I am a senior research scientist at Nokia Bell Labs and a visiting researcher at the University of Cambridge. My work enables AI to handle the messiness of the real world through human-centric, data-efficient, and robust machine learning. I am particularly interested in the following paradigms:
- Self-supervision. Contrastive, masked, or generative - what comes after that?
- Transfer learning. How can models generalize out of distribution - what are their limits?
- Multi-modality/tasking. How to merge modalities in a data-agnostic way?
Previously, I completed a PhD in Computer Science at the University of Cambridge working with Prof. Cecilia Mascolo. During my studies, I was fortunate to work in diverse industries and companies including Microsoft Research, Telefonica Research, Ocado, Qustodio (acquired for $50M), and research labs.
My research has been published in top venues in artificial intelligence, ML for health, human-computer interaction, and signal processing while recent projects have been featured in international media such as the BBC, CNN, Guardian, Washington Post, Forbes, and Financial Times (see more below). Further, I am part of COVID-19 Sounds, one of the largest studies of audio AI for health.
june 2023 •
With the organizers of the Research Roundtables at ML4H 2022 we released a report on "Recent Advances, Applications and Open Challenges in Machine Learning for Health".
may 2023 •
Our music preferences paper was featured in the german newspaper Der Tagesspiegel. A paper "Evaluating Listening Performance for COVID-19 Detection by Clinicians and Machine Learning: Comparative Study" was published in JMIR, and a paper "Conditional Neural ODE Processes for Individual Disease Progression Forecasting: A Case Study on COVID-19" will appear in KDD 2023.
april 2023 •
We are organizing FairComp and WellComp workshops at UbiComp 2023 in Mexico - consider submitting your best works!
march 2023 •
Gave an invited talk on human-centric AI for health signals at a symposium organized by Cambridge Public Health and the Precision Health Initiative. My talk is available on Youtube.
february 2023 •
I was selected as a 'Rising Star in AI' by Jürgen Schmidhuber's AI initiative at KAUST and had the opportunity to talk at the honorary symposium. Also, our fitness work was covered by the Daily Mirror.
january 2023 •
Our fitness work was covered by the Bicycling Magazine, the Heidelberg Laureate Forum (Spektrum.de), and Managed Healthcare Executive.
december 2022 •
A paper on fitness prediction with wearables appeared in Nature Digital Medicine and was covered by the University of Cambridge and the Communications of the ACM. I was also invited to present this line of work at the Precision Health Informatics Data Lab of King's College London.
november 2022 •
Presented a paper on out-of-distribution detection and a paper on domain adaptation in ML4H 2022 (co-located with NeurIPS 2022 in New Orleans), where I also served as a senior panel/roundtable chair.
september 2022 • Organized and co-chaired WellComp 2022, held in conjunction with Ubicomp 2022 in Cambridge. Our paper "Investigating Domain-agnostic Performance in Activity Recognition using Accelerometer Data" was published at the HASCA workshop of the same conference. I will also serve on the organizing committee of CHIL 2023 as track chair - consider submitting your best works!
august 2022 • Gave an interview to IndiaAI.gov, the AI initiative of the government of India. Also, the CS department at Cambridge covered our recent JMIR paper.
july 2022 • Attended MobiUK 2022 at UCL with one contributed talk/abstract.
june 2022 • Gave a keynote talk at the AI Summit of the London Tech Week. We also released the recordings of the Federated Sensing tutorial at Mobicom'21.
may 2022 • Joined Bell Labs in Cambridge as a research scientist!
april 2022 • Our Covid-19 Sounds work has received the 2021 Hall of Fame Better Future Award from the Department of Computer Science and Technology at the University of Cambridge! A recent paper "COVID-19 Disease Progression Prediction via Audio Signals: A Longitudinal Study" has been accepted in JMIR. Also, our paper "Detecting sleep outside the clinic using wearable heart rate devices" has been accepted in Scientific Reports.
march 2022 • Gave a talk on "Self-supervised learning for health signals" at the Feinstein Institutes of Northwell Health in New York (remotely), hosted by Theo Zanos.
february 2022 • Our paper "Universals and variations in musical preferences: A study of preferential reactions to Western music in 53 countries" was published in the Journal of Personality and Social Psychology. The University of Cambridge covered it in a featured story.
december 2021 • Received an ACM SIGMOBILE travel award to attend MobiCom this coming March in New Orleans, USA.
november 2021 • Our paper "Sounds of COVID-19: exploring realistic performance of audio-based digital testing" has been accepted to Nature Digital Medicine! A short paper "Evaluating Contrastive Learning on Wearable Timeseries for Downstream Clinical Outcomes" is accepted to ML4H 2021, while our perspective "Breaking away from labels: the promise of self-supervised machine learning in intelligent health" will appear in Cell Patterns.
📖 Publications
2023
Conditional Neural ODE Processes for Individual Disease Progression Forecasting: A Case Study on COVID-19
Ting Dang, Jing Han, Tong Xia, Erika Bondareva, Chloë Siegele-Brown, Jagmohan Chauhan, Andreas Grammenos, Dimitris Spathis, Pietro Cicuta, Cecilia Mascolo
International Conference on Knowledge Discovery and Data Mining
(KDD), Long Beach, USA
Beyond Accuracy: A Critical Review of Fairness in Machine Learning for Mobile and Wearable Computing
Sofia Yfantidou, Marios Constantinides, Dimitris Spathis, Athena Vakali, Daniele Quercia, Fahim Kawsar
arXiv preprint
Recent Advances, Applications and Open Challenges in Machine Learning for Health: Reflections from Research Roundtables at ML4H 2022 Symposium
Stefan Hegselmann, Helen Zhou, Yuyin Zhou, Jennifer Chien, Sujay Nagaraj, Neha Hulkund, Shreyas Bhave, Michael Oberst ... Dimitris Spathis, Jun Seita, Bastiaan Quast, Megan Coffee, Collin Stultz, Irene Y Chen, Shalmali Joshi, Girmaw Abebe Tadesse
technical report
Evaluating Listening Performance for COVID-19 Detection by Clinicians and Machine Learning: A Comparative Study
Jing Han, Marco Montagna, Andreas Grammenos, Tong Xia, Erika Bondareva, Chloë Siegele-Brown, Jagmohan Chauhan, Ting Dang, Dimitris Spathis, Andres Floto, Pietro Cicuta, Cecilia Mascolo
Journal of Medical Internet Research (JMIR), 25
A Summary of the ComParE COVID-19 Challenges
Alican Akman, Harry Coppock, Christian Bergler, Maurice Gerczuk, Chloë Brown, Jagmohan Chauhan, Andreas Grammenos, Apinan Hasthanasombat, Dimitris Spathis, Tong Xia, Pietro Cicuta, Jing Han, Shahin Amiriparian, Alice Baird, Lukas Stappen, Sandra Ottl, Panagiotis Tzirakis, Anton Batliner, Cecilia Mascolo, Björn Wolfgang Schuller
Frontiers in Digital Health
2022
Longitudinal cardio-respiratory fitness prediction through wearables in free-living environments
Dimitris Spathis*, Ignacio Perez-Pozuelo*, Tomas I. Gonzales, Yu Wu, Soren Brage, Nicholas Wareham, Cecilia Mascolo (*equal contribution)
Nature Digital Medicine, 5(176)
Altmetric Top 5% of all research outputs
Sounds of COVID-19: exploring realistic performance of audio-based digital testing
Jing Han*, Tong Xia*, Dimitris Spathis, Erika Bondareva, Chloë Brown, Jagmohan Chauhan, Ting Dang, Andreas Grammenos, Apinan Hasthanasombat, Andres Floto, Pietro Cicuta, Cecilia Mascolo
Nature Digital Medicine, 5(16)
Breaking away from labels: the promise of self-supervised machine learning in intelligent health
Dimitris Spathis, Ignacio Perez-Pozuelo, Laia Marques-Fernandez, Cecilia Mascolo
Cell Patterns, 3(2)
Detecting sleep outside the clinic using wearable heart rate devices
Ignacio Perez-Pozuelo, Marius Posa, Dimitris Spathis, Kate Westgate, Nicholas Wareham, Cecilia Mascolo, Soren Brage, Joao Palotti
Scientific Reports, 12 (7956)
Exploring Longitudinal Cough, Breath, and Voice Data for COVID-19 Progression Prediction via Sequential Deep Learning: Model Development and Validation
Ting Dang, Jing Han, Tong Xia, Dimitris Spathis, Erika Bondareva, Chloë Brown, Jagmohan Chauhan, Andreas Grammenos, Apinan Hasthanasombat, Andres Floto, Pietro Cicuta, Cecilia Mascolo
Journal of Medical Internet Research (JMIR), 24(6)
Universals and variations in musical preferences: A study of preferential reactions to Western music in 53 countries
David Greenberg, Sebastian Wride, Daniel Snowden, Dimitris Spathis, Jeff Potter, Jason Rentfrow
Journal of Personality and Social Psychology, 122(2)
Altmetric Top 5% of all research outputs
Looking for Out-of-Distribution Environments in Multi-center Critical Care Data
Dimitris Spathis, Stephanie Hyland
Machine Learning for Health, New Orleans, USA
.png)
Turning Silver into Gold: Domain Adaptation with Noisy Labels for Wearable Cardio-Respiratory Fitness Prediction
Yu Wu, Dimitris Spathis, Hong Jia, Ignacio Perez-Pozuelo, Tomas I Gonzales, Soren Brage, Nicholas Wareham, Cecilia Mascolo
Machine Learning for Health, New Orleans, USA
Investigating Domain-agnostic Performance in Activity Recognition using Accelerometer Data
Apinan Hasthanasombat, Abhirup Ghosh, Dimitris Spathis, Cecilia Mascolo
UbiComp workshop on Human Activity Sensing Corpus & Applications (HASCA @ UbiComp), Cambridge, UK
2021
COVID-19 Sounds: A Large-Scale Audio Dataset for Digital Respiratory Screening
Tong Xia*, Dimitris Spathis*, Chloe Brown, Jagmohan Chauhan, Andreas Grammenos, Jing Han, Apinan Hasthanasombat, Erika Bondareva, Ting Dang, Andres Floto, Pietro Cicuta, Cecilia Mascolo
Neural Information Processing Systems (NeurIPS), Datasets and Benchmarks Track
Self-supervised transfer learning of physiological representations from free-living wearable data
Dimitris Spathis, Ignacio Perez-Pozuelo, Soren Brage, Nicholas Wareham, Cecilia Mascolo
Conference on Health, Inference, and Learning (CHIL), Virtual event, USA
Exploring Automatic COVID-19 Diagnosis via voice and symptoms from Crowdsourced Data
Jing Han, Chloë Brown*, Jagmohan Chauhan*, Andreas Grammenos*, Apinan Hasthanasombat*, Dimitris Spathis*, Tong Xia*, Pietro Cicuta, Cecilia Mascolo
International Conference on Acoustics, Speech, & Signal Processing
(ICASSP), Toronto, Canada
SelfHAR: Improving Human Activity Recognition through Self-training with Unlabeled Data
Chi Ian Tang, Ignacio Perez-Pozuelo*, Dimitris Spathis*, Soren Brage, Nicholas Wareham, Cecilia Mascolo
Proc. on Interactive, Mobile, Wearable and Ubiquitous Technologies (IMWUT/Ubicomp), 5(1)
The INTERSPEECH 2021 Computational Paralinguistics Challenge: COVID-19 Cough, COVID-19 Speech, Escalation & Primates
Björn W. Schuller, ... Dimitris Spathis, Tong Xia, Pietro Cicuta, Leon J. M. Rothkrantz, Joeri Zwerts, Jelle Treep, Casper Kaandorp
Conference of the International Speech Communication Association (Interspeech), Brno, Czechia
Digital Phenotyping and Sensitive Health Data: Implications for Data Governance
Ignacio Perez-Pozuelo, Dimitris Spathis, Jordan Gifford-Moore, Jessica Morley, Josh Cowls
Journal of the American Medical Informatics Association, 28(9)
Anticipatory Detection of Compulsive Body-focused Repetitive Behaviors with Wearables
Benjamin Searle, Dimitris Spathis, Marios Constantinides, Daniele Quercia, Cecilia Mascolo
ACM International Conference on Mobile Human-Computer Interaction (MobileHCI), Toulouse, France
Evaluating Contrastive Learning on Wearable Timeseries for Downstream Clinical Outcomes
Kevalee Shah, Dimitris Spathis, Chi Ian Tang, Cecilia Mascolo
Machine Learning for Health (ML4H), Virtual event
Federated mobile sensing for activity recognition
Stefanos Laskaridis, Dimitris Spathis, Mario Almeida
ACM International Conference on Mobile Computing and Networking (MobiCom), New Orleans, USA (tutorial)
Wearables, smartphones and artificial intelligence for digital phenotyping and health
Ignacio Perez-Pozuelo, Dimitris Spathis, Emma Clifton, Cecilia Mascolo
Digital Health, Chapter 3
2020
Exploring Automatic Diagnosis of COVID-19 from Crowdsourced Respiratory Sound Data
Chloë Brown*, Jagmohan Chauhan*, Andreas Grammenos*, Jing Han*, Apinan Hasthanasombat*, Dimitris Spathis*, Tong Xia*, Pietro Cicuta, Cecilia Mascolo
International Conference on Knowledge Discovery and Data Mining
(KDD), San Diego, USA
Oral presentation Cambridge University Hall of Fame Better Future Award
Learning Generalizable Physiological Representations from Large-scale Wearable Data
Dimitris Spathis, Ignacio Perez-Pozuelo, Soren Brage, Nicholas Wareham, Cecilia Mascolo
NeurIPS Machine Learning for Mobile Health workshop (ML4MH @ NeurIPS), Vancouver, Canada
Exploring Contrastive Learning in Human Activity Recognition for Healthcare
Chi Ian Tang, Ignacio Perez-Pozuelo, Dimitris Spathis, Cecilia Mascolo
NeurIPS Machine Learning for Mobile Health workshop (ML4MH @ NeurIPS), Vancouver, Canada
2019
Sequence Multi-task Learning to Forecast Mental Wellbeing from Sparse Self-reported Data
Dimitris Spathis, Sandra Servia, Katayoun Farrahi, Cecilia Mascolo, Jason Rentfrow
International Conference on Knowledge Discovery and Data Mining
(KDD), Anchorage, USA
Oral presentation (Top 6%)
Passive mobile sensing and psychological traits for large scale mood prediction
Dimitris Spathis, Sandra Servia, Katayoun Farrahi, Cecilia Mascolo, Jason Rentfrow
International Conference on Pervasive Computing Technologies for Healthcare (PervasiveHealth), Trento, Italy
Pre-PhD (2013-2018)
Interactive dimensionality reduction
using similarity projections
Dimitris Spathis, Nikolaos Passalis, Anastasios Tefas
Knowledge-Based Systems, 165
Fast, Visual and Interactive Semi-supervised Dimensionality Reduction
Dimitris Spathis, Nikolaos Passalis, Anastasios Tefas
ECCV Efficient Feature Representation Learning workshop (CEFRL @ ECCV 2018), Munich, Germany
Diagnosing Asthma and Chronic Obstructive Pulmonary Disease with Machine Learning
Dimitris Spathis, Panayiotis Vlamos
Health Informatics Journal, 25(3)
Class-based Prediction Errors to Detect Hate Speech with
Out-of-vocabulary Words
Joan Serra, Ilias Leontiadis, Dimitris Spathis, Gianluca Stringhini, Jeremy Blackburn, Athena Vakali
ACL Abusive Language Online workshop (ALW @ ACL 2017), Vancouver, Canada
A comparison between semi-supervised and supervised text mining techniques on detecting irony in greek political tweets
Basilis Charalampakis, Dimitris Spathis, Elias Kouslis, Katia Kermanidis
Engineering Applications of Artificial Intelligence, 51
Detecting Irony on Greek Political Tweets: A Text Mining Approach
Basilis Charalampakis, Dimitris Spathis, Elias Kouslis, Katia Kermanidis
International Conference on Engineering Applications of Neural Networks, Rhodes, Greece
Glocal News: An Attempt to Visualize the Discovery of Localized Top Local News, Globally
Dimitris Spathis, Theofilos Mouratidis, Spyros Sioutas, Athanasios Tsakalidis
International Conference on Conceptual Modeling, Hong Kong, China
Theses
Machine learning to model health with multimodal mobile sensor data
PhD thesis
University of Cambridge, 2021
Learning to interact with high-dimensional data
MSc thesis
Aristotle University, 2017
🧐 Academic service
Organizer:
- Co-chair of FairComp and WellComp workshops at UbiComp 2023, Cancun, Mexico.
- Co-organizer and track chair of CHIL 2023, Boston, USA.
- Senior panel/roundtable chair at ML4H 2022, New Orleans, USA.
- Chair of WellComp workshop at UbiComp 2022, Cambridge, UK.
- Co-organizer of the Federated sensing tutorial at MobiCom 2021, New Orleans, USA.
Program Committee Member: AAAI 2021-2023, IJCAI 2020, KDD 2020-2023 (PC & Session Chair), FAccT 2023, SIAM SDM 2022, Sensiblend @ Ubicomp 2021, Mobiquitous 2022.
Reviewer: NeurIPS, ICLR, ICML, AAAI, IJCAI, KDD, CHI, Ubicomp/IMWUT, CHIL, Nature Digital Medicine, Nature Scientific Reports, ICASSP, Expert Systems with Applications, Neurocomputing, WWW/The Web Conference, Engineering Applications of Artificial Intelligence, Sensors, ICWSM, ICPR, Pervasive and Mobile Computing, Computer Networks, The Visual Computer, and more.
📢 Talks
Human-centric AI for health signals with applications in fitness and activity modeling
- 📍 Cambridge Public Health symposium, Cambridge, UK — March 27, 2023
- 📍 Rising Stars in AI, KAUST, Saudi Arabia — February 20, 2023
- 📍 ML4H'22, New Orleans, USA (co-located with NeurIPS'22) — November 28, 2022
- 📍 King's College London, Precision Health Informatics Data Lab, London, UK — November 24, 2022
- 📍 AI Summit, London Tech week, London, UK — June 16, 2022
- 📍 Mobicom'21 (held 2022), New Orleans, USA — April 1, 2022
- 📍 Feinstein Institutes of Northwell Health, New York, USA (remote) — March 22, 2022
- 📍 NeurIPS'21, virtual event, Australia — December 7, 2021
- 📍 NeurIPS MeetUp Cambridge, University of Cambridge, UK — December 8, 2021
- 📍 MobiUK'21, virtual event, UK — July 6, 2021
- 📍 CHIL'21, virtual event, USA — April 8, 2021
- 📍 NeurIPS'20 ML4MH workshop, virtual event, Canada — December 12, 2020
- 📍 Jesus College Postgraduate Conference, virtual event, UK — March 5, 2021
- 📍 Barclays Eagle Lab, Cambridge, UK — March 12, 2020
- 📍 KDD'19, Anchorage, USA — August 4, 2019
- 📍 PervasiveHealth'19, Trento, Italy — May 20, 2019
- 📍 MRC Epidemiology Unit, University of Cambridge, UK — March 5, 2019
- 📍 Ocado, Barcelona, Spain & Hatfield, UK (remote) — July 10, 2019
- 📍 Facebook PhD Open House, London, UK — October 25, 2018
- 📍 MobiUK'18, Cambridge, UK — September 13, 2018
- 📍 ACL'17 Abusive Language workshop, Vancouver, Canada — August 4, 2017
- 📍 EANN'15, Rhodes, Greece — September 25, 2015
🗞️ Press
Audio AI for COVID-19: Cambridge University (1), (2), (3), (4), BBC, The Guardian, Financial Times, The Times, Forbes, Slate, Huffington Post, DailyMail, ITV, IEEE Spectrum, TheNextWeb, STAT, EPFL, TheScientist, The Register, KDnuggets, NPR/WBUR, Royal Society of Biology, Lancet Digital Health, Psychology Today, El Pais, RAI, Corriere della Sera, Focus, DerStandard.
AI for wearables: Cambridge University (1), (2), VentureBeat, Business Insider, Communications of the ACM, National Committee for Quality Assurance, Daily Mirror, Bicycling Magazine, Heidelberg Laureate Forum (Spektrum.de).
Data-driven music psychology: Cambridge University, The Times, Washington Post, CNN, The Telegraph, Sky News, ITV, DailyMail, Inc., CTV, ZDF, Der Tagesspiegel, ABC.ES, ABC.AU, ELLE, Cosmopolitan, RTBF, TEDx.
Interviews: IndiaAI.gov
🎒 Mentoring
I enjoy collaborating with PhD and thesis students. Here are some recent research projects I supervised:
- Chi Ian Tang — Self-supervised and continual learning (papers at IMWUT & NeurIPS-W)
- Benjamin Searle — Predicting compulsive behaviours with wearables (paper at MobileHCI)
- Kevalee Shah — Benchmarking contrastive learning (paper at ML4H)
- Yu (Yvonne) Wu — Weakly-supervised and self-supervised learning (paper at ML4H)
- Shohreh Deldari — Multimodal self-supervised learning (ongoing)
- Sofia Yfantidou — Machine learning fairness (ongoing)
- Chuen Low — Attention models for timeseries
I have also been a teaching assistant for the following undergraduate courses:
- Machine Learning & Real-World Data (U. of Cambridge)
- Mobile & Sensor Systems (U. of Cambridge)
- Scientific Computing (U. of Cambridge)
- Numerical Analysis (Aristotle University)
🎠 Playground
“The next big thing in technology often starts off looking like a toy”
Quantifying name-dropping
Communitypoprefs.com is a data visualization website, where we present every pop-culture reference over the course of 5 seasons of the TV series Community.
Map out your music taste on Spotify
Visualizing my favourite songs on Spotify with dimensionality reduction and anomaly detection. Data essay published in Cuepoint Magazine, Medium's premier music publication.
Children books and childish language?
Text mining Game of Thrones, Harry Potter, Hunger Games and Lord of the Rings books. Data essay featured in Medium's Editor Picks.
Anonymize kids' faces before posting online
Mobile app with face recognition, age estimation, & emotion recognition to blur kids or replace their face with emotion-based emoji. Developed during HackZurich 2018.
Discover top local news globally
Glocalne.ws was a mashup of Google News and Google Maps. Unfortunately it is now defunct due to API discontinuance.
Composing music and text with Recurrent Neural Networks
Training neural networks on massive amounts of musical notation and literature and letting them create their own art. Essay in Greek but you can still see/listen to the results.
🕳️🐇 Personal
Non-academic things about me: I love music, both playing and listening. I am mostly into art rock and indie folk, with the occasional exception of some well-crafted pop. Although I am an accordionist by training, over the last few years I've been playing mostly piano and ukulele. In a previous life, I performed with the critically acclaimed band The Children of the Oldness (aka Kore Ydro) and recorded the album "Consortium in Amato" (listen here).
I also enjoy street photography and in particular playing with light—photography comes from Greek φως (light) and γραφή (writing), or drawing with light. A sample of my shots is on Flickr and one of my landscapes was featured in the Huffington Post.
Lastly, and perhaps most importantly, I'm always on the lookout for ways to move items from the "non-academic list" to the "academic list"—let me know if you'd like to help!