# Interventional Multi-Instance Learning with Deconfounded Instance-Level Prediction

arXiv: https://arxiv.org/abs/2204.09204 · HTML: https://mlsanity.com/paper/2204.09204/

## Key facts

- Cited by 13 papers in the map (data through 14 Oct 2026).
- Builds on 32 of its 53 references that are in the map.
- First posted on arXiv 20 Apr 2022.

## Builds on (most cited first, 30 of 32)

- [Deep Residual Learning for Image Recognition](https://mlsanity.com/paper/1512.03385/) (2015)
- [Faster R-CNN: Towards Real-Time Object Detection with Region Proposal Networks](https://mlsanity.com/paper/1506.01497/) (2015)
- [SGDR: Stochastic Gradient Descent with Warm Restarts](https://mlsanity.com/paper/1608.03983/) (2016)
- [Improved Baselines with Momentum Contrastive Learning](https://mlsanity.com/paper/2003.04297/) (2020)
- [FixMatch: Simplifying Semi-Supervised Learning with Consistency and Confidence](https://mlsanity.com/paper/2001.07685/) (2020)
- [Attention-based Deep Multiple Instance Learning](https://mlsanity.com/paper/1802.04712/) (2018)
- [Temporal Ensembling for Semi-Supervised Learning](https://mlsanity.com/paper/1610.02242/) (2016)
- [Network Dissection: Quantifying Interpretability of Deep Visual Representations](https://mlsanity.com/paper/1704.05796/) (2017)
- [Dual-stream Multiple Instance Learning Network for Whole Slide Image Classification with Self-supervised Contrastive Learning](https://mlsanity.com/paper/2011.08939/) (2020)
- [Implicit Regularization in Deep Matrix Factorization](https://mlsanity.com/paper/1905.13655/) (2019)
- [Combating noisy labels by agreement: A joint training method with co-regularization](https://mlsanity.com/paper/2003.02752/) (2020)
- [Direct and Indirect Effects](https://mlsanity.com/paper/1301.2300/) (2013)
- [Counterfactual VQA: A Cause-Effect Look at Language Bias](https://mlsanity.com/paper/2006.04315/) (2020)
- [Long-Tailed Classification by Keeping the Good and Removing the Bad Momentum Causal Effect](https://mlsanity.com/paper/2009.12991/) (2020)
- [Causal Intervention for Weakly-Supervised Semantic Segmentation](https://mlsanity.com/paper/2009.12547/) (2020)
- [Representation Learning via Invariant Causal Mechanisms](https://mlsanity.com/paper/2010.07922/) (2020)
- [Whole Slide Images based Cancer Survival Prediction using Attention Guided Deep Multiple Instance Learning Networks](https://mlsanity.com/paper/2009.11169/) (2020)
- [Interpretable Convolutional Neural Networks](https://mlsanity.com/paper/1710.00935/) (2017)
- [Patch-based Convolutional Neural Network for Whole Slide Tissue Image Classification](https://mlsanity.com/paper/1504.07947/) (2015)
- [Revisiting Multiple Instance Neural Networks](https://mlsanity.com/paper/1610.02501/) (2016)
- [Distilling Causal Effect of Data in Class-Incremental Learning](https://mlsanity.com/paper/2103.01737/) (2021)
- [Interventional Few-Shot Learning](https://mlsanity.com/paper/2009.13000/) (2020)
- [Visual Commonsense R-CNN](https://mlsanity.com/paper/2002.12204/) (2020)
- [Counterfactual Zero-Shot and Open-Set Visual Recognition](https://mlsanity.com/paper/2103.00887/) (2021)
- [Two Causal Principles for Improving Visual Dialog](https://mlsanity.com/paper/1911.10496/) (2019)
- [CAMEL: A Weakly Supervised Learning Framework for Histopathology Image Segmentation](https://mlsanity.com/paper/1908.10555/) (2019)
- [C-MIL: Continuation Multiple Instance Learning for Weakly Supervised Object Detection](https://mlsanity.com/paper/1904.05647/) (2019)
- [Neural Image Compression for Gigapixel Histopathology Image Analysis](https://mlsanity.com/paper/1811.02840/) (2018)
- [3C-Net: Category Count and Center Loss for Weakly-Supervised Action Localization](https://mlsanity.com/paper/1908.08216/) (2019)
- [Signet Ring Cell Detection With a Semi-supervised Learning Framework](https://mlsanity.com/paper/1907.03954/) (2019)

## Built on by (most cited first, 13 of 13)

- [Interventional Bag Multi-Instance Learning On Whole-Slide Pathological Images](https://mlsanity.com/paper/2303.06873/) (2023)
- [Transcriptomics-guided Slide Representation Learning in Computational Pathology](https://mlsanity.com/paper/2405.11618/) (2024)
- [The Rise of AI Language Pathologists: Exploring Two-level Prompt Learning for Few-shot Weakly-supervised Whole Slide Image Classification](https://mlsanity.com/paper/2305.17891/) (2023)
- [Pathology-knowledge Enhanced Multi-instance Prompt Learning for Few-shot Whole Slide Image Classification](https://mlsanity.com/paper/2407.10814/) (2024)
- [Interpreting Vulnerabilities of Multi-Instance Learning to Adversarial Perturbations](https://mlsanity.com/paper/2211.17071/) (2022)
- [Data-driven Knowledge Fusion for Deep Multi-instance Learning](https://mlsanity.com/paper/2304.11905/) (2023)
- [Cracking Instance Jigsaw Puzzles: An Alternative to Multiple Instance Learning for Whole Slide Image Analysis](https://mlsanity.com/paper/2507.08178/) (2025)
- [Rethinking Attention-Based Multiple Instance Learning for Whole-Slide Pathological Image Classification: An Instance Attribute Viewpoint](https://mlsanity.com/paper/2404.00351/) (2024)
- [Compact and De-biased Negative Instance Embedding for Multi-Instance Learning on Whole-Slide Image Classification](https://mlsanity.com/paper/2402.10595/) (2024)
- [Weakly Semi-supervised Whole Slide Image Classification by Two-level Cross Consistency Supervision](https://mlsanity.com/paper/2504.12132/) (2025)
- [SimMIL: A Universal Weakly Supervised Pre-Training Framework for Multi-Instance Learning in Whole Slide Pathology Images](https://mlsanity.com/paper/2505.06710/) (2025)
- [DLiPath: A Benchmark for the Comprehensive Assessment of Donor Liver Based on Histopathological Image Dataset](https://mlsanity.com/paper/2506.03185/) (2025)
- [Diffusion Attention Expert Model for Predicting and Semi-automatic Localizing STAS in Lung Cancer Histopathological Images](https://mlsanity.com/paper/2605.16444/) (2026)

## Abstract (arXiv)

When applying multi-instance learning (MIL) to make predictions for bags of instances, the prediction accuracy of an instance often depends on not only the instance itself but also its context in the corresponding bag. From the viewpoint of causal inference, such bag contextual prior works as a confounder and may result in model robustness and interpretability issues. Focusing on this problem, we propose a novel interventional multi-instance learning (IMIL) framework to achieve deconfounded instance-level prediction. Unlike traditional likelihood-based strategies, we design an Expectation-Maximization (EM) algorithm based on causal intervention, providing a robust instance selection in the training phase and suppressing the bias caused by the bag contextual prior. Experiments on pathological image analysis demonstrate that our IMIL method substantially reduces false positives and outperforms state-of-the-art MIL methods.