Finding the Homology of Decision Boundaries with Active Learning

Topological Data Analysis of Decision Boundaries with Application to Model Selection

We propose the labeled Čech complex, the plain labeled Vietoris-Rips complex, and the locally scaled labeled Vietoris-Rips complex to perform persistent homology inference of decision boundaries in classification tasks. We provide theoretical conditions and analysis for recovering the homology of a decision boundary from samples. Our main objective is quantification of deep neural network complexity to enable matching of datasets to pre-trained models; we report results for experiments using MNIST, FashionMNIST, and CIFAR10.

主动粒子悬浮液中力预测的拓扑正则化：结合EGNN与持续同调

Topological Regularization for Force Prediction in Active Particle Suspension with EGNN and Persistent Homology

提出多尺度学习框架，结合格子玻尔兹曼、E(2)-等变图神经网络和物理信息神经网络，并用持续同调拓扑正则化，实现主动粒子悬浮液中高精度力网络预测。

SUPClust：边界处的主动学习

SUPClust: Active Learning at the Boundaries

针对标注数据获取成本高的问题，本研究提出新型主动学习方法SUPClust，通过识别类别决策边界处的高信息量样本进行标注，在类别不平衡场景下也能有效提升模型性能。

Adversarial Active Learning for Deep Networks: a Margin Based Approach

We propose a new active learning strategy designed for deep neural networks. The goal is to minimize the number of data annotation queried from an oracle during training. Previous active learning strategies scalable for deep networks were mostly based on uncertain sample selection. In this work, we focus on examples lying close to the decision boundary. Based on theoretical works on margin theory for active learning, we know that such examples may help to considerably decrease the number of annotations. While measuring the exact distance to the decision boundaries is intractable, we propose to…

ANALYTiC：理解机器学习中的决策边界与降维

ANALYTiC: Understanding Decision Boundaries and Dimensionality Reduction in Machine Learning

本文提出 ANALYTiC 方法，将降维与决策边界结合主动学习，在三个轨迹数据集上提升轨迹语义标注的效率和可解释性。

MaxiMin Active Learning in Overparameterized Model Classes}

Generating labeled training datasets has become a major bottleneck in Machine Learning (ML) pipelines. Active ML aims to address this issue by designing learning algorithms that automatically and adaptively select the most informative examples for labeling so that human time is not wasted labeling irrelevant, redundant, or trivial examples. This paper proposes a new approach to active ML with nonparametric or overparameterized models such as kernel methods and neural networks. In the context of binary classification, the new approach is shown to possess a variety of desirable properties that a…