me

Email Github Linkedin Scholar

Alessio Gravina​ is a Post-Doc at the University of Pisa. He received his PhD in Computer Science from University of Pisa, supervised by Davide Bacciu and Claudio Gallicchio. His research interests take place in the domain of representation learning for graphs inspired by dynamical systems and neural differential equations. He is a member of Computational Intelligence and Machine Learning group and Pervasive AI Lab. He was a visiting researcher at Huawei Research Center, Munich in 2023; IDSIA, Lugano (CH) in 2022; and at Stanford University in 2019. During his career, he won the Fujistu AI-NLP Challenge and was a visiting student at University College Dublin as a member of the Erasmus+ programme.

Interests: Graph Representation Learning - Neural Differential Equations - Dynamic Graphs - Deep Learning

Download CV (74 KiB)

Download PhD Thesis (9,1 MB)

This website has been designed to minimise the energy consumption and CO2 emissions that result from navigating the internet. The interface uses Arial and Times New Roman to avoid unnecessary HTTP requests. It is available only in dark mode to reduce screen brightness and energy consumption – especially in mobile use where OLED screens are most common.

Education

Location University of Pisa, Pisa, Italy
From - To 11/2020 - 10/2024
Thesis title Information propagation dynamics in Deep Graph Networks
Description Representation learning for graphs inspired by dynamical systems and neural differential equations

Location Virtual
From - To 08/2021
Description 15-days specialized AI school that covers the topics of Rep. Learning & Statistical ML, ML in Healthcare, NLP, and AI for Good. Acceptance rate 15%.

Location University College Dublin, Dublin, Ireland
From - To 01/2019 - 05/2019
Description Student at the Computer Science Department in the framework of the EU Erasmus+ project

Location University of Pisa, Pisa, Italy
From - To 09/2018 - 03/2020
Final grade 110/110 cum laude (equivalent GPA: 4/4)
Thesis title Machine Learning prediction of compounds impact on Schizophrenia treatment

Location University of Pisa, Pisa, Italy
From - To 09/2014 - 03/2018
Final grade 103/110 (equivalent GPA: 3.75/4)
Thesis title Machine Learning for the prediction of Bronchopulmonary dysplasia risk

Experience

Location University of Pisa, Pisa, Italy
From - To 08/2024 - present
Description Representation learning for graphs inspired by dynamical systems

Location Huawei Research Center, Munich, Germany
From - To 03/2023 - 08/2023
Description Joined the AI4Sec team to work on Representation Learning for Continuous-Time Dynamic Graphs leveraging ODE-based neural architectures. The internship has been done under the supervision of Claas Grohnfeldt, Giulio Lovisotto and Michele Russo.

Location Dalle Molle Institute for Artificial Intelligence Research (IDSIA USI-SUPSI), Lugano, Switzerland
From - To 04/2022 - 07/2022
Description Worked on Representation Learning for Dynamic Graphs under the supervision of Prof. Cesare Alippi

Location University of Pisa, Pisa, Italy
From - To 02/2021 - 05/2021
Course Introduction to Programming and Algorithms
Description Weekly office hours for homework assistance and reinforcement of learned concepts

Location University of Pisa, Pisa, Italy
From - To 07/2020 - 11/2020
Description Worked on Deep Learning for graphs applied to Covid-19 related data

Location Vydiant, Remote
From - To 01/2020 - 06/2020
Description Worked on relation identification for biomedical corpus

Location Stanford University, Stanford, United States
From - To 09/2019 - 12/2019
Description Worked on Deep Learning for graphs applied to Schizophrenia treatment

Awards

Year 2023
Description Best Student Paper Award for the work "Non-Dissipative Propagation by Anti-Symmetric Deep Graph Networks". This is a preliminary version of the other work "Anti-Symmetric DGN: a stable architecture for Deep Graph Networks" published in ICLR 2023.
Link DLG-AAAI`23 workshop and announcement

Rank 1st place
Prize $20,000
Year 2018
Description Developed a novel natural language processing technology to complement and strengthen Fujitsu’s Zinrai FAQ search.
Link https://openinnovationgateway.com/ai-nlp-challenge/

Publications

(*) means corresponding author or equal contribution

Authors A. Gravina*, D. Zambon, D. Bacciu, C. Alippi
Link https://www.ijcai.org/proceedings/2024/445
Citation 
@inproceedings{gravina2024tgode,
    title     = {Temporal Graph ODEs for Irregularly-Sampled Time Series},
    author    = {Gravina, Alessio and Zambon, Daniele and Bacciu, Davide and Alippi, Cesare},
    booktitle = {Proceedings of the Thirty-Third International Joint Conference on
                Artificial Intelligence, {IJCAI-24}},
    publisher = {International Joint Conferences on Artificial Intelligence Organization},
    editor    = {Kate Larson},
    pages     = {4025--4034},
    year      = {2024},
    month     = {8},
    note      = {Main Track},
    doi       = {10.24963/ijcai.2024/445},
    url       = {https://doi.org/10.24963/ijcai.2024/445},
}
Abstract Modern graph representation learning works mostly under the assumption of dealing with regularly sampled temporal graph snapshots, which is far from realistic, e.g., social networks and physical systems are characterized by continuous dynamics and sporadic observations. To address this limitation, we introduce the Temporal Graph Ordinary Differential Equation (TG-ODE) framework, which learns both the temporal and spatial dynamics from graph streams where the intervals between observations are not regularly spaced. We empirically validate the proposed approach on several graph benchmarks, showing that TG-ODE can achieve state-of-the-art performance in irregular graph stream tasks.
Github https://github.com/gravins/TG-ODE

Authors A. Gravina*, G. Lovisotto*, C. Gallicchio, D. Bacciu, C. Grohnfeldt
Link https://openreview.net/forum?id=gVg8V9isul
Citation 
@inproceedings{gravina2024ctan,
    title={Long Range Propagation on Continuous-Time Dynamic Graphs},
    author={Alessio Gravina and Giulio Lovisotto and Claudio Gallicchio and Davide Bacciu and Claas Grohnfeldt},
    booktitle={Forty-first International Conference on Machine Learning},
    year={2024},
    url={https://openreview.net/forum?id=gVg8V9isul}
}
Abstract Learning in Continuous-Time Dynamic Graphs (C-TDGs) requires accurately modeling spatio-temporal information on streams of irregularly sampled events. While many methods have been proposed recently, we find that most message passing-, recurrent- or self-attention-based methods perform poorly on long-range tasks. These tasks require correlating information that occurred "far" away from the current event, either spatially (higher-order node information) or along the time dimension (events occurred in the past). To address long-range dependencies, we introduce continuous-time graph anti-symmetric network (CTAN). Grounded within the ordinary differential equations framework, our method is designed for efficient propagation of information. In this paper, we show how CTAN's (i) long-range modeling capabilities are substantiated by theoretical findings and how (ii) its empirical performance on synthetic long-range benchmarks and real-world benchmarks is superior to other methods. Our results motivate CTAN's ability to propagate long-range information in C-TDGs as well as the inclusion of long-range tasks as part of temporal graph models evaluation.
Github https://github.com/gravins/non-dissipative-propagation-CTDGs

Authors A. Gravina* and D. Bacciu
Link https://ieeexplore.ieee.org/document/10490120
Citation 
@article{gravina2023deep,
    author={Gravina, Alessio and Bacciu, Davide},
    journal={IEEE Transactions on Neural Networks and Learning Systems}, 
    title={{Deep Learning for Dynamic Graphs: Models and Benchmarks}}, 
    year={2024},
    volume={},
    number={},
    pages={1-14},
    doi={10.1109/TNNLS.2024.3379735}
}
Abstract Recent progress in research on deep graph networks (DGNs) has led to a maturation of the domain of learning on graphs. Despite the growth of this research field, there are still important challenges that are yet unsolved. Specifically, there is an urge of making DGNs suitable for predictive tasks on real-world systems of interconnected entities, which evolve over time. With the aim of fostering research in the domain of dynamic graphs, first, we survey recent advantages in learning both temporal and spatial information, providing a comprehensive overview of the current state-of-the-art in the domain of representation learning for dynamic graphs. Second, we conduct a fair performance comparison among the most popular proposed approaches on node-and edge-level tasks, leveraging rigorous model selection and assessment for all the methods, thus establishing a sound baseline for evaluating new architectures and approaches.
Github https://github.com/gravins/dynamic_graph_benchmark

Authors A. Gravina*, G. Lovisotto*, C. Gallicchio, D. Bacciu, C. Grohnfeldt
Link https://openreview.net/pdf?id=zAHFC2LNEen
Citation Please refer to the extended version of this work: "Long Range Propagation on Continuous-Time Dynamic Graphs"
Abstract Recent research on Deep Graph Networks (DGNs) has broadened the domain of learning on graphs to real-world systems of interconnected entities that evolve over time. This paper addresses prediction problems on graphs defined by a stream of events, possibly irregularly sampled over time, generally referred to as Continuous-Time Dynamic Graphs (C-TDGs). While many predictive problems on graphs may require capturing interactions between nodes at different distances, existing DGNs for C-TDGs are not designed to propagate and preserve long-range information - resulting in suboptimal performance. In this work, we present Continuous-Time Graph Anti-Symmetric Network (CTAN), a DGN for C-TDGs designed within the ordinary differential equations framework that enables efficient propagation of long-range dependencies. We show that our method robustly performs stable and non-dissipative information propagation over dynamically evolving graphs, where the number of ODE discretization steps allows scaling the propagation range. We empirically validate the proposed approach on several real and synthetic graph benchmarks, showing that CTAN leads to improved performance while enabling the propagation of long-range information.
Github https://github.com/gravins/non-dissipative-propagation-CTDGs

Authors J. Reha, G. Lovisotto, M. Russo, A. Gravina, and C. Grohnfeldt
Link https://openreview.net/pdf?id=88tGIxxhsfn
Citation 
@inproceedings{
    reha2023anomaly,
    title={Anomaly Detection in Continuous-Time Temporal Provenance Graphs},
    author={Jakub Reha and Giulio Lovisotto and Michele Russo and Alessio Gravina and Claas Grohnfeldt},
    booktitle={Temporal Graph Learning Workshop @ NeurIPS 2023},
    year={2023},
    url={https://openreview.net/forum?id=88tGIxxhsf}
    }
Abstract Recent advances in Graph Neural Networks (GNNs) have matured the field of learning on graphs, making GNNs essential for prediction tasks in complex, interconnected, and evolving systems. In this paper, we focus on self-supervised, inductive learning for continuous-time dynamic graphs. Without compromising generality, we propose an approach to learn representations and mine anomalies in provenance graphs, which are a form of large-scale, heterogeneous, attributed, and continuous-time dynamic graphs used in the cybersecurity domain, syntactically resembling complex temporal knowledge graphs. We modify the Temporal Graph Network (TGN) framework to heterogeneous input data and directed edges, refining it specifically for inductive learning on provenance graphs. We present and release two pioneering large-scale, continuous-time temporal, heterogeneous, attributed benchmark graph datasets. The datasets incorporate expert-labeled anomalies, promoting subsequent research on representation learning and anomaly detection on intricate real-world networks. Comprehensive experimental analyses of modules, datasets, and baselines underscore the effectiveness of TGN-based inductive learning, affirming its practical utility in identifying semantically significant anomalies in real-world systems.
Github https://github.com/JakubReha/ProvCTDG

Authors F. Errica*, A. Gravina*, D. Bacciu, and A. Micheli
Link https://www.esann.org/sites/default/files/proceedings/2023/ES2023-35.pdf
Citation 
@inproceedings{hmm_tgl,
    title={Hidden Markov Models for Temporal Graph Representation Learning},
    author={Errica, Federico and Gravina, Alessio and Bacciu, Davide and Micheli, Alessio},
    booktitle={Proceedings of the 31st European Symposium on Artificial Neural Networks, 
               Computational Intelligence and Machine Learning (ESANN)},
    year={2023},
    }
Abstract We propose the Hidden Markov Model for temporal Graphs, a deep and fully probabilistic model for learning in the domain of dynamic time-varying graphs. We extend hidden Markov models for sequences to the graph domain by stacking probabilistic layers that perform efficient message passing and learn representations for the individual nodes. We evaluate the goodness of the learned representations on temporal node prediction tasks, and we observe promising results compared to neural approaches.
Github https://github.com/nec-research/hidden_markov_model_temporal_graphs

Authors A. Gravina*, C. Gallicchio, and D. Bacciu
Link Provided soon
Citation 
Provided soon
Abstract Deep Graph Networks (DGNs) currently dominate the research landscape of learning from graphs, due to the efficiency of their adaptive message-passing scheme between nodes. However, DGNs are typically afflicted by a distortion in the information flowing from distant nodes (i.e., over-squashing) that limit their ability to learn long-range dependencies. This reduces their effectiveness, since predictive problems may require to capture interactions at different, and possibly large, radii in order to be effectively solved. We focus on Anti-symmetric Deep Graph Networks (A-DGNs), a recently proposed neural architecture for learning from graphs. A-DGNs are designed based on stable and non-dissipative ordinary differential equations, with a key architectural design based on an anti-symmetric structure of the internal weights. In this paper, we investigate the merits of the resulting architectural bias by incorporating randomized internal connections in node embedding computations and by restricting the training algorithms to operate exclusively at the output layer. To empirically validate our approach, we conduct experiments on various graph benchmarks, demonstrating the effectiveness of the proposed approach in learning from graph data.
Github https://github.com/gravins/Anti-SymmetricDGN

Authors A. Gravina*, D. Bacciu, and C. Gallicchio
Link https://openreview.net/forum?id=J3Y7cgZOOS
Citation 
@inproceedings{gravina2023adgn,
  author = {Alessio Gravina and Davide Bacciu and Claudio Gallicchio},
  title = {Anti-Symmetric {DGN}: a stable architecture for Deep Graph Networks},
  booktitle = {The Eleventh International Conference on Learning Representations },
  year = {2023},
  url = {https://openreview.net/forum?id=J3Y7cgZOOS}
}
Abstract Deep Graph Networks (DGNs) currently dominate the research landscape of learning from graphs, due to their efficiency and ability to implement an adaptive message-passing scheme between the nodes. However, DGNs are typically limited in their ability to propagate and preserve long-term dependencies between nodes, i.e., they suffer from the over-squashing phenomena. This reduces their effectiveness, since predictive problems may require to capture interactions at different, and possibly large, radii in order to be effectively solved. In this work, we present Anti-Symmetric Deep Graph Networks (A-DGNs), a framework for stable and non-dissipative DGN design, conceived through the lens of ordinary differential equations. We give theoretical proof that our method is stable and non-dissipative, leading to two key results: long-range information between nodes is preserved, and no gradient vanishing or explosion occurs in training. We empirically validate the proposed approach on several graph benchmarks, showing that A-DGN leads to improved performance and enables to learn effectively even when dozens of layers are used.
Github https://github.com/gravins/Anti-SymmetricDGN

Authors A. Gravina*, D. Bacciu, and C. Gallicchio
Link https://drive.google.com/file/d/1uPHhjwSa3g_hRvHwx6UnbMLgGN_cAqMu/view
Citation Please refer to the extended version of this work: "Anti-Symmetric DGN: a stable architecture for Deep Graph Networks"
Abstract Deep Graph Networks (DGNs) currently dominate the research landscape of learning from graphs, due to the efficiency of their adaptive message-passing scheme between nodes. However, DGNs are typically limited in their ability to propagate and preserve long-term dependencies between nodes, i.e., they suffer from the over-squashing phenomena. This reduces their effectiveness, since predictive problems may require to capture interactions at different, and possibly large, radii in order to be effectively solved. In this work, we present Anti-Symmetric DGN (A-DGN), a framework for stable and non-dissipative DGN design, conceived through the lens of ordinary differential equations. We give theoretical proof that our method is stable and non-dissipative, leading to two key results: long-range information between nodes is preserved, and no gradient vanishing or explosion occurs in training. We empirically validate the proposed approach on several graph benchmarks, showing that A-DGN yields to improved performance and enables to learn effectively even when dozens of layers are used.
Github https://github.com/gravins/Anti-SymmetricDGN
Award This work was awarded of the Best Student Paper Award at the DLG-AAAI`23 workshop. See also the announcement here.

Authors D. Bacciu, F. Errica, A. Gravina*, L. Madeddu, M. Podda, G. Stilo
Link https://ieeexplore.ieee.org/document/10026802
Citation 
@article{gravina2023DrugRep,
   author = {Bacciu, Davide and Errica, Federico and Gravina, Alessio and Madeddu, Lorenzo and Podda, Marco and Stilo, Giovanni},
   title = {Deep Graph Networks for Drug Repurposing with Multi-Protein Targets},
   journal = {IEEE Transactions on Emerging Topics in Computing},
   year = {2023},
   volume={}
   number={},
   pages={1-14},
   doi={10.1109/TETC.2023.3238963}
}
Abstract In the early phases of the COVID-19 pandemic, repurposing of drugs approved for use in other diseases helped counteract the aggressiveness of the virus. Therefore, the availability of effective and flexible methodologies to speed up and prioritize the repurposing process is fundamental to tackle present and future challenges to worldwide health. This work addresses the problem of drug repurposing through the lens of deep learning for graphs, by designing an architecture that exploits both structural and biological information to propose a reduced set of drugs that may be effective against an unknown disease. Our main contribution is a method to repurpose a drug against multiple proteins, rather than the most common single-drug/single-protein setting. The method leverages graph embeddings to encode the relevant proteins' and drugs' information based on gene ontology data and structural similarities. Finally, we publicly release a comprehensive and unified data repository for graph-based analysis to foster further studies on COVID-19 and drug repurposing. We empirically validate the proposed approach in a general drug repurposing setting, showing that it generalizes better than single protein repurposing schemes. We conclude the manuscript with an exemplified application of our method to the COVID-19 use case. All source code is publicly available.
Github https://github.com/gravins/covid19-drug-repurposing-with-DGNs

Authors A. Gravina*, J.L. Wilson, D. Bacciu, K.J. Grimes, and C. Priami
Link https://journals.plos.org/ploscompbiol/article?id=10.1371/journal.pcbi.1009531
Citation 
@article{10.1371/journal.pcbi.1009531,
  doi = {10.1371/journal.pcbi.1009531},
  author = {Gravina, Alessio AND Wilson, Jennifer L. AND Bacciu, Davide AND Grimes, Kevin J. AND Priami, Corrado},
  journal = {PLOS Computational Biology},
  publisher = {Public Library of Science},
  title = {Controlling astrocyte-mediated synaptic pruning signals for schizophrenia drug repurposing with deep graph networks},
  year = {2022},
  month = {05},
  volume = {18},
  url = {https://doi.org/10.1371/journal.pcbi.1009531},
  pages = {1-19},
  number = {5},                
}
Abstract Schizophrenia is a debilitating psychiatric disorder, leading to both physical and social morbidity. Worldwide 1% of the population is struggling with the disease, with 100,000 new cases annually only in the United States. Despite its importance, the goal of finding effective treatments for schizophrenia remains a challenging task, and previous work conducted expensive large-scale phenotypic screens. This work investigates the benefits of Machine Learning for graphs to optimize drug phenotypic screens and predict compounds that mitigate abnormal brain reduction induced by excessive glial phagocytic activity in schizophrenia subjects. Given a compound and its concentration as input, we propose a method that predicts a score associated with three possible compound effects, i.e., reduce, increase, or not influence phagocytosis. We leverage a high-throughput screening to prove experimentally that our method achieves good generalization capabilities. The screening involves 2218 compounds at five different concentrations. Then, we analyze the usability of our approach in a practical setting, i.e., prioritizing the selection of compounds in the SWEETLEAD library. We provide a list of 64 compounds from the library that have the most potential clinical utility for glial phagocytosis mitigation. Lastly, we propose a novel approach to computationally validate their utility as possible therapies for schizophrenia.
Github https://github.com/gravins/DGNs-for-schizophrenia

Authors A. Gravina*, F. Rossetto*, S. Severini*, and G. Attardi
Link http://ceur-ws.org/Vol-2481/paper64.pdf
Citation 
@inproceedings{grs_comparative_study,
  author    = {Gravina, Alessio and Rossetto, Federico and Severini, Silvia and Attardi, Giuseppe},
  editor    = {Bernardi, Raffaella and Navigli, Roberto and Semeraro, Giovanni},
  title     = {A Comparative Study of Models for Answer Sentence Selection},
  booktitle = {Proceedings of the Sixth Italian Conference on Computational Linguistics,
              Bari, Italy, November 13-15, 2019},
  series    = {{CEUR} Workshop Proceedings},
  volume    = {2481},
  publisher = {CEUR-WS.org},
  year      = {2019},
  url       = {http://ceur-ws.org/Vol-2481/paper64.pdf}
}
Abstract Answer Sentence Selection is one of the steps typically involved in Question Answering. Question Answering is considered a hard task for natural language processing systems, since full solutions would require both natural language understanding and inference abilities. In this paper, we explore how the state of the art in answer selection has improved recently, comparing two of the best proposed models for tackling the problem: the Crossattentive Convolutional Network and the BERT model. The experiments are carried out on two datasets, WikiQA and SelQA, both created for and used in open-domain question answering challenges. We also report on cross domain experiments with the two datasets.

Authors A. Gravina*, F. Rossetto*, S. Severini*, and G. Attardi
Link http://ceur-ws.org/Vol-2244/paper_05.pdf
Citation 
@inproceedings{grs_cross_attention,
  author    = {Gravina, Alessio and Rossetto, Federico and Severini, Silvia and Attardi, Giuseppe},
  editor    = {Basile, Pierpaolo and Basile, Valerio and Croce, Danilo and Dell'Orletta, Felice and Guerini, Marco},
  title     = {Cross Attention for Selection-based Question Answering},
  booktitle = {Proceedings of the 2nd Workshop on Natural Language for Artificial
                Intelligence {(NL4AI} 2018) co-located with 17th International Conference
                of the Italian Association for Artificial Intelligence (AI*IA 2018),
                Trento, Italy, November 22nd to 23rd, 2018},
  series    = {{CEUR} Workshop Proceedings},
  volume    = {2244},
  pages     = {53--62},
  publisher = {CEUR-WS.org},
  year      = {2018},
  url       = {http://ceur-ws.org/Vol-2244/paper\_05.pdf},
}
Abstract Answer Sentence Selection (ASS) is one of the steps typically involved in Question Answering, a hard task for natural language processing since full solutions would require both natural language understanding and world knowledge. We present a new approach to tackle ASS, based on a Cross-Attentive Convolutional Neural Network. The approach was designed for competing in the Fujitsu AI-NLP challenge Fujitsu [4], which evaluates systems on their performance on the SelQA [7] dataset. This dataset was created on purpose as a benchmark to stress the ability of systems to go beyond simple word co-occurrence criteria. Our submission achieved the top score in the challenge.

Contacts

alessio.gravina@di.unipi.it

Dipartimento di Informatica, Largo B. Pontecorvo 3, 56127 Pisa, Italy