4 papers
Data-driven Machine Learning Cannot Reach Symbolic-level Logical Reasoning -- The Limit of the Scaling Law
Tiansi Dong, Mateja Jamnik, Pietro Liò
By promoting vectors to spheres and enabling explicit model construction, neural networks can perform symbolic-level syllogistic reasoning without training data. We identify two fu…
Communicability-Inspired Positional Encoding (CIPE)
Yipeng Zhang, Zhongtian Sun, Pietro Liò +1
Positional encodings (PEs) are essential for Transformers. Yet designing effective PEs for non-Euclidean graphs remains challenging. Such encodings should ideally induce an Attenti…
Hierarchical Pooling for Sheaf Neural Networks
Dionisia Naddeo, Carlo Abate, Pietro Liò +2
Sheaf Neural Networks (SNNs) generalize Graph Neural Networks (GNNs) by replacing scalar node signals with stalk-valued signals and by using restriction maps to measure compatibili…
Concept Graph Convolutions: Message Passing in the Concept Space
Lucie Charlotte Magister, Pietro Lio
The trust in the predictions of Graph Neural Networks is limited by their opaque reasoning process. Prior methods have tried to explain graph networks via concept-based explanation…