270 citations · 805 across the 13 of their papers we have counts for
12 papers · 1 filter
On Classification Thresholds for Graph Attention with Edge Features
Kimon Fountoulakis, Dake He, Silvio Lattanzi +3
The recent years we have seen the rise of graph neural networks for prediction tasks on graphs. One of the dominant architectures is graph attention due to its ability to make pred…
Synthetic Graph Generation to Benchmark Graph Learning
Anton Tsitsulin, Benedek Rozemberczki, John Palowitch +1
Graph learning algorithms have attained state-of-the-art performance on many graph analysis tasks such as node classification, link prediction, and clustering. It has, however, bec…
Shift-Robust GNNs: Overcoming the Limitations of Localized Graph Training Data
Qi Zhu, Natalia Ponomareva, Jiawei Han +1
There has been a recent surge of interest in designing Graph Neural Networks (GNNs) for semi-supervised learning tasks. Unfortunately this work has assumed that the nodes labeled f…
Graph Traversal with Tensor Functionals: A Meta-Algorithm for Scalable Learning
Elan Markowitz, Keshav Balasubramanian, Mehrnoosh Mirtaheri +4
Graph Representation Learning (GRL) methods have impacted fields from chemistry to social science. However, their algorithmic implementations are specialized to specific use-cases…
InstantEmbedding: Efficient Local Node Representations
Ştefan Postăvaru, Anton Tsitsulin, Filipe Miguel Gonçalves de Almeida +3
In this paper, we introduce InstantEmbedding, an efficient method for generating single-node representations using local PageRank computations. We theoretically prove that our appr…
Pathfinder Discovery Networks for Neural Message Passing
Benedek Rozemberczki, Peter Englert, Amol Kapoor +2
In this work we propose Pathfinder Discovery Networks (PDNs), a method for jointly learning a message passing graph over a multiplex network with a downstream semi-supervised model…