free web stats



antoniasardi.uoa.gr
(don't copy/paste, as it won't work!)

>_ I hold a Ph.D. from the Dept. of Informatics and Telecoms, National and Kapodistrian University of Athens. My Ph.D. thesis, Anomaly Detection on Temporal Data with Applications to Social Networks and Healthcare, was advised by Prof. D. Gunopulos. I, also, hold an M.Sc. in Advanced Information Systems and a B.Sc. in Computer Science from the same department. Since 2011, I am working as a Research Scientist and Engineer in various research projects at the National and Kapodistrian University of Athens (NKUA) and Athens University in Economics and Business (AUEB).

My research interests include Data Mining, Machine Learning, and Anomaly Detection, with a focus on Social Network Analysis, Graph Representations and Healthcare Applications. Additionally, I am a member of the Knowledge Discovery in Databases Laboratory (KDDLab) and the Management of Data, Information & Knowledge Group (Madgik). I am a regular PC/reviewer for ICML, ICLR (outstanding reviewer in 2021), NeurIPS (top reviewer in 2018), TheWebConf, ICWSM, AAAI, and other various ML/AI conferences and journals.

In 2020, I did a research visit at the Geometric Computing Group advised by prof. L. Guibas at the Computer Science Department at Stanford University. We were working on Self-Supervised Node Representation Learning in Citation Networks. In 2019, I was a research intern working with the Personalization team at Spotify Tech Research, under Mounia Lalmas' supervision. My project was on Music Recommendations via Graph Representations (published in ISMIR 2021). In 2018, I was a research intern working with Edgar Meij and the Graph Analytics team at Bloomberg AI. My project was on Ranking Notable News using Knowledge Graphs (published in ECIR 2020). In 2017, I was a machine learning engineering intern at Uber, where I worked on Anomaly Detection in Sparse Timeseries and deployed a relevant system into production.

I have organized and volunteered in various outreach programs, such as ACM Student Chapter UoA, Rails Girls Athens and Django Girls, and I am always excited to participate in such events. If you are organizing one, and you think I will be a good fit, do not hesitate to contact me!


Highlights

October 2021 Our work "Multi-Task Learning of Graph-based Inductive Representations of Music Content" is accepted at ISMIR 2021! Joint work with Federico Tomasi, Rishabh Mehrotra and Mounia Lalmas. Read here more about our work that was featured at the Spotify Research Blog.
March 2020 I am excited to receive an outstanding reviewer award for ICLR 2021!
December 2020 I am thrilled to announce I have successfully defended my PhD thesis. 🎉🎓
December 2020 Our work "News Monitor: A Framework for Querying News in Real Time" is accepted at the ECIR 2021! Joint work with Nikolaos Panagiotou and Dimitrios Gunopulos.
November 2020 Our work "Predictive Modeling of Infant Mortality" is accepted at the Data Mining and Knowledge Discovery journal! Joint work with Clemens Noelke, Nick Huntington, Dolores Acevedo-Garcia and Dimitrios Gunopulos.
February 2020 Excited to join the Geometric Computing Group advised by prof. Guibas at the Computer Science Department at Stanford University.
December 2019 Our work "Identifying Notable News Stories" is accepted at ECIR 2020! Joint work with Edgar Meij and Giorgio Stefanoni from my Bloomberg AI internship last year. 🎉
Update: Check out our paper and our presentation on YouTube to learn more.
December 2019 Our proposal got accepted and we will be awarded with 75,000€ to build a system for "News Articles Monitoring and Analysis". Joint work with Nikolaos Panagiotou and prof. Gunopulos.
August 2019 Attended the KDD conference in Archorage, Alaska and presented our work about "Characterizing Infant Mortality Prediction" at the Applied Data Science for Healthcare workshop, as part of the KDD Health Day.
June 2019 Excited to start a research internship at Tech Research in Spotify London with Mounia Lalmas as my mentor! 🎧





Publications

Also, my LinkedIn, Google Scholar and DBLP profiles.


2021

Conferences/Workshops

Saravanou A., Tomasi F., Mehrotra R. and Lalmas M., "Multi-Task Learning of Graph-based Inductive Representations of Music Content", International Society for Music Information Retrieval Conference (ISMIR) [paper][blog post]

Panagiotou N., Saravanou A., and Gunopulos D., "News Monitor: A Framework for Exploring News in Real-Time", MDPI DATA Journal [paper]

Saravanou A., Panagiotou N., and Gunopulos D., "News Monitor: A Framework for Quering News in Real-Time", ECIR 2021 (Virtual) [paper][presentation][demo]


2020

Ph.D. Thesis

Anomaly Detection on Temporal Data with Applications to Social Networks and Healthcare
Supervisor: Prof. Gunopulos D. [read online]

Conferences/Workshops

Saravanou A., Noelke C., Huntington N., Acevedo-Garcia D. and Gunopulos D., "Predicting Infant Mortality", Data Mining and Knowledge Discovery (Journal) [paper]

Saravanou A., Stefanoni G., and Meij E., "Identifying Notable News Stories", ECIR 2020 (Virtual) [paper][video]


2019

Conferences/Workshops

Saravanou A., Noelke C., Huntington N., Acevedo-Garcia D. and Gunopulos D., "Infant Mortality Prediction using Birth Certificate Data", KDD Health Day 2019 (Anchorage, Alaska) [paper][code]


2018

Conferences/Workshops

Saravanou A., Katakis I., Valkanas G., and Gunopulos D., "Detection and Delineation of Events and Sub-Events in Social Networks", ICDE 2018 (Paris, France) [paper][poster][code]


2017

Conferences/Workshops

Saravanou A., Katakis I., Valkanas G., Kalogeraki V., and Gunopulos D., "Revealing the Hidden Links in Content Networks: An Application to Event Discovery", ACM CIKM 2017 (Pan Pacific Singapore) [paper][poster][code]

Saravanou A. and Gunopulos D., "Event Detection in Social Networks", SIAM SDM Doctoral Forum 2017 (Houston, TX, USA) [poster]


2016

Summer School

Saravanou A. and Gunopulos D., "Event Detection on Social Media Streams", MLSS Machine Learning Summer School 2016 (Cadiz, Spain) [poster]


2015

Conferences/Workshops

Saravanou A., Valkanas G., Gunopulos D., and Andrienko G., "Twitter Floods when it Rains: A Case Study of the UK Floods in early 2014", WWW, SWDM'15 Workshop, (Florence, Italy) [paper] [slides]


Magazines

Steenhoek S., Adrienko G., Adrienko N., Katakis I., Saravanou A., Valkanas G., Gunopulos D., Fuchs G., and Stange H., “Stürme und Hochwasser in Social Media”, Crisis Prevention, 11-2015


2014

Conferences/Workshops

Valkanas G., Saravanou A., and Gunopulos D., "A Faceted Crawler for the Twitter Service", WISE 2014 [paper] [poster]


M.Sc. Thesis

Data Mining on Social Media to Detect Events and Disasters
Supervisor: Prof. Gunopulos D.

Also, appeared in: Selected Theses of Bachelor and Master Students (UoA, 2015) (in english), p. 101-116 [book]


2012

B.Sc. Thesis

Product Review Summarization
Supervisor: Prof. Gunopulos D.

Also, appeared in: Selected Theses of Bachelor and Master Students (UoA, 2013) (in greek), p. 59-73 [book]







Projects

Ongoing Projects

Music Recommendations using Multi-Task Learning for Node Representations
Work done while I was a research intern at Personalization team at Spotify Tech Research. More details to be added soon, as this work is currently under review.

Node Representation Learning using Self-Supervision
This project started while I was doing a research visit at the Geometric Computing Group advised by prof. Guibas at Stanford University. This project is ongoing, stay tuned to learn more about our work!


Past Projects

Infant Mortality Prediction
This work was done in collaboration with the Heller School for Social Policy and Management (Brandeis University). We apply several machine learning models in data extracted from birth certificates to show how well they can perform at the infant mortality prediction problem. We focus on socio-economic factors, and show that they can improve the overall performance of the prediction task, while not requiring data from future visits to the doctor. We presented part of this project during the KDD Health Day 2019 [paper][code]. The work has now been accepted in the Data Mining and Knowledge Discovery journal. Journal paper, code and data will be published here soon! (update: Dec. 2020)

News Monitor: A Framework for News Monitoring and Analysis
This work is part of our efforts at the KDDLab to build a News Monitoring system that collects news articles from several RSS feeds and combines them with related posts from social networks. The system then analyzes the data and performs a set of tasks, such as: first story detection, opinion mining, knowledge base construction, and question answering. Paper, videos, code and demo will be published here soon! (update: Dec. 2020)

Ranking Notable News using Knowledge Graph Stuctures
This projest is part of the work I did while I was a research intern at the Graph Analytics team of Bloomberg AI in London, advised by Edgar Meij and Giorgio Stefanoni. We show how the structured representations of news stories can be used to rank them based on their notability, and we use a crowdsourcing task to obtain golden truth labels. This work is published in ECIR 2020 [paper][video], and was also presented in the MEDIATE workshop, ICWSM 2020 [video].

Sub-Event Detection in Content Graphs
In this project, we propose to detect events in a Content Graph, and we summarize each of them in a timeline of highlights. We are one of the first ones to define the sub-event detection problem, and we conduct an evaluation on a manually annotated dataset from Twitter that contains football games from Premier League. This work is published in ICDE 2018 [paper] [code].

Event Detection in Social Networks
In this project, we define a Content Network, we show how to reveal hidden links in this graph and we use this structure to detect events. We show how our method can also be used in an event ranking setup. We evaluate our method using other baselines and the state-of-the-art in a Twitter dataset that we have manually annotated. In addition to the above, this method has applications in trend detection on co-authorship and product-review graphs. This work is published in CIKM 2017 [paper] [code].







Teaching

I have served as a teaching assistant in the following courses. For the majority of them, I was responsible for designing the student assignments/projects, leading the labs, holding office hours, grading the paperwork and examining the students.


Graduate Courses

Mining Big Datasets (Fall 2015, 2016, 2017, 2018, 2019, 2020)


Under-graduate Courses

Data Mining (Spring 2012, 2013, 2014, 2015, 2016, 2017, 2018)

Database Systems Implementation (Fall 2013, 2014, 2015, & 2020)

Design of Data Systems (Spring 2015, 2016, 2017)

Software Development (Fall 2014)

Software Engineering (Spring 2013)

Artificial Intelligence (Fall 2012, 2013)

Human-Computer Interaction (Fall 2011)