with Boosted Memorization, ICML 2022 -- imbalanced
  123. Self-Supervised Learning from Images with a Joint-Embedding Predictive Architecture, CVPR 2023 [I-JEPA]
  124. Prototypical Contrastive Learning of Unsupervised Representations, ICLR 2021 [PCL]
  125. With a little help from my friends: nearest-neighbor contrastive learning of visual representations, ICCV 2021 [NNCLR]
  126. ReSSL: Relational self-supervised learning with weak augmentation, NeurIPS, 2021
  127. BEiT: BERT pre-training of image transformers, ICLR 2022
  128. iBOT: Image BERT pre-training with online tokenizer, ICLR 2022
  129. Emerging properties in self-supervised vision transformers, ICCV 2021 [DINO]
  130. Decoupled Contrastive Learning, ECCV 2022 [DCL]
  131. Automatic Shortcut Removal for Self-Supervised Representation Learning, NeurIPS 2022
  132. Adversarial Masking for Self-Supervised Learning, NeurIPS 2022
  133. Improving Self-Supervised Learning by Characterizing Idealized Representations, NeurIPS 2022

Related ML papers