Invariance-Aware Randomized Smoothing Certificates
원문 초록
Building models that comply with the invariances inherent to different domains, such as invariance under translation or rotation, is a key aspect of applying machine learning to real world problems like molecular property prediction, medical imaging, protein folding or LiDAR classification. For the first time, we study how the invariances of a model can be leveraged to provably guarantee the robustness of its predictions. We propose a gray-box approach, enhancing the powerful black-box randomized smoothing technique with white-box knowledge about invariances. First, we develop gray-box certificates based on group orbits, which can be applied to arbitrary models with invariance under permutation and Euclidean isometries. Then, we derive provably tight gray-box certificates. We experimentally demonstrate that the provably tight certificates can offer much stronger guarantees, but that in practical scenarios the orbit-based method is a good approximation.
함께 살펴볼 논문
공통 태그를 근거로 연결했습니다. 실제 인용 관계나 논문의 우수성을 뜻하지 않습니다.
Descriptor-based Foundation Models for Molecular Property Prediction
Robust Molecular Property Prediction via Densifying Scarce Labeled Data
The Catechol Benchmark: Time-series Solvent Selection Data for Few-shot Machine Learning
Impact of SMILES Notational Inconsistencies on Chemical Language Model Performance
Towards Faster and More Compact Foundation Models for Molecular Property Prediction
Learning Hierarchical Interaction for Accurate Molecular Property Prediction
토론
이 논문과 연결된 포럼 글이 아직 없습니다.