5 papers
Preserving Utility in Continual LLM Unlearning via Orthogonal Projections
Juan Belieni, Ana Carolina Erthal, Eliezer de Souza da Silva +1
Unlearning concerns the task of removing the influence of a sensitive portion of the training data, such as protected, copyrighted or private text, from a model without retraining…
Mitigating Over-squashing without Rewiring: A Sheaf Effective Resistance Perspective
André Ribeiro, Germano Barcelos, Amauri H. Souza +2
Graph Neural Networks (GNNs) often struggle to capture long-range dependencies due to over-squashing -- a phenomenon in which the repeated compression of node embeddings into finit…
Differentiable Lifting for Topological Neural Networks
Jorge Luiz Franco, Gabriel Duarte, Alexander Nikitin +3
Topological neural networks (TNNs) enable leveraging high-order structures on graphs (e.g., cycles and cliques) to boost the expressive power of message-passing neural networks. In…
MATH-PT: A Math Reasoning Benchmark for European and Brazilian Portuguese
Tiago Teixeira, Ana Carolina Erthal, Juan Belieni +5
The use of large language models (LLMs) for complex mathematical reasoning is an emergent area of research, with fast progress in methods, models, and benchmark datasets. However,…
Cooperative Sheaf Neural Networks
André Ribeiro, Ana Luiza Tenório, Juan Belieni +2
Sheaf diffusion has recently emerged as a promising design pattern for graph representation learning due to its inherent ability to handle heterophilic data and avoid oversmoothing…