paper-with-me

홈 › Papers

Towards Scalable Topological Regularizers

2025-01-24 · Hiu-Tung Wong, Darrick Lee, Hong Yan

Latent space matching, which consists of matching distributions of features in latent space, is a crucial component for tasks such as adversarial attacks and defenses, domain adaptation, and generative modelling. Metrics for probability measures, such as Wasserstein and maximum mean discrepancy, are commonly used to quantify the differences between such distributions. However, these are often costly to compute, or do not appropriately take the geometric and topological features of the distributions into consideration. Persistent homology is a tool from topological data analysis which quantifies the multi-scale topological structure of point clouds, and has recently been used as a topological regularizer in learning tasks. However, computation costs preclude larger scale computations, and discontinuities in the gradient lead to unstable training behavior such as in adversarial tasks. We propose the use of principal persistence measures, based on computing the persistent homology of a large number of small subsamples, as a topological regularizer. We provide a parallelized GPU implementation of this regularizer, and prove that gradients are continuous for smooth densities. Furthermore, we demonstrate the efficacy of this regularizer on shape matching, image generation, and semi-supervised learning tasks, opening the door towards a scalable regularizer for topological features.

📄 PDF Abstract BibTeX arXiv:2501.14641

Code (0)

등록된 구현이 없습니다.

Tasks

Domain AdaptationGPUImage GenerationTopological Data Analysis

Similar Papers 제목 키워드 기반

Robust Optimization as Data Augmentation for Large-scale Graphs

2020-10-19 · CVPR 2022 1 · Kezhi Kong, Guohao Li, Mucong Ding, Zuxuan Wu 외

Data augmentation helps neural networks generalize better by enlarging the training set, but it remains an open question how to effectively augment graph data to enhance the performance of GNNs (Graph Neural Networks). W…

Data AugmentationGraph ClassificationLink PredictionNode Classification+2

SOLAR: Scalable Optimization of Large-scale Architecture for Reasoning

2025-03-06 · Chen Li, Yinyi Luo, Anudeep Bolimera, Uzair Ahmed 외

Large Language Models excel in reasoning yet often rely on Chain-of-Thought prompts, limiting performance on tasks demanding more nuanced topological structures. We present SOLAR (Scalable Optimization of Large-scale Arc…

GSM8KMathTAG

Topology-Enhanced Alignment for Large Language Models: Trajectory Topology Loss and Topological Preference Optimization

2026-05-08 · Yurui Pan, Ke Xu, Bo Peng arxiv

Alignment of large language models (LLMs) via SFT and RLHF/DPO typically ignores the global geometry of the representation space, relying instead on local token likelihoods or scalar scores. We view generation as tracing…

RTD-Lite: Scalable Topological Analysis for Comparing Weighted Graphs in Learning Tasks

2025-03-14 · Eduard Tulchinskii, Daria Voronkova, Ilya Trofimov, Evgeny Burnaev 외

Topological methods for comparing weighted graphs are valuable in various learning tasks but often suffer from computational inefficiency on large datasets. We introduce RTD-Lite, a scalable algorithm that efficiently co…

Dimensionality Reduction

A total variation based regularizer promoting piecewise-Lipschitz reconstructions

2019-03-12 · Martin Burger, Yury Korolev, Carola-Bibiane Schönlieb, Christiane Stollenwerk

We introduce a new regularizer in the total variation family that promotes reconstructions with a given Lipschitz constant (which can also vary spatially). We prove regularizing properties of this functional and investig…