# Provable Multi-instance Deep AUC Maximization with Stochastic Pooling

arXiv: https://arxiv.org/abs/2305.08040 · HTML: https://mlsanity.com/paper/2305.08040/

## Key facts

- Cited by 3 papers in the map (data through 14 Oct 2026).
- Builds on 22 of its 57 references that are in the map.
- First posted on arXiv 14 May 2023.

## Builds on (most cited first, 22 of 22)

- [PointNet: Deep Learning on Point Sets for 3D Classification and Segmentation](https://mlsanity.com/paper/1612.00593/) (2016)
- [CheXpert: A Large Chest Radiograph Dataset with Uncertainty Labels and Expert Comparison](https://mlsanity.com/paper/1901.07031/) (2019)
- [Deep Sets](https://mlsanity.com/paper/1703.06114/) (2017)
- [Attention-based Deep Multiple Instance Learning](https://mlsanity.com/paper/1802.04712/) (2018)
- [On Gradient Descent Ascent for Nonconvex-Concave Minimax Problems](https://mlsanity.com/paper/1906.00331/) (2019)
- [Multiple Instance Learning: A Survey of Problem Characteristics and Applications](https://mlsanity.com/paper/1612.03365/) (2016)
- [AUC Maximization in the Era of Big Data and AI: A Survey](https://mlsanity.com/paper/2203.15046/) (2022)
- [Lung and Colon Cancer Histopathological Image Dataset (LC25000)](https://mlsanity.com/paper/1912.12142/) (2019)
- [Large-scale Robust Deep AUC Maximization: A New Surrogate Loss and Empirical Studies on Medical Image Classification](https://mlsanity.com/paper/2012.03173/) (2020)
- [3D Deep Learning on Medical Images: A Review](https://mlsanity.com/paper/2004.00218/) (2020)
- [Stochastic AUC Maximization with Deep Neural Networks](https://mlsanity.com/paper/1908.10831/) (2019)
- [On Symmetric Losses for Learning from Corrupted Labels](https://mlsanity.com/paper/1901.09314/) (2019)
- [Biased Stochastic First-Order Methods for Conditional Stochastic Optimization and Applications in Meta Learning](https://mlsanity.com/paper/2002.10790/) (2020)
- [Advanced Graph and Sequence Neural Networks for Molecular Property Prediction and Drug Discovery](https://mlsanity.com/paper/2012.01981/) (2020)
- [The University of California San Francisco Preoperative Diffuse Glioma MRI (UCSF-PDGM) Dataset](https://mlsanity.com/paper/2109.00356/) (2021)
- [One-Pass AUC Optimization](https://mlsanity.com/paper/1305.1363/) (2013)
- [A Theoretical Study of Inductive Biases in Contrastive Learning](https://mlsanity.com/paper/2211.14699/) (2022)
- [Classifying and Segmenting Microscopy Images Using Convolutional Multiple Instance Learning](https://mlsanity.com/paper/1511.05286/) (2015)
- [Communication-Efficient Distributed Stochastic AUC Maximization with Deep Neural Networks](https://mlsanity.com/paper/2005.02426/) (2020)
- [Finite-Sum Coupled Compositional Stochastic Optimization: Theory and Applications](https://mlsanity.com/paper/2202.12396/) (2022)
- [On the Generalization Ability of Online Learning Algorithms for Pairwise Loss Functions](https://mlsanity.com/paper/1305.2505/) (2013)
- [Benchmarking Deep AUROC Optimization: Loss Functions and Algorithmic Choices](https://mlsanity.com/paper/2203.14177/) (2022)

## Built on by (most cited first, 3 of 3)

- [LibAUC: A Deep Learning Library for X-Risk Optimization](https://mlsanity.com/paper/2306.03065/) (2023)
- [Non-Smooth Weakly-Convex Finite-sum Coupled Compositional Optimization](https://mlsanity.com/paper/2310.03234/) (2023)
- [Closing the Approximation Gap of Partial AUC Optimization: A Tale of Two Formulations](https://mlsanity.com/paper/2512.01213/) (2025)

## Abstract (arXiv)

This paper considers a novel application of deep AUC maximization (DAM) for multi-instance learning (MIL), in which a single class label is assigned to a bag of instances (e.g., multiple 2D slices of a CT scan for a patient). We address a neglected yet non-negligible computational challenge of MIL in the context of DAM, i.e., bag size is too large to be loaded into {GPU} memory for backpropagation, which is required by the standard pooling methods of MIL. To tackle this challenge, we propose variance-reduced stochastic pooling methods in the spirit of stochastic optimization by formulating the loss function over the pooled prediction as a multi-level compositional function. By synthesizing techniques from stochastic compositional optimization and non-convex min-max optimization, we propose a unified and provable muli-instance DAM (MIDAM) algorithm with stochastic smoothed-max pooling or stochastic attention-based pooling, which only samples a few instances for each bag to compute a stochastic gradient estimator and to update the model parameter. We establish a similar convergence rate of the proposed MIDAM algorithm as the state-of-the-art DAM algorithms. Our extensive experiments on conventional MIL datasets and medical datasets demonstrate the superiority of our MIDAM algorithm.