Related papers: 3D-GSRD: 3D Molecular Graph Auto-Encoder with Sele…

Unrolled neural networks have recently achieved state-of-the-art accelerated MRI reconstruction. These networks unroll iterative optimization algorithms by alternating between physics-based consistency and neural-network based…

Unsupervised domain adaptation (UDA) for semantic segmentation seeks to transfer models from a labeled source domain to an unlabeled target domain. While auxiliary self-supervised tasks such as contrastive learning have enhanced feature…

This work considers the task of representation learning on the attributed relational graph (ARG). Both the nodes and edges in an ARG are associated with attributes/features allowing ARGs to encode rich structural information widely observed…

Generative recommendation (GR) typically first quantizes continuous item embeddings into multi-level semantic IDs (SIDs), and then generates the next item via autoregressive decoding. Although existing methods are already competitive in…

Novel view synthesis (NVS) and surface reconstruction (SR) are essential tasks in 3D Gaussian Splatting (3D-GS). Despite recent progress, these tasks are often addressed independently, with GS-based rendering methods struggling under…

The last years have witnessed the emergence of a promising self-supervised learning strategy, referred to as masked autoencoding. However, there is a lack of theoretical understanding of how masking matters on graph autoencoders (GAEs). In…

The goal of this work is to address two limitations in autoencoder-based models: latent space interpretability and compatibility with unstructured meshes. This is accomplished here with the development of a novel graph neural network (GNN)…

Generating precise 3D molecular geometries is crucial for drug discovery and material science. While prior efforts leverage 1D representations like SELFIES to ensure molecular validity, they fail to fully exploit the rich chemical knowledge…

Self-supervised learning (SSL) plays a central role in molecular representation learning. Yet, many recent innovations in masking-based pretraining are introduced as heuristics and lack principled evaluation, obscuring which design choices…

In the real world, a molecule is a 3D geometric structure. Compared to 1D SMILES sequences and 2D molecular graphs, 3D molecules represent the most informative molecular modality. Despite the rapid progress of autoregressive-based language…

3D scene graphs provide a structured representation of object entities and their relationships, enabling high-level interpretation and reasoning for robots while remaining intuitively understandable to humans. Existing approaches for 3D…

Recently, generative graph models have shown promising results in learning graph representations through self-supervised methods. However, most existing generative graph representation learning (GRL) approaches rely on random masking across…

The quest for accurate prediction of drug molecule properties poses a fundamental challenge in the realm of Artificial Intelligence Drug Discovery (AIDD). An effective representation of drug molecules emerges as a pivotal component in this…

3D Geometric Graph Neural Networks (GNNs) have emerged as transformative tools for modeling molecular data. Despite their predictive power, these models often suffer from limited interpretability, raising concerns for scientific…

Graph Masked Autoencoders (GMAEs) have emerged as a notable self-supervised learning approach for graph-structured data. Existing GMAE models primarily focus on reconstructing node-level information, categorizing them as single-scale GMAEs.…

Deep learning for molecular science has so far mainly focused on 2D molecular graphs. Recently, however, there has been work to extend it to 3D molecular geometry, due to its scientific significance and critical importance in real-world…

Self-supervised learning (SSL) is a method that learns the data representation by utilizing supervision inherent in the data. This learning method is in the spotlight in the drug field, lacking annotated data due to time-consuming and…

While deep learning methods have achieved impressive success in many vision benchmarks, it remains difficult to understand and explain the representations and decisions of these models. Though vision models are typically trained on 2D…

There are many ways to represent a molecule as input to a machine learning model and each is associated with loss and retention of certain kinds of information. In the interest of preserving three-dimensional spatial information, including…

Masked Graph Auto-Encoder, a powerful graph self-supervised training paradigm, has recently shown superior performance in graph representation learning. Existing works typically rely on node contextual information to recover the masked…