paper-with-me

Papers

Global graph features unveiled by unsupervised geometric deep learning

2025-03-07 · Mirja Granfors, Jesús Pineda, Blanca Zufiria Gerbolés, Joana B. Pereira, Carlo Manzo, Giovanni Volpe

Graphs provide a powerful framework for modeling complex systems, but their structural variability makes analysis and classification challenging. To address this, we introduce GAUDI (Graph Autoencoder Uncovering Descriptive Information), a novel unsupervised geometric deep learning framework that captures both local details and global structure. GAUDI employs an innovative hourglass architecture with hierarchical pooling and upsampling layers, linked through skip connections to preserve essential connectivity information throughout the encoding-decoding process. By mapping different realizations of a system - generated from the same underlying parameters - into a continuous, structured latent space, GAUDI disentangles invariant process-level features from stochastic noise. We demonstrate its power across multiple applications, including modeling small-world networks, characterizing protein assemblies from super-resolution microscopy, analyzing collective motion in the Vicsek model, and capturing age-related changes in brain connectivity. This approach not only improves the analysis of complex graphs but also provides new insights into emergent phenomena across diverse scientific domains.

📄 PDF Abstract BibTeX arXiv:2503.05560

Code (0)

등록된 구현이 없습니다.

Tasks

Deep LearningDescriptiveSuper-Resolution

Similar Papers 제목 키워드 기반

Unsupervised deep learning for grading of age-related macular degeneration using retinal fundus images

2020-10-22 · Baladitya Yellapragada, Sascha Hornhauer, Kiersten Snyder, Stella Yu 외

Many diseases are classified based on human-defined rubrics that are prone to bias. Supervised neural networks can automate the grading of retinal fundus images, but require labor-intensive annotations and are restricted…

Parallax-Tolerant Unsupervised Deep Image Stitching

2023-02-16 · ICCV 2023 1 · Lang Nie, Chunyu Lin, Kang Liao, Shuaicheng Liu 외

Traditional image stitching approaches tend to leverage increasingly complex geometric features (point, line, edge, etc.) for better performance. However, these hand-crafted features are only suitable for specific natura…

Image RegistrationImage Stitching

Unsupervised Dense Deformation Embedding Network for Template-Free Shape Correspondence

2021-08-26 · ICCV 2021 10 · Ronghan Chen, Yang Cong, Jiahua Dong

Shape correspondence from 3D deformation learning has attracted appealing academy interests recently. Nevertheless, current deep learning based methods require the supervision of dense annotations to learn per-point tran…

Decoder

DynaVol: Unsupervised Learning for Dynamic Scenes through Object-Centric Voxelization

2023-04-30 · Yanpeng Zhao, Siyu Gao, Yunbo Wang, Xiaokang Yang

Unsupervised learning of object-centric representations in dynamic visual scenes is challenging. Unlike most previous approaches that learn to decompose 2D images, we present DynaVol, a 3D scene generative model that uni…

DecoderNeRFNeural RenderingNovel View Synthesis+3

UnsMOT: Unified Framework for Unsupervised Multi-Object Tracking with Geometric Topology Guidance

2023-09-03 · Son Tran, Cong Tran, Anh Tran, Cuong Pham

Object detection has long been a topic of high interest in computer vision literature. Motivated by the fact that annotating data for the multi-object tracking (MOT) problem is immensely expensive, recent studies have tu…

Multi-Object Trackingobject-detectionObject DetectionObject Tracking