# Non-I.I.D. Multi-Instance Learning for Predicting Instance and Bag Labels using Variational Auto-Encoder

arXiv: https://arxiv.org/abs/2105.01276 · HTML: https://mlsanity.com/paper/2105.01276/

## Key facts

- Cited by 6 papers in the map (data through 14 Oct 2026).
- Builds on 4 of its 21 references that are in the map.
- First posted on arXiv 4 May 2021.

## Builds on (most cited first, 4 of 4)

- [Auto-Encoding Variational Bayes](https://mlsanity.com/paper/1312.6114/) (2013)
- [Attention-based Deep Multiple Instance Learning](https://mlsanity.com/paper/1802.04712/) (2018)
- [Whole Slide Images based Cancer Survival Prediction using Attention Guided Deep Multiple Instance Learning Networks](https://mlsanity.com/paper/2009.11169/) (2020)
- [Revisiting Multiple Instance Neural Networks](https://mlsanity.com/paper/1610.02501/) (2016)

## Built on by (most cited first, 6 of 6)

- [Multi-Instance Causal Representation Learning for Instance Label Prediction and Out-of-Distribution Generalization](https://mlsanity.com/paper/2202.12570/) (2022)
- [Disambiguated Attention Embedding for Multi-Instance Partial-Label Learning](https://mlsanity.com/paper/2305.16912/) (2023)
- [Multi-Instance Partial-Label Learning: Towards Exploiting Dual Inexact Supervision](https://mlsanity.com/paper/2212.08997/) (2022)
- [Breast Cancer Molecular Subtypes Prediction on Pathological Images with Discriminative Patch Selecting and Multi-Instance Learning](https://mlsanity.com/paper/2203.07659/) (2022)
- [Rethinking Multiple Instance Learning: Developing an Instance-Level Classifier via Weakly-Supervised Self-Training](https://mlsanity.com/paper/2408.04813/) (2024)
- [Transformer-based Multi-Instance Learning for Weakly Supervised Object Detection](https://mlsanity.com/paper/2303.14999/) (2023)

## Abstract (arXiv)

Multi-instance learning is a type of weakly supervised learning. It deals with tasks where the data is a set of bags and each bag is a set of instances. Only the bag labels are observed whereas the labels for the instances are unknown. An important advantage of multi-instance learning is that by representing objects as a bag of instances, it is able to preserve the inherent dependencies among parts of the objects. Unfortunately, most existing algorithms assume all instances to be textitidentically and independently distributed, which violates real-world scenarios since the instances within a bag are rarely independent. In this work, we propose the Multi-Instance Variational Auto-Encoder (MIVAE) algorithm which explicitly models the dependencies among the instances for predicting both bag labels and instance labels. Experimental results on several multi-instance benchmarks and end-to-end medical imaging datasets demonstrate that MIVAE performs better than state-of-the-art algorithms for both instance label and bag label prediction tasks.