Luca Pasa
Current Organizations / Institutes
The organizations/institutes from the scholar's latest article
Luca Pasa has a total of 34 co-authors. Here are the top co-authors by number of shared publications:
- Alessandro Sperduti
University of Padua
11 shared publications - Nicolò Navarin
University of Padova, Padua, Italy
11 shared publications - Claudio Gallicchio
University of Pisa
3 shared publications - Paolo Frazzetto
University of Padua
3 shared publications - Alessio Micheli
University of Pisa
2 shared publications Davide Anguita
2 shared publications
Latest Publications
- 22 September 2026
- Published by Springer Nature
- p. 396-408
SeeAct-VC: Improving Browser Automation Through Complementary Visual Clues
- 22 September 2026
- Published by Springer Nature
- p. 396-408
SeeAct-VC: Improving Browser Automation Through Complementary Visual Clues
- Open Access
- 15 September 2026
- Published by Springer Nature in Machine Learning
- Vol. 115 (9) , 220
The Unreasonable Effectiveness of Randomized Representations in Online Continual Graph Learning
Catastrophic forgetting is one of the main obstacles for Online Continual Graph Learning (OCGL), where nodes arrive one by one, distribution drifts may occur at any time and offline training on task-specific subgraphs is not feasible. In this work, we explore a surprisingly simple yet highly effective approach for OCGL: we use a fixed, randomly initialized encoder to generate robust and expressive node embeddings by aggregating neighborhood information, training online only a lightweight classifier. By freezing the encoder, we eliminate drifts of the representation parameters, a key source of forgetting, obtaining embeddings that are both expressive and stable. When evaluated across several OCGL benchmarks, despite its simplicity and lack of memory buffer, this approach yields consistent gains over state-of-the-art methods, with surprising improvements of up to 30% and performance often approaching that of the joint offline-training upper bound. These results suggest that in OCGL, catastrophic forgetting can be minimized without complex replay or regularization by embracing architectural simplicity and stability.
- 15 September 2026
- Published by Springer Nature in Machine Learning
- Vol. 115 (9) , 220
Open AccessThe Unreasonable Effectiveness of Randomized Representations in Online Continual Graph Learning
Catastrophic forgetting is one of the main obstacles for Online Continual Graph Learning (OCGL), where nodes arrive one by one, distribution drifts may occur at any time and offline training on task-specific subgraphs is not feasible. In this work, we explore a surprisingly simple yet highly effective approach for OCGL: we use a fixed, randomly initialized encoder to generate robust and expressive node embeddings by aggregating neighborhood information, training online only a lightweight classifier. By freezing the encoder, we eliminate drifts of the representation parameters, a key source of forgetting, obtaining embeddings that are both expressive and stable. When evaluated across several OCGL benchmarks, despite its simplicity and lack of memory buffer, this approach yields consistent gains over state-of-the-art methods, with surprising improvements of up to 30% and performance often approaching that of the joint offline-training upper bound. These results suggest that in OCGL, catastrophic forgetting can be minimized without complex replay or regularization by embracing architectural simplicity and stability.
- 14 September 2026
- Published by Springer Nature
- p. 130-142
Guiding Diffusion with Logical Constraints: Molecular Graph Generation Under Lipinski’s Rules
- 14 September 2026
- Published by Springer Nature
- p. 130-142
Guiding Diffusion with Logical Constraints: Molecular Graph Generation Under Lipinski’s Rules
- Open Access
- 22 December 2025
- Published by Elsevier in Neurocomputing
- Vol. 669
Informed machine learning for complex data
- 22 December 2025
- Published by Elsevier in Neurocomputing
- Vol. 669
Open AccessInformed machine learning for complex data
- 6 August 2025
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Transactions on Dependable and Secure Computing
- Vol. 22 (6) , 7302-7318
Your PIN is Mine: Uncovering Users’ PINs at Point of Sale Machines
Point of Sale (PoS) machines have become extremely popular recently. In many economies, most transactions occur using them. Although PoS technology is evolving, PINs are still heavily used. In this paper, we perform a large-scale study to understand how difficult it is to uncover user PINs at PoS, even when the users cover the pad with their hands. Our study involves 142 participants, two types of PoS, and around 13,800 PINs. We develop machine learning techniques to infer PoS PINs by using hidden cameras. Our results show that uncovering PINs in PoS is more complex than in other cases where a user PIN is used, e.g., ATMs, because of the small pad area of PoS. Nevertheless, we could achieve more than 50% Top-3 accuracy for 4-digit PINs and 45% Top-3 accuracy for 5-digit PINs, even when the PIN is covered by the user's hand. We comment on the impact of the camera's position and PoS on the successful inference of the user's PINs. We also comment on the hardness of inferring PINs depending on the physical distance of digits and recommend what are good practices to generate PINs and cover PoS to make PIN inference difficult.
- 6 August 2025
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Transactions on Dependable and Secure Computing
- Vol. 22 (6) , 7302-7318
Your PIN is Mine: Uncovering Users’ PINs at Point of Sale Machines
Point of Sale (PoS) machines have become extremely popular recently. In many economies, most transactions occur using them. Although PoS technology is evolving, PINs are still heavily used. In this paper, we perform a large-scale study to understand how difficult it is to uncover user PINs at PoS, even when the users cover the pad with their hands. Our study involves 142 participants, two types of PoS, and around 13,800 PINs. We develop machine learning techniques to infer PoS PINs by using hidden cameras. Our results show that uncovering PINs in PoS is more complex than in other cases where a user PIN is used, e.g., ATMs, because of the small pad area of PoS. Nevertheless, we could achieve more than 50% Top-3 accuracy for 4-digit PINs and 45% Top-3 accuracy for 5-digit PINs, even when the PIN is covered by the user's hand. We comment on the impact of the camera's position and PoS on the successful inference of the user's PINs. We also comment on the hardness of inferring PINs depending on the physical distance of digits and recommend what are good practices to generate PINs and cover PoS to make PIN inference difficult.
- Open Access
- 7 January 2025
- Published by Elsevier in Waste Management
- Vol. 194, 36-44
Enhancing door-to-door waste collection forecasting through ML
- 7 January 2025
- Published by Elsevier in Waste Management
- Vol. 194, 36-44
Open AccessEnhancing door-to-door waste collection forecasting through ML
- Open Access
- 7 August 2024
- Published by Elsevier in Neurocomputing
- Vol. 606
Investigating over-parameterized randomized graph networks
- 7 August 2024
- Published by Elsevier in Neurocomputing
- Vol. 606
Open AccessInvestigating over-parameterized randomized graph networks
- Open Access
- 13 May 2024
- Published by Association for Computing Machinery (ACM)
- p. 963-966
"All of Me": Mining Users' Attributes from their Public Spotify Playlists
In the age of digital music streaming, playlists on platforms like Spotify have become an integral part of individuals' musical experiences. People create and publicly share their own playlists to express their musical tastes, promote the discovery of their favorite artists, and foster social connections. In this work, we aim to address the question: can we infer users' private attributes from their public Spotify playlists? To this end, we conducted an online survey involving 739 Spotify users, resulting in a dataset of 10,286 publicly shared playlists comprising over 200,000 unique songs and 55,000 artists. Then, we utilize statistical analyses and machine learning algorithms to build accurate predictive models for users' attributes.
- 13 May 2024
- Published by Association for Computing Machinery (ACM)
- p. 963-966
Open Access"All of Me": Mining Users' Attributes from their Public Spotify Playlists
In the age of digital music streaming, playlists on platforms like Spotify have become an integral part of individuals' musical experiences. People create and publicly share their own playlists to express their musical tastes, promote the discovery of their favorite artists, and foster social connections. In this work, we aim to address the question: can we infer users' private attributes from their public Spotify playlists? To this end, we conducted an online survey involving 739 Spotify users, resulting in a dataset of 10,286 publicly shared playlists comprising over 200,000 unique songs and 55,000 artists. Then, we utilize statistical analyses and machine learning algorithms to build accurate predictive models for users' attributes.
- Open Access
- 8 April 2024
- Published by Association for Computing Machinery (ACM)
- p. 474-481
Beyond the Additive Nodes' Convolutions: a Study on High-Order Multiplicative Integration
- 8 April 2024
- Published by Association for Computing Machinery (ACM)
- p. 474-481
Open AccessBeyond the Additive Nodes' Convolutions: a Study on High-Order Multiplicative Integration
- Open Access
- 26 December 2023
- Published by Springer Nature in Knowledge and Information Systems
- Vol. 66 (4) , 2393-2416
A unified framework for backpropagation-free soft and hard gated graph neural networks
We propose a framework for the definition of neural models for graphs that do not rely on backpropagation for training, thus making learning more biologically plausible and amenable to parallel implementation. Our proposed framework is inspired by Gated Linear Networks and allows the adoption of multiple graph convolutions. Specifically, each neuron is defined as a set of graph convolution filters (weight vectors) and a gating mechanism that, given a node and its topological context, generates the weight vector to use for processing the node’s attributes. Two different graph processing schemes are studied, i.e., a message-passing aggregation scheme where the gating mechanism is embedded directly into the graph convolution, and a multi-resolution one where neighboring nodes at different topological distances are jointly processed by a single graph convolution layer. We also compare the effectiveness of different alternatives for defining the context function of a node, i.e., based on hyperplanes or on prototypes, and using a soft or hard-gating mechanism. We propose a unified theoretical framework allowing us to theoretically characterize the proposed models’ expressiveness. We experimentally evaluate our backpropagation-free graph convolutional neural models on commonly adopted node classification datasets and show competitive performances compared to the backpropagation-based counterparts.
- 26 December 2023
- Published by Springer Nature in Knowledge and Information Systems
- Vol. 66 (4) , 2393-2416
Open AccessA unified framework for backpropagation-free soft and hard gated graph neural networks
We propose a framework for the definition of neural models for graphs that do not rely on backpropagation for training, thus making learning more biologically plausible and amenable to parallel implementation. Our proposed framework is inspired by Gated Linear Networks and allows the adoption of multiple graph convolutions. Specifically, each neuron is defined as a set of graph convolution filters (weight vectors) and a gating mechanism that, given a node and its topological context, generates the weight vector to use for processing the node’s attributes. Two different graph processing schemes are studied, i.e., a message-passing aggregation scheme where the gating mechanism is embedded directly into the graph convolution, and a multi-resolution one where neighboring nodes at different topological distances are jointly processed by a single graph convolution layer. We also compare the effectiveness of different alternatives for defining the context function of a node, i.e., based on hyperplanes or on prototypes, and using a soft or hard-gating mechanism. We propose a unified theoretical framework allowing us to theoretically characterize the proposed models’ expressiveness. We experimentally evaluate our backpropagation-free graph convolutional neural models on commonly adopted node classification datasets and show competitive performances compared to the backpropagation-based counterparts.