Older News

2024

• October 2024 Our paper “InterruptMe: Designing Intelligent Prompting Mechanisms for Pervasive Applications” has been awarded a Best Paper Runner-up Award in the 10-year Impact Awards category at ACM UbiComp 2024. You can find our UbiComp 2014 paper here.

• September 2024 We won the Best Paper Award for the paper “MarcoPolo: A Zero-Permission Attack for Location Type Inference from the Magnetic Field Using Mobile Devices” at CANS 2024. You can download the paper here.

• September 2024 New preprint: “Reinforcement Learning Discovers Efficient Decentralized Graph Path Search Strategies”. You can download the paper here.

• August 2024 Our paper “Graph Reinforcement Learning for Combinatorial Optimization: A Survey and Unifying Perspective” has been accepted for publication in Transactions on Machine Learning Research (TMLR). The paper will appear soon, in the meantime you can download the preprint here.

• August 2024 Our manifesto paper “Ecological Brain: Reframing the Study of Human Behaviour and Cognition” co-authored with the students of the first cohorts of our Leverhulme Doctoral Training Programme for the Ecological Study of the Brain has been accepted for publication in Royal Society Society Open Science. The preprint of the paper is available here.

• August 2024 Our paper “Dynamics of Moral Behavior in Heterogeneous Populations of Learning Agents” has been accepted in the Proceedings of the 7th AAAI/ACM Conference on AI, Ethics, and Society (AIES 2024). You can find the preprint of the paper here.

• July 2024 Our paper “Training Foundation Models as Data Compression: On Information, Model Weights and Copyright Law” will be presented at the 2nd Internation Workshop on Generative AI and Law (GenLaw 2024), colocated with the 41st International Conference on Machine Learning (ICML 2024), as spotlight presentation. You can download the paper here.

• June 2024 New preprint: “Partial Information Decomposition for Data Interpretability and Feature Selection”. You can download the paper here.

• June 2024 Our paper “(Ir)rationality and Cognitive Biases in Large Language Models” is now out in Royal Society Open Science. You can download the paper here.

• June 2024 Our paper “Game-theoretic Agent-based Modelling of Micro-level Conflict: Evidence from the ISIS-Kurdish War” is now out in PLOS ONE. You can download the paper here.

• June 2024 New preprint: “Large Language Models are Effective Priors for Causal Graph Discovery”. You can download the paper here.

• June 2024 Our paper “Creative Beam Search: LLM-as-a-Judge for Improving Response Generation has been accepted for publication in the proceedings of the 15th International Conference on Computational Creativity (ICCC 2024). You can download the paper here.

• May 2024 Our paper “Trust-based Consensus in Multi-Agent Reinforcement Learning Systems” has been accepted at the 1st Reinforcement Learning Conference (RLC 2024). The camera ready version will be available soon. In the meantime, you can download the preprint here.

• May 2024 Our paper “CoMIX: A Multi-agent Reinforcement Learning Training Architecture for Efficient Decentralized Coordination and Independent Decision Making” has been accepted for publication in Transactions on Machine Learning Research (TMLR). The paper will appear soon, in the meantime you can download the preprint here.

• May 2024 Our paper “Creativity and Machine Learning: A Survey” has been accepted in ACM Computing Surveys. The paper will appear soon. In the meantime, you can download the preprint here.

• April 2024 New preprint: “Graph Reinforcement Learning for Combinatorial Optimization: A Survey and Unifying Perspective”. You can download the paper here.

• April 2024 I gave an invited talk at the Machine+Behavior Conference 2024 at the Max Planck Institute in Berlin.

• April 2024 I gave an invited talk hosted by Aalto University and the University of Helsinki on 3 April 2024 as part of the event “AI generated it - who owns it?”.

• March 2024 New preprint “Do Agents Dream of Electric Sheep?: Improving Generalization in Reinforcement Learning through Generative Learning”. You can download the preprint here.

• March 2024 New preprint: “Dynamics of Moral Behavior in Heterogeneous Populations of Learning Agents”. You can download the preprint here.

• January 2024 New preprint: “Information-Theoretic State Variable Selection for Reinforcement Learning”. You can download the preprint here.

• January 2024 Our paper “Reinforcement Learning for Generative AI: State of the Art, Opportunities and Open Research Challenges” has been accepted for publication in the Journal of Artificial Intelligence Research (JAIR). You can download the paper here.

• January 2024 New preprint “Learning Machine Morality through Experience and Interaction”. You can download the preprint here.

• January 2024 New preprint “(Ir)rationality in AI: State of the Art, Research Challenges and Open Questions”. You can download the preprint here.

2023

• New preprint: “Tree Search in DAG Space with Model-based Reinforcement Learning for Causal Discovery”. You can download the preprint here.

• New preprint: “Reinforcement Learning for Generative AI: State of the Art, Opportunities and Open Research Challenges”. You can download the preprint here.

• New preprint: “CoMIX: A Multi-agent Reinforcement Learning Training Architecture for Efficient Decentralized Coordination and Independent Decision Making”. You can download the preprint here.

• New preprint: “Augmented Modular Reinforcement Learning based on Heterogeneous Knowledge” discussing a novel learning modular architecture based on reinforcement learning for processing and integrating multiple types of information (knowledge). You can download the article here.

• Our paper “Modeling Moral Choices in Social Dilemmas with Multi-Agent Reinforcement” has been accepted for publication in the main research track of the 32nd International Joint Conference on Artificial Intelligence (IJCAI 2023). You can download the preprint of the paper here.

• New preprint: “On the Creativity of Large Language Models” discussing the problem of machine creativity in relation to LLMs. You can download the article here.

• Our paper “CT-DQN: Control-Tutored Deep Reinforcement Learning” has been accepted for publication at the Learning for Dynamics and Control Conference (L4DC 2023). You can download the pre-print version of the paper here. The camera ready version of the paper will appear soon.

• Our paper “Planning Spatial Networks with Monte Carlo Tree Search” has been accepted for publication in Proceedings of the Royal Society A. You can download the paper here.

• Our paper “RLQ: Workload Allocation with Reinforcement Learning in Distributed Queues” has been accepted for publications in IEEE Transactions in Parallel and Distributed Systems. You can download the paper here.

• The applications for the UCL Foundational Artificial Intelligence PhD program for the September 2023 intake are now open. You can find all the information here.

• I am currently advertising a Postdoctoral Fellow position in my lab. I am looking for candidates with expertise in Machine Learning/Artificial Intelligence (with an interest in reinforcement learning and/or causal inference). Please do not hesitate to contact me for an informal discussion. Please apply here.

2022

• Our paper “Dynamic Network Reconfiguration for Entropy Maximization using Deep Reinforcement Learning” has been accepted at the Learning on Graphs Conference (LoG 2022). You can download the paper here.

• Our paper Control-Tutored Reinforcement Learning: Towards the Integration of Data-Driven and Model-Based Control has been accepted for publication at L4DC 2022.

• Our paper Goal-directed Graph Construction using Reinforcement Learning has been accepted for publication in the Proceedings of the Royal Society A.

• I got interviewed for a Q&A article on causality in digital medicine in Nature Communications.

• Our paper Solving Graph-based Public Good Games with Tree Search and Imitation Learning has been accepted for publication at NeurIPS 2021.

2021

• New arXiv preprint: “Reinforcement Learning on Encrypted Data”.

2020

• New paper Cooperation and Reputation Dynamics with Reinforcement Learning accepted at AAMAS 2021 (as full paper selected for oral presentation).

• New paper accepted in the Proceedings of the ACM on Interactive, Mobile, and Wearable Technologies (ACM IMWUT) and to be presented at ACM UbiComp 2021: Where You Go Matters: A Study on the Privacy Implications of Continuous Location Tracking.

• New preprint: Improving the Robustness of Graphs through Reinforcement Learning and Graph Neural Networks.

• Two new papers accepted in ACM IMWUT and to be presented at ACM UbiComp 2020: Quantifying the Relationships between Everyday Objects and Emotional States through Deep Learning Based Image Analysis Using Smartphones and A Multi-perspective Analysis of Social Context and Personal Factors in Office Settings for the Design of an Effective Mobile Notification System.

• Our book Intelligent Notification Systems published by Morgan&Claypool is out!

• Our paper Partner Selection for the Emergence of Cooperation in Multi-Agent Systems using Reinforcement Learning has been accepted for presentation in the Technical Program of AAAI 2020.

2019

• We received the 2019 ACM SIGMOBILE Test-of-Time Award for our paper “Sensing Meets Mobile Social Networks: The Design, Implementation and Evaluation of the CenceMe Application”.

• We received the Best Paper Award at ACM CHIIR’19 for the paper “NotifyMeHere: Intelligent Notification Delivery in Multi-Device Environments”.

• We received the SenSys Test-of-Time Award at ACM SenSys 2018 for our paper “Sensing Meets Mobile Social Networks: The Design, Implementation and Evaluation of the CenceMe Application” (presented at SenSys 2008).

• The application process for the 2019 intake of the cross-disciplinary Ecological Brain Doctoral Training Centre funded by Leverhulme Trust is now open. The Centre will fund 5 Ph.D. studentships (stipend plus fee) this year. The focus of the centre is the study of the brain and human behaviour in-the-wild. If you are interested please get in touch.

• The application process for the Ph.D. studentships of The Alan Turing Institute is also open. More information can be found here. The process of the selection will take place at University level first. Please get in touch if you are interested.

• We have launched MyMood. MyMood is an application that lets you record your emotional state at various times during the day using images. You can download the app here.

• We have launched TrackingAdvisor, a new iOS app that tracks your movements and automatically infers what the places you visit tell about you. You can download the app here.

2018

• I have been awarded a Visiting Professorship at the Department of Informatics, Universita’ della Svizzera Italiana in Lugano, Switzerland.

• I will be giving a talk on “Identification (and Obfuscation) in the Smartphone Era” at the 2nd International Workshop on Personal Analytics and Privacy in conjunction with ECML PKDD 2018.

• I joined the Editorial Board of ACM Computing Surveys.

• Our ICWSM paper on user identification using metadata has been covered by Wired, The Guardian, Süddeutsche Zeitung, and Schneier on Security among the others.

• I joined the Editorial Board of IEEE Pervasive Computing as Associate Editor in Chief.

• I joined the Editorial Board of the ACM Transactions on the Internet of Things.

• I joined the Editorial Board of ACM Computing Surveys.

• Our paper “You are your Metadata: Identification and Obfuscation of Social Media Users using Metadata Information” has been accepted for publication in the Proceedings of AAAI ICWSM 2018. In this paper we discuss the issues related to identification and obfuscation of user identity by means of metadata that are associated to social media profiles and posts.

• Our paper Predicting the Temporal Activity Patterns of New Venues has been accepted in EPJ Data Science. The paper presents a prediction framework able to use characteristic temporal signatures of places extracted from location-based social media to forecast weekly popularity dynamics of a new venue establishment in a city neighborhood.

• We wrote a paper on “Interpretable Machine Learning for Privacy-Preserving Pervasive Systems”. In this paper we propose a machine learning interpretability framework for inference algorithms based on data collected through pervasive systems and we outline the open challenges in this research area.

• The new preprint “Intelligent Notification Systems: A Survey of the State of the Art and Research Challenges” is now available on arXiv. The survey provides an overview of the current state of the art in the area of intelligent notification mechanisms that rely on the awareness of users’ context and preferences. It also outlines the research challenges in this area.

2017

• Our new paper containing some initial results about the development of deep learning models for psychological state prediction from mobile data was presented at the NIPS Workshop on Machine Learning for Health. You can download the paper here.

• Our new paper “Are you Getting Sick? Predicting Influenza-like Symptoms Using Human Mobility Behaviors” about the prediction of symptoms associated to influenza by analysing mobility patterns collected by means of mobile phones has been published in EPJ Data Science.

• Two papers were accepted in the Proceedings of the ACM on Interactive, Mobile, Wearable and Ubiquitous Technologies (IMWUT) and were presented in the main research track of ACM UbiComp’17 as part of the new journal-based conference model. In “MyTraces: Investigating Correlation and Causation between Users’ Emotional States and Mobile Phone Interaction” we show that users’ emotions have a causal impact on different aspects of mobile phone interaction. We also discuss the causal impact of the use of specific applications, reflecting the external users’ context such as socializing and travelling on the emotional state of the individual. In “Understanding the Role of Places and Activities on Mobile Phone Interaction and Usage Patterns” we present an in-depth study of the relationships between users’ activities and interaction with notifications and apps.

• An overview of our PrefMiner paper has been published in the ACM SIGMOBILE Mobile Computing and Communications Review (GetMobile). The paper discusses how PrefMiner can be considered one of the first examples of interpretable machine learning applied to the design of intelligent mobile systems. You can download the paper here.

• Our PrefMiner paper has also been listed in the ACM Best of Computing Notable Books and Articles for 2016.

• We wrote an article on “Avoiding Pitfalls when Using Machine Learning in HCI Studies”, which appeared in the July 2017 edition of ACM Interactions: the paper discusses some of the issues related to the use of machine learning in HCI, especially in behavioural studies.

• We have published the pre-print “A Comparison of Spatial-based Targeted Disease Containment Strategies using Mobile Phone Data” on the design of spatial disease containment strategies based on a real-world cellular network call dataset from Ivory Coast. More specifically, the paper discusses the impact of the socio-geographical heterogeneity on disease transmission dynamics. In particular, we consider the spreading of the Ebola virus as a case study.

• Our paper “Designing Effective Movement Digital Biomarkers for Unobtrusive Emotional State Mobile Monitoring” has been accepted at the 1st ACM Workshop on Digital Biomarkers colocated with ACM MobiSys 2017. The paper discusses the design of novel digital biomarkers for the inference of emotional states based on the fine-grained characterization of the mobility patterns of a user over time. You can download the paper from here. 

• We wrote a short survey on “Sensing and Modeling Human Behavior Using Social Media and Mobile Data”. The article will be part of a book that will be published in the next months. The pre-print of the article is available on ArXiv.

• Our paper “Anonymous or not? Understanding the Factors Affecting Personal Mobile Data Disclosure” has been published in ACM Transactions on Internet Technology. The article contains an experimental evaluation of the different factors affecting users’ disclosing choices of location and social interaction information. The paper can be downloaded here.

• I wrote an article on “Tracing Networks of Knowledge in the Digital Age”. The paper will appear in the Proceedings of the British Academy in the coming months. The paper is an output of the “Tracing networks: communicating knowledge in antiquity and the digital age” event organised by the British Academy some years ago. A pre-print of the paper can be downloaded from this link.

• Our paper on “Probabilistic Matching: Causal Inference under Measurement Errors” has been accepted for publication at the International Joint Conference on Neural Networks (IJCNN’17). In this work, we propose a novel approach for causal inference when one or more key variables are noisy. The proposed method has many practical applications for example for the analysis of streams of sensor data. A pre-print version of the paper can be downloaded here.

• We wrote a (fun) paper with some (serious) health policy implications about the analysis of cuisines around the world based on data from Yummly. The paper has been accepted for publication at WWW’17 in the Web Science Track. The project has been covered by MIT Technology Review, The Independent and France 24 among the others.

• Our paper “The Effect of Timing and Frequency of Push Notifications on Usage of a Smartphone-Based Stress Management Intervention: An Exploratory Trial” has been published in PLOS ONE. The article discusses the results of a trial on the impact of intelligent context-aware push notifications in smartphone-based stress management behavioural interventions.

2016

• I have joined the Editorial Board of the “Proceedings of the ACM on Interactive, Mobile, Wearable and Ubiquitous Technologies (IMWUT)”, the new journal that will publish the papers presented at ACM UbiComp. More information about the new publication model of UbiComp can be found here.

• We won the Best Paper Award at ACM UbiComp 2016 for our paper “PrefMiner: Mining User’s Preferences for Intelligent Mobile Notification Management”.

• At ACM UbiComp 2016 we also presented the paper “Towards Multi-modal Anticipatory Monitoring of Depressive States through the Analysis of Human-Smartphone Interaction” at the “Mental Health: Sensing and Intervention Workshop” colocated with UbiComp 2016.

• Our paper “Spatio-temporal Networks: Reachability, Centrality and Robustness” has been published in Royal Society Open Science. The work was also covered by the Evening Standard.

• We have been awarded a Google Internet of Things (IoT) Technology Research Award.

• Our paper “A Multilayer Approach to Multiplexity and Link Prediction in Online Geo-Social Networks” has been published in EPJ Data Science.

• I am one of the inaugural Faculty Fellows of the Alan Turing Institute, the UK National Institute for Data Science.

• Our paper “My Phone and Me: Understanding People’s Receptivity to Mobile Notifications” discussing various aspects of the reactions to (and interactions with) mobile notifications has been accepted for publication at ACM CHI’16 in the main research track. This is a data-driven and quantitative study that sheds a light on the actual use and impact of notifications on smartphones.

• Two full papers accepted at WWW’16: the paper “Measuring Urban Social Diversity Using Interconnected Geo-Social Networks” proposes a novel approach to the study of urban diversity using interconnected geo-social networks, with an analysis of human mobility and behaviour in London, whereas the paper “Who Benefits from the Sharing Economy of Airbnb?” analyses the penetration of Airbnb again in London also in relation to the geo-demographic characteristics of the various areas of the capital.

• Our paper “Investigating Causality in Human Behavior from Smartphone Sensor Data: A Quasi Experimental Approach” introducing a novel quasi-experimental approach for analysing causality (vs correlation) in human behaviour using sensor data collected by means of ubiquitous devices has been published in EPJ Data Science. In this paper we try to answer the following question: can we detect causality in a dataset even if we did not design the experiments and control groups? 

Last updated: 24 November 2024.