We show that standard Transformers without graph-specific modifications can lead to
promising results in graph learning both in theory and practice. Given a graph, we simply …

Quantum neural network architectures that have little to no inductive biases are known to
face trainability and generalization issues. Inspired by a similar problem, recent …

This work studies the design of neural networks that can process the weights or gradients of
other neural networks, which we refer to as neural functional networks (NFNs). Despite a …

Despite the great promise of quantum machine learning models, there are several
challenges one must overcome before unlocking their full potential. For instance, models …

A bstract PELICAN is a novel permutation equivariant and Lorentz invariant or covariant
aggregator network designed to overcome common limitations found in architectures …

The ubiquity of top-rich final states in the context of beyond the Standard Model (BSM)
searches has led to their status as extensively studied signatures at the LHC. Over the past …

Many current approaches to machine learning in particle physics use generic architectures
that require large numbers of parameters and disregard underlying physics principles …

A challenging problem in many modern machine learning tasks is to process weight-space
features, ie, to transform or extract information from the weights and gradients of a neural …

We provide a full characterisation of all of the possible group equivariant neural networks
whose layers are some tensor power of $\mathbb {R}^{n} $ for three symmetry groups that …

As particle accelerators increase their collision rates, and deep learning solutions prove
their viability, there is a growing need for lightweight and fast neural network architectures …