4.6k citations · 13.8k across the 80 of their papers we have counts for
86 papers
Graph Learning Should Move Beyond Restrictive Views of Spectral and Message-Passing GNNs
Antonis Vasileiou, Juan Cervino, Pascal Frossard +7
Graph neural networks (GNNs) are commonly divided into message-passing neural networks (MPNNs) and spectral GNNs, reflecting two largely separate research traditions in machine lea…
Implicit Gaussian process representation of vector fields over arbitrary latent manifolds
Robert L. Peach, Matteo Vinao-Carl, Nir Grossman +6
Gaussian processes (GPs) are popular nonparametric statistical models for learning unknown functions and quantifying the spatiotemporal uncertainty in data. Recent works have exten…
Interpretable statistical representations of neural population dynamics and geometry
Adam Gosztolai, Robert L. Peach, Alexis Arnaudon +2
The dynamics of neuron populations commonly evolve on low-dimensional manifolds. Thus, we need methods that learn the dynamical processes over neural manifolds to infer interpretab…
Generalised Implicit Neural Representations
Daniele Grattarola, Pierre Vandergheynst
We consider the problem of learning implicit neural representations (INRs) for signals on non-Euclidean domains. In the Euclidean case, INRs are trained on a discrete sampling of a…
What is Trending on Wikipedia? Capturing Trends and Language Biases Across Wikipedia Editions
Volodymyr Miz, Joëlle Hanna, Nicolas Aspert +2
In this work, we propose an automatic evaluation and comparison of the browsing behavior of Wikipedia readers that can be applied to any language editions of Wikipedia. As an examp…
Revisiting hard thresholding for DNN pruning
Konstantinos Pitas, Mike Davies, Pierre Vandergheynst
The most common method for DNN pruning is hard thresholding of network weights, followed by retraining to recover any lost accuracy. Recently developed smart pruning algorithms use…