# Multi-Instance Causal Representation Learning for Instance Label Prediction and Out-of-Distribution Generalization

arXiv: https://arxiv.org/abs/2202.12570 · HTML: https://mlsanity.com/paper/2202.12570/

## Key facts

- Cited by 17 papers in the map (data through 14 Oct 2026).
- Builds on 16 of its 60 references that are in the map.
- First posted on arXiv 25 Feb 2022.

## Builds on (most cited first, 16 of 16)

- [Fashion-MNIST: a Novel Image Dataset for Benchmarking Machine Learning Algorithms](https://mlsanity.com/paper/1708.07747/) (2017)
- [Invariant Risk Minimization](https://mlsanity.com/paper/1907.02893/) (2019)
- [Deep Sets](https://mlsanity.com/paper/1703.06114/) (2017)
- [Attention-based Deep Multiple Instance Learning](https://mlsanity.com/paper/1802.04712/) (2018)
- [Challenging Common Assumptions in the Unsupervised Learning of Disentangled Representations](https://mlsanity.com/paper/1811.12359/) (2018)
- [Causal inference using invariant prediction: identification and confidence intervals](https://mlsanity.com/paper/1501.01332/) (2015)
- [Variational Autoencoders and Nonlinear ICA: A Unifying Framework](https://mlsanity.com/paper/1907.04809/) (2019)
- [Dual-stream Multiple Instance Learning Network for Whole Slide Image Classification with Self-supervised Contrastive Learning](https://mlsanity.com/paper/2011.08939/) (2020)
- [Deep Learning for Classical Japanese Literature](https://mlsanity.com/paper/1812.01718/) (2018)
- [Invariant Risk Minimization Games](https://mlsanity.com/paper/2002.04692/) (2020)
- [Revisiting Multiple Instance Neural Networks](https://mlsanity.com/paper/1610.02501/) (2016)
- [Multi-Level Variational Autoencoder: Learning Disentangled Representations from Grouped Observations](https://mlsanity.com/paper/1705.08841/) (2017)
- [Deep Learning-based Computational Pathology Predicts Origins for Cancers of Unknown Primary](https://mlsanity.com/paper/2006.13932/) (2020)
- [A Comparison of Five Multiple Instance Learning Pooling Functions for Sound Event Detection with Weak Labeling](https://mlsanity.com/paper/1810.09050/) (2018)
- [Multiple Instance Learning Networks for Fine-Grained Sentiment Analysis](https://mlsanity.com/paper/1711.09645/) (2017)
- [Non-I.I.D. Multi-Instance Learning for Predicting Instance and Bag Labels using Variational Auto-Encoder](https://mlsanity.com/paper/2105.01276/) (2021)

## Built on by (most cited first, 17 of 17)

- [Reproducibility in Multiple Instance Learning: A Case For Algorithmic Unit Tests](https://mlsanity.com/paper/2310.17867/) (2023)
- [Disambiguated Attention Embedding for Multi-Instance Partial-Label Learning](https://mlsanity.com/paper/2305.16912/) (2023)
- [Identifying Semantic Component for Robust Molecular Property Prediction](https://mlsanity.com/paper/2311.04837/) (2023)
- [Multi-Instance Partial-Label Learning: Towards Exploiting Dual Inexact Supervision](https://mlsanity.com/paper/2212.08997/) (2022)
- [From Correlation to Causation: Max-Pooling-Based Multi-Instance Learning Leads to More Robust Whole Slide Image Classification](https://mlsanity.com/paper/2408.09449/) (2024)
- [Multi-Instance Partial-Label Learning with Margin Adjustment](https://mlsanity.com/paper/2501.12597/) (2025)
- [Unifying Invariance and Spuriousity for Graph Out-of-Distribution via Probability of Necessity and Sufficiency](https://mlsanity.com/paper/2402.09165/) (2024)
- [Exploiting Conjugate Label Information for Multi-Instance Partial-Label Learning](https://mlsanity.com/paper/2408.14369/) (2024)
- [Unifying Invariant and Variant Features for Graph Out-of-Distribution via Probability of Necessity and Sufficiency](https://mlsanity.com/paper/2407.15273/) (2024)
- [Introducing Diminutive Causal Structure into Graph Representation Learning](https://mlsanity.com/paper/2406.08709/) (2024)
- [MExD: An Expert-Infused Diffusion Model for Whole-Slide Image Classification](https://mlsanity.com/paper/2503.12401/) (2025)
- [Calibratable Disambiguation Loss for Multi-Instance Partial-Label Learning](https://mlsanity.com/paper/2512.17788/) (2025)
- [Introducing Expertise Logic into Graph Representation Learning from A Causal Perspective](https://mlsanity.com/paper/2301.08496/) (2023)
- [Transformer-based Multi-Instance Learning for Weakly Supervised Object Detection](https://mlsanity.com/paper/2303.14999/) (2023)
- [Rethinking the Value of Labels for Instance-Dependent Label Noise Learning](https://mlsanity.com/paper/2305.06247/) (2023)
- [Guidance Not Obstruction: A Conjugate Consistent Enhanced Strategy for Domain Generalization](https://mlsanity.com/paper/2412.10089/) (2024)
- [Denoising Mutual Knowledge Distillation in Bi-Directional Multiple Instance Learning](https://mlsanity.com/paper/2505.12074/) (2025)

## Abstract (arXiv)

Multi-instance learning (MIL) deals with objects represented as bags of instances and can predict instance labels from bag-level supervision. However, significant performance gaps exist between instance-level MIL algorithms and supervised learners since the instance labels are unavailable in MIL. Most existing MIL algorithms tackle the problem by treating multi-instance bags as harmful ambiguities and predicting instance labels by reducing the supervision inexactness. This work studies MIL from a new perspective by considering bags as auxiliary information, and utilize it to identify instance-level causal representations from bag-level weak supervision. We propose the CausalMIL algorithm, which not only excels at instance label prediction but also provides robustness to distribution change by synergistically integrating MIL with identifiable variational autoencoder. Our approach is based on a practical and general assumption: the prior distribution over the instance latent representations belongs to the non-factorized exponential family conditioning on the multi-instance bags. Experiments on synthetic and real-world datasets demonstrate that our approach significantly outperforms various baselines on instance label prediction and out-of-distribution generalization tasks.