paper-with-me

Papers

Equivariant Denoisers Cannot Copy Graphs: Align Your Graph Diffusion Models

2024-05-27 · Najwa Laabid, Severi Rissanen, Markus Heinonen, Arno Solin, Vikas Garg

Graph diffusion models, dominant in graph generative modeling, remain underexplored for graph-to-graph translation tasks like chemical reaction prediction. We demonstrate that standard permutation equivariant denoisers face fundamental limitations in these tasks due to their inability to break symmetries in noisy inputs. To address this, we propose aligning input and target graphs to break input symmetries while preserving permutation equivariance in non-matching graph portions. Using retrosynthesis (i.e., the task of predicting precursors for synthesis of a given target molecule) as our application domain, we show how alignment dramatically improves discrete diffusion model performance from 5% to a SOTA-matching 54.7% top-1 accuracy. Code is available at https://github.com/Aalto-QuML/DiffAlign.

📄 PDF Abstract BibTeX arXiv:2405.17656

Code (1)

aalto-quml/diffalign 공식 구현 pytorch

Tasks

Chemical Reaction PredictionGraph GenerationGraph-To-Graph TranslationRetrosynthesis

Methods 이 논문이 사용한 방법론

SPEED The monocular depth estimation (MDE) is the task of estimating depth from a single frame. This information is an essential knowledge in many computer vision tasks such as scene…
Diffusion Diffusion models generate samples by gradually removing noise from a signal, and their training objective can be expressed as a reweighted variational lower-bound…

Similar Papers 제목 키워드 기반

Equivariant Denoisers for Image Restoration

2024-12-06 · Marien Renaud, Arthur Leclaire, Nicolas Papadakis

One key ingredient of image restoration is to define a realistic prior on clean images to complete the missing information in the observation. State-of-the-art restoration methods rely on a neural network to encode this …

DenoisingImage RestorationStochastic Optimization

Isometric Transformation Invariant and Equivariant Graph Convolutional Networks

2020-05-13 · ICLR 2021 1 · Masanobu Horie, Naoki Morita, Toshiaki Hishinuma, Yu Ihara 외

Graphs are one of the most important data structures for representing pairwise relations between objects. Specifically, a graph embedded in a Euclidean space is essential to solving real problems, such as physical simula…

Object DetectionPhysical Simulations

RoTIR: Rotation-Equivariant Network and Transformers for Fish Scale Image Registration

2024-01-20 · Ruixiong Wang, Alin Achim, Renata Raele-Rolfe, Qiao Tong 외

Image registration is an essential process for aligning features of interest from multiple images. With the recent development of deep learning techniques, image registration approaches have advanced to a new level. In t…

Deep LearningImage Registration

It Has Potential: Gradient-Driven Denoisers for Convergent Solutions to Inverse Problems

2021-12-01 · NeurIPS 2021 12 · Regev Cohen, Yochai Blau, Daniel Freedman, Ehud Rivlin

In recent years there has been increasing interest in leveraging denoisers for solving general inverse problems. Two leading frameworks are regularization-by-denoising (RED) and plug-and-play priors (PnP) which incorpora…

Denoising

E(n) Equivariant Topological Neural Networks

2024-05-24 · Claudio Battiloro, Ege Karaismailoğlu, Mauricio Tec, George Dasoulas 외

Graph neural networks excel at modeling pairwise interactions, but they cannot flexibly accommodate higher-order interactions and features. Topological deep learning (TDL) has emerged recently as a promising tool for add…

Inductive BiasMolecular Property PredictionProperty Prediction