# Bag Graph: Multiple Instance Learning using Bayesian Graph Neural Networks

arXiv: https://arxiv.org/abs/2202.11132 · HTML: https://mlsanity.com/paper/2202.11132/

## Key facts

- Cited by 6 papers in the map (data through 14 Oct 2026).
- Builds on 17 of its 37 references that are in the map.
- First posted on arXiv 22 Feb 2022.

## Builds on (most cited first, 17 of 17)

- [Semi-Supervised Classification with Graph Convolutional Networks](https://mlsanity.com/paper/1609.02907/) (2016)
- [Inductive Representation Learning on Large Graphs](https://mlsanity.com/paper/1706.02216/) (2017)
- [Dropout as a Bayesian Approximation: Representing Model Uncertainty in Deep Learning](https://mlsanity.com/paper/1506.02142/) (2015)
- [Deep Sets](https://mlsanity.com/paper/1703.06114/) (2017)
- [Attention-based Deep Multiple Instance Learning](https://mlsanity.com/paper/1802.04712/) (2018)
- [GraphSAINT: Graph Sampling Based Inductive Learning Method](https://mlsanity.com/paper/1907.04931/) (2019)
- [Cluster-GCN: An Efficient Algorithm for Training Deep and Large Graph Convolutional Networks](https://mlsanity.com/paper/1905.07953/) (2019)
- [How to learn a graph from smooth signals](https://mlsanity.com/paper/1601.02513/) (2016)
- [Set Transformer: A Framework for Attention-based Permutation-Invariant Neural Networks](https://mlsanity.com/paper/1810.00825/) (2018)
- [Revisiting Multiple Instance Neural Networks](https://mlsanity.com/paper/1610.02501/) (2016)
- [Bayesian graph convolutional neural networks for semi-supervised classification](https://mlsanity.com/paper/1811.11103/) (2018)
- [Contrastive and Generative Graph Convolutional Networks for Graph-based Semi-Supervised Learning](https://mlsanity.com/paper/2009.07111/) (2020)
- [Fully Convolutional Multi-Class Multiple Instance Learning](https://mlsanity.com/paper/1412.7144/) (2014)
- [Large Scale Graph Learning from Smooth Signals](https://mlsanity.com/paper/1710.05654/) (2017)
- [Multiple instance learning with graph neural networks](https://mlsanity.com/paper/1906.04881/) (2019)
- [A Flexible Generative Framework for Graph-based Semi-supervised Learning](https://mlsanity.com/paper/1905.10769/) (2019)
- [Non-Parametric Graph Learning for Bayesian Graph Neural Networks](https://mlsanity.com/paper/2006.13335/) (2020)

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

- [Reproducibility in Multiple Instance Learning: A Case For Algorithmic Unit Tests](https://mlsanity.com/paper/2310.17867/) (2023)
- [PathoTune: Adapting Visual Foundation Model to Pathological Specialists](https://mlsanity.com/paper/2403.16497/) (2024)
- [C2MIL: Synchronizing Semantic and Topological Causalities in Multiple Instance Learning for Robust and Interpretable Survival Analysis](https://mlsanity.com/paper/2509.20152/) (2025)
- [Graph Neural Networks, Deep Reinforcement Learning and Probabilistic Topic Modeling for Strategic Multiagent Settings](https://mlsanity.com/paper/2511.10501/) (2025)
- [Spatial Blindness in Whole-Slide Multiple Instance Learning](https://mlsanity.com/paper/2605.17449/) (2026)
- [Multi-Label Proportion Learning for Sea-Ice Type Prediction](https://mlsanity.com/paper/2609.16347/) (2026)

## Abstract (arXiv)

Multiple Instance Learning (MIL) is a weakly supervised learning problem where the aim is to assign labels to sets or bags of instances, as opposed to traditional supervised learning where each instance is assumed to be independent and identically distributed (IID) and is to be labeled individually. Recent work has shown promising results for neural network models in the MIL setting. Instead of focusing on each instance, these models are trained in an end-to-end fashion to learn effective bag-level representations by suitably combining permutation invariant pooling techniques with neural architectures. In this paper, we consider modelling the interactions between bags using a graph and employ Graph Neural Networks (GNNs) to facilitate end-to-end learning. Since a meaningful graph representing dependencies between bags is rarely available, we propose to use a Bayesian GNN framework that can generate a likely graph structure for scenarios where there is uncertainty in the graph or when no graph is available. Empirical results demonstrate the efficacy of the proposed technique for several MIL benchmark tasks and a distribution regression task.