Search Results for author:
Found 14 papers, 4 papers with code
Navigating the Design Space of Equivariant Diffusion-Based Generative Models for De Novo 3D Molecule Generation
To further strengthen the applicability of diffusion models to limited training data, we investigate the transferability of EQGAT-diff trained on the large PubChem3D dataset with implicit hydrogen atoms to target different data distributions.
From slides (through tiles) to pixels: an explainability framework for weakly supervised models in pre-clinical pathology
We validate quantitatively our methods by quantifying the agreements of our explanations' heatmaps with pathologists' annotations, as well as with predictions from a segmentation model trained on such annotations.
Explainable Artificial Intelligence (XAI)
whole slide images
Equivariant Graph Attention Networks for Molecular Property Prediction
Learning and reasoning about 3D molecular structures with varying size is an emerging and important challenge in machine learning and especially in drug discovery.
Explaining, Evaluating and Enhancing Neural Networks' Learned Representations
Finally, we show that adopting our proposed scores as constraints during the training of a representation learning task improves the downstream performance of the model.
Unsupervised Learning of Group Invariant and Equivariant Representations
In this work, we extend group invariant and equivariant representation learning to the field of unsupervised deep learning.
Improving Molecular Graph Neural Network Explainability with Orthonormalization and Induced Sparsity
Rationalizing which parts of a molecule drive the predictions of a molecular graph convolutional neural network (GCNN) can be difficult.
Permutation-Invariant Variational Autoencoder for Graph-Level Representation Learning
In this work we address this issue by proposing a permutation-invariant variational autoencoder for graph structured data.
Parameterized Hypercomplex Graph Neural Networks for Graph Classification
Despite recent advances in representation learning in hypercomplex (HC) space, this subject is still vastly unexplored in the context of graphs.
Ranked #15 on
Graph Property Prediction
on ogbg-molpcba
Auto-Encoding Molecular Conformations
In this work we introduce an Autoencoder for molecular conformations.
Gini in a Bottleneck: Sparse Molecular Representations for Graph Convolutional Neural Networks
Due to the nature of deep learning approaches, it is inherently difficult to understand which aspects of a molecular graph drive the predictions of the network.
DeepPCM: Predicting Protein-Ligand Binding using Unsupervised Learned Representations
We apply this reasoning to propose a novel proteochemometric modeling methodology which, for the first time, uses embeddings generated via unsupervised representation learning for both the protein and ligand descriptors.
IVE-GAN: Invariant Encoding Generative Adversarial Networks
Although GANs can learn a rich representation of the covered modes of the data in their latent space, the framework misses an inverse mapping from data to this latent space.
Fast and Accurate Deep Network Learning by Exponential Linear Units (ELUs)
In contrast to ReLUs, ELUs have negative values which allows them to push mean unit activations closer to zero like batch normalization but with lower computational complexity.
Ranked #144 on
Image Classification
on CIFAR-100
(using extra training data)
