paper-with-me

홈 › Papers

GeSS: Benchmarking Geometric Deep Learning under Scientific Applications with Distribution Shifts

2023-10-12 · Deyu Zou, Shikun Liu, Siqi Miao, Victor Fung, Shiyu Chang, Pan Li

Geometric deep learning (GDL) has gained significant attention in scientific fields, for its proficiency in modeling data with intricate geometric structures. However, very few works have delved into its capability of tackling the distribution shift problem, a prevalent challenge in many applications. To bridge this gap, we propose GeSS, a comprehensive benchmark designed for evaluating the performance of GDL models in scientific scenarios with distribution shifts. Our evaluation datasets cover diverse scientific domains from particle physics, materials science to biochemistry, and encapsulate a broad spectrum of distribution shifts including conditional, covariate, and concept shifts. Furthermore, we study three levels of information access from the out-of-distribution (OOD) test data, including no OOD information, only unlabeled OOD data, and OOD data with a few labels. Overall, our benchmark results in 30 different experiment settings, and evaluates 3 GDL backbones and 11 learning algorithms in each setting. A thorough analysis of the evaluation results is provided, poised to illuminate insights for GDL researchers and domain practitioners who are to use GDL in their applications.

📄 PDF Abstract BibTeX arXiv:2310.08677

Code (2)

graph-com/gdl_ds 공식 구현 pytorch
graph-com/gess 공식 구현 pytorch

Tasks

Benchmarking

Similar Papers 제목 키워드 기반

Symmetry-Informed Geometric Representation for Molecules, Proteins, and Crystalline Materials

2023-06-15 · NeurIPS 2023 11 · Shengchao Liu, Weitao Du, Yanjing Li, Zhuoxinran Li 외

Artificial intelligence for scientific discovery has recently generated significant interest within the machine learning and scientific communities, particularly in the domains of chemistry, biology, and material discove…

BenchmarkingComputational chemistryscientific discovery

Geometry Matters: Benchmarking Scientific ML Approaches for Flow Prediction around Complex Geometries

2024-12-31 · Ali Rabeh, Ethan Herron, Aditya Balu, Soumik Sarkar 외

Rapid and accurate simulations of fluid dynamics around complicated geometric bodies are critical in a variety of engineering and scientific applications, including aerodynamics and biomedical flows. However, while scien…

BenchmarkingOut-of-Distribution Generalization

Computer-Aided Diagnosis of Low Grade Endometrial Stromal Sarcoma (LGESS)

2021-07-09 · Xinxin Yang, Mark Stamp

Low grade endometrial stromal sarcoma (LGESS) is rare form of cancer, accounting for about 0.2% of all uterine cancer cases. Approximately 75% of LGESS patients are initially misdiagnosed with leiomyoma, which is a type …

Deep Learning

SaGess: Sampling Graph Denoising Diffusion Model for Scalable Graph Generation

2023-06-29 · Stratis Limnios, Praveen Selvaraj, Mihai Cucuringu, Carsten Maple 외

Over recent years, denoising diffusion generative models have come to be considered as state-of-the-art methods for synthetic data generation, especially in the case of generating images. These approaches have also prove…

DenoisingGraph GenerationLink PredictionSynthetic Data Generation

GESS: Multi-cue Guided Local Feature Learning via Geometric and Semantic Synergy

2026-04-07 · Yang Yi, Xieyuanli Chen, Jinpu Zhang, Hui Shen 외 arxiv

Robust local feature detection and description are foundational tasks in computer vision. Existing methods primarily rely on single appearance cues for modeling, leading to unstable keypoints and insufficient descriptor …