具有随机池化的可证多示例深度 AUC 最大化
Provable Multi-instance Deep AUC Maximization with Stochastic Pooling
AI总结：
针对多示例学习中包过大导致标准池化难以进行 GPU 反向传播的问题，本文提出带随机平滑最大或注意力池化的可证 MIDAM 算法，并验证其收敛性与性能优势。
摘要：
本文考虑了深度 AUC 最大化（DAM）在多示例学习（MIL）中的一种新颖应用，其中单个类别标签被分配给一个由多个示例组成的包（例如，一名患者 CT 扫描的多个二维切片）。我们解决了 DAM 背景下 MIL 中一个被忽视但不可忽略的计算挑战，即包过大，无法加载到 GPU 内存中进行反向传播，而 MIL 的标准池化方法需要这一过程。为应对该挑战，我们本着随机优化的思想，通过将池化预测上的损失函数表述为一个多层复合函数，提出了方差缩减的随机池化方法。通过综合随机复合优化和非凸极小极大优化中的技术，我们提出了一种统一且可证的多示例 DAM（MIDAM）算法，该算法采用随机平滑最大池化或随机基于注意力的池化，只需为每个包采样少量示例来计算随机梯度估计量并更新模型参数。我们证明所提出的 MIDAM 算法具有与最先进 DAM 算法相似的收敛速率。我们在常规 MIL 数据集和医学数据集上的大量实验证明了 MIDAM 算法的优越性。
英文摘要：
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.
机构、总结、中文摘要均由AI分析而来，可能存在错误，请以论文正文为准。
