mlsanityData to 7 Oct 2026

Class-aware and Augmentation-free Contrastive Learning from Label Proportion

arXiv 2408.06743 ↗First posted 13 Aug 2024cs.LGcited by 0

Not on the map. Why?

Abstract (arXiv)

Learning from Label Proportion (LLP) is a weakly supervised learning scenario in which training data is organized into predefined bags of instances, disclosing only the class label proportions per bag. This paradigm is essential for user modeling and personalization, where user privacy is paramount, offering insights into user preferences without revealing individual data. LLP faces a unique difficulty: the misalignment between bag-level supervision and the objective of instance-level prediction, primarily due to the inherent ambiguity in label proportion matching. Previous studies have demonstrated deep representation learning can generate auxiliary signals to promote the supervision level in the image domain. However, applying these techniques to tabular data presents significant challenges: 1) they rely heavily on label-invariant augmentation to establish multi-view, which is not feasible with the heterogeneous nature of tabular datasets, and 2) tabular datasets often lack sufficient semantics for perfect class distinction, making them prone to suboptimality caused by the inherent ambiguity of label proportion matching. To address these challenges, we propose an augmentation-free contrastive framework TabLLP-BDC that introduces class-aware supervision (explicitly aware of class differences) at the instance level. Our solution features a two-stage Bag Difference Contrastive (BDC) learning mechanism that establishes robust class-aware instance-level supervision by disassembling the nuance between bag label proportions, without relying on augmentations. Concurrently, our model presents a pioneering multi-task pretraining pipeline tailored for tabular-based LLP, capturing intrinsic tabular feature correlations in alignment with label proportion distribution. Extensive experiments demonstrate that TabLLP-BDC achieves state-of-the-art performance for LLP in the tabular domain.

Key facts. No citing papers in the map yet (data through 7 Oct 2026). Builds on 34 of its 72 references that are in the map. First posted on arXiv 13 Aug 2024.

Builds on

34 of 72 references.

References · 34

  1. 2017Attention Is All You Needcited by 59,932
  2. 2020A Simple Framework for Contrastive Learning of Visual Representationscited by 11,979
  3. 2018Representation Learning with Contrastive Predictive Codingcited by 7,662
  4. 2017mixup: Beyond Empirical Risk Minimizationcited by 5,155
  5. 2018Unsupervised Representation Learning by Predicting Image Rotationscited by 1,586
  6. 2016Temporal Ensembling for Semi-Supervised Learningcited by 1,054
  7. 2018Deep Clustering for Unsupervised Learning of Visual Featurescited by 1,020
  8. 2017Virtual Adversarial Training: A Regularization Method for Supervised and Semi-Supervised Learningcited by 918
  9. 2021Revisiting Deep Learning Models for Tabular Datacited by 725
  10. 2019Self-supervised Visual Feature Learning with Deep Neural Networks: A Surveycited by 656
  11. 2018Real-world Anomaly Detection in Surveillance Videoscited by 570
  12. 2019S4L: Self-Supervised Semi-Supervised Learningcited by 335
22 more
  1. 2018AutoInt: Automatic Feature Interaction Learning via Self-Attentive Neural Networkscited by 319
  2. 2021SAINT: Improved Neural Networks for Tabular Data via Row Attention and Contrastive Pre-Trainingcited by 310
  3. 2019Deep Semi-Supervised Anomaly Detectioncited by 290
  4. 2019Graph Convolutional Label Noise Cleaner: Train a Plug-and-play Action Classifier for Anomaly Detectioncited by 171
  5. 2021SCARF: Self-Supervised Contrastive Learning using Random Feature Corruptioncited by 151
  6. 2016Semi-Supervised Learning with Generative Adversarial Networkscited by 103
  7. 2021SubTab: Subsetting Features of Tabular Data for Self-Supervised Representation Learningcited by 101
  8. 2017Self-supervised Learning of Motion Capturecited by 97
  9. 2018Learning Representations of Ultrahigh-dimensional Data for Random Distance-based Outlier Detectioncited by 79
  10. 2020Conditional Wasserstein GAN-based Oversampling of Tabular Data for Imbalanced Learningcited by 67
  11. 2021Weakly Supervised Video Anomaly Detection via Center-guided Discriminative Learningcited by 44
  12. 2014On Learning from Label Proportionscited by 38
  13. 2019Learning from Label Proportions with Consistency Regularizationcited by 34
  14. 2019Deep multi-class learning from label proportionscited by 33
  15. 2013Real-time Bidding for Online Advertising: Measurement and Analysiscited by 32
  16. 2022Learning from Label Proportions by Learning with Label Noisecited by 30
  17. 2017Co-training for Demographic Classification Using Deep Learning from Label Proportionscited by 28
  18. 2023Weakly Supervised Anomaly Detection: A Surveycited by 22
  19. 2021Two-stage Training for Learning from Label Proportionscited by 19
  20. 2022ADMoE: Anomaly Detection with Mixture-of-Experts from Noisy Labelscited by 15
  21. 2022Anomaly Detection by Leveraging Incomplete Anomalous Knowledge with Anomaly-Aware Bidirectional GANscited by 11
  22. 2022Challenges and approaches to privacy preserving post-click conversion predictioncited by 10

Built on by

Not cited yet.