activity
20182023
most citedRethinking Graph Transformers with Spectral Attention

70 citations · 83 across the 6 of their papers we have counts for

collaborators
Showing cs.LGShow all

7 papers · 1 filter

cs.LG2023

Generating QM1B with PySCF

Alexander Mathiasen, Hatem Helal, Kerstin Klaser +6

The emergence of foundation models in Computer Vision and Natural Language Processing have resulted in immense progress on downstream tasks. This progress was enabled by datasets w…

cs.LG2023

Towards Foundational Models for Molecular Learning on Large-Scale Multi-Task Datasets

Dominique Beaini, Shenyang Huang, Joao Alex Cunha +32

Recently, pre-trained foundation models have enabled significant advancements in multiple fields. In molecular machine learning, however, where datasets are often hand-curated, and…

cs.LG2023

Graph Positional and Structural Encoder

Semih Cantürk, Renming Liu, Olivier Lapointe-Gagné +4

Positional and structural encodings (PSE) enable better identifiability of nodes within a graph, rendering them essential tools for empowering modern GNNs, and in particular graph…

cs.LG202170 cited

Rethinking Graph Transformers with Spectral Attention

Devin Kreuzer, Dominique Beaini, William L. Hamilton +2

In recent years, the Transformer architecture has proven to be very successful in sequence processing, but its application to other data structures, such as graphs, has remained li…

cs.LG2020

Directional Graph Networks

Dominique Beaini, Saro Passaro, Vincent Létourneau +3

The lack of anisotropic kernels in graph neural networks (GNNs) strongly limits their expressiveness, contributing to well-known issues such as over-smoothing. To overcome this lim…

cs.LG2020

Principal Neighbourhood Aggregation for Graph Nets

Gabriele Corso, Luca Cavalleri, Dominique Beaini +2

Graph Neural Networks (GNNs) have been shown to be effective models for different predictive tasks on graph-structured data. Recent work on their expressive power has focused on is…