mlsanityData to 14 Oct 2026

Detecting Scarce and Sparse Anomalous: Solving Dual Imbalance in Multi-Instance Learning

arXiv 2503.13562 ↗First posted 17 Mar 2025stat.ML cs.AI cs.LGcited by 0

Not on the map. Why?

Abstract (arXiv)

In real-world applications, it is highly challenging to detect anomalous samples with extremely sparse anomalies, as they are highly similar to and thus easily confused with normal samples. Moreover, the number of anomalous samples is inherently scarce. This results in a dual imbalance Multi-Instance Learning (MIL) problem, manifesting at both the macro and micro levels. To address this "needle-in-a-haystack problem", we find that MIL problem can be reformulated as a fine-grained PU learning problem. This allows us to address the imbalance issue in an unbiased manner using micro-level balancing mechanisms. To this end, we propose a novel framework, Balanced Fine-Grained Positive-Unlabeled (BFGPU)-based on rigorous theoretical foundations. Extensive experiments on both synthetic and real-world datasets demonstrate the effectiveness of BFGPU.

Key facts. No citing papers in the map yet (data through 14 Oct 2026). Builds on 23 of its 46 references that are in the map. First posted on arXiv 17 Mar 2025.

Builds on

23 of 46 references.

References · 23

  1. 2019PyTorch: An Imperative Style, High-Performance Deep Learning Librarycited by 20,305
  2. 2023GPT-4 Technical Reportcited by 18,396
  3. 2019RoBERTa: A Robustly Optimized BERT Pretraining Approachcited by 13,372
  4. 2022Training a Helpful and Harmless Assistant with Reinforcement Learning from Human Feedbackcited by 3,720
  5. 2018Attention-based Deep Multiple Instance Learningcited by 1,095
  6. 2019Deep Semi-Supervised Anomaly Detectioncited by 291
  7. 2022DTFD-MIL: Double-Tier Feature Distillation Multiple Instance Learning for Histopathology Whole Slide Image Classificationcited by 256
  8. 2017Positive-Unlabeled Learning with Non-Negative Risk Estimatorcited by 219
  9. 2018Learning from positive and unlabeled data: a surveycited by 219
  10. 2024BABILong: Testing the Limits of LLMs with Long Context Reasoning-in-a-Haystackcited by 215
  11. 2016Multiple Instance Learning: A Survey of Problem Characteristics and Applicationscited by 164
  12. 2018Latent Space Autoregression for Novelty Detectioncited by 149
11 more
  1. 2014Toward Supervised Anomaly Detectioncited by 73
  2. 2019Deep Weakly-supervised Anomaly Detectioncited by 59
  3. 2024Needle In A Multimodal Haystackcited by 58
  4. 2020Self-PU: Self Boosted and Calibrated Positive-Unlabeled Trainingcited by 47
  5. 2016Theoretical Comparisons of Positive-Unlabeled Learning against Positive-Negative Learningcited by 41
  6. 2018Classification from Positive, Unlabeled and Biased Negative Datacited by 34
  7. 2014PU Learning for Matrix Completioncited by 30
  8. 2017Multiple Instance Learning Networks for Fine-Grained Sentiment Analysiscited by 23
  9. 2016Efficient Training for Positive Unlabeled Learningcited by 10
  10. 2023UADB: Unsupervised Anomaly Detection Boostercited by 8
  11. 2023Robust Positive-Unlabeled Learning via Noise Negative Sample Self-correctioncited by 5

Built on by

Not cited yet.