3 papers
cs.CL2026
Disentangling Curriculum Learning in NLP: Towards a Unifying Taxonomy
Vanessa Toborek, Florian Seiffarth, Sebastian Müller +3
Despite more than a decade of curriculum learning (CL) research in NLP, the field lacks a principled account of which difficulty function or scheduler to use for a given problem. T…
cs.LG2026
Invariant-Based Weight Sharing for Message Passing
Florian Seiffarth
Message-passing neural networks (MPNNs) are a powerful framework for learning representations of graph-structured domains. However, weights in MPNNs act on features only, limiting…
cs.LG2024
Rule Based Learning with Dynamic (Graph) Neural Networks
Florian Seiffarth
A common problem of classical neural network architectures is that additional information or expert knowledge cannot be naturally integrated into the learning process. To overcome…