no code implementations • 9 Feb 2024 • Dobrik Georgiev, Pietro Liò, Davide Buffelli
Recent work on neural algorithmic reasoning has demonstrated that graph neural networks (GNNs) could learn to execute classical algorithms.
no code implementations • 16 Aug 2023 • Davide Buffelli, Ashish Gupta, Agnieszka Strzalka, Vassilis Plachouras
In the past few years, deep learning methods have attracted a lot of research, and are now heavily used in modern real-world recommender systems.
1 code implementation • 4 Nov 2022 • Rishabh Jain, Gabriele Ciravegna, Pietro Barbiero, Francesco Giannini, Davide Buffelli, Pietro Lio
Recently, Logic Explained Networks (LENs) have been proposed as explainable-by-design neural models providing logic explanations for their predictions.
no code implementations • 6 Sep 2022 • Davide Buffelli, Efthymia Tsamoura
Our work introduces a regularization technique for injecting symbolic background knowledge into neural SGG models that overcomes the limitations of prior art.
1 code implementation • 16 Jul 2022 • Davide Buffelli, Pietro Liò, Fabio Vandin
Previous works have tried to tackle this issue in graph classification by providing the model with inductive biases derived from assumptions on the generative process of the graphs, or by requiring access to graphs from the test domain.
1 code implementation • 10 Jan 2022 • Davide Buffelli, Fabio Vandin
While this approach achieves great results in the single-task setting, the generation of node embeddings that can be used to perform multiple tasks (with performance comparable to single-task models) is still an open problem.
no code implementations • 1 Jan 2021 • Davide Buffelli, Fabio Vandin
Graph Convolutional Networks (GCNs) represent the state-of-the-art for many graph related tasks.
1 code implementation • 12 Dec 2020 • Davide Buffelli, Fabio Vandin
We show that the embeddings produced by our method can be used to perform multiple tasks with comparable or higher performance than classically trained models.
1 code implementation • 6 Jun 2020 • Davide Buffelli, Fabio Vandin
Graph Neural Networks (GNNs) rely on the graph structure to define an aggregation strategy where each node updates its representation by combining information from its neighbours.
1 code implementation • 6 Jun 2020 • Davide Buffelli, Fabio Vandin
We propose a simple and effective transfer-learning based strategy to adapt a model to a specific user, providing an average increment of $6\%$ on the F1 score on the predictions for that user.