Abstract. Many recommender-system datasets are pruned, i.e. some data is removed that wouldn’t be removed in a production recommender-system. For instance, the MovieLens dataset contains only data from users who rated 20 or more movies.1 Similarly, some researchers prune data themselves and conduct their experiments only on subsets of the Read more…
I spent the past two weeks at the National Institute of Informatics (NII) in Tokyo, where I am a visiting professor. As always, being in Tokyo was a great experience both on a personal and a professional level. NII is an amazing meeting place for national and international researchers. I Read more…
Update 2019-08-12: Some numbers presented in this post were incorrect, and we updated them. For the latest full analysis, please refer to extended pre-print of Data Pruning in Recommender Systems Research: Best Practice or Malpractice? Datasets are a key ingredient to successful research in the field of recommender systems and Read more…
This is the pre-print of our upcoming publication at the 13th ACM Conference on Recommender Systems (RecSys’19). Joeran Beel, Alan Griffin, and Conor O’Shea. 2019. Darwin & Goliath: A White-Label Recommender-System As-a-Service with Automated Algorithm-Selection. In Proceedings of the 13th ACM Conference on Recommender Systems (RecSys’19). ACM, New York, NY, Read more…
I am delighted to announce that I was invited to join the editorial board of the International Journal on Digital Libraries (IJDL). I will focus on submissions relating to information retrieval, recommender systems and machine learning in the field of digital libraries. The International Journal on Digital Libraries is a Read more…
Four of our poster and demo submissions got accepted for presentation at the 13th ACM Recommender Systems Conference (RecSys 2019) in Copenhagen in September. The accepted submissions are as follows (pre-prints will follow soon): Darwin & Goliath: A White-Label Recommender-System As-a-Service with Automated Algorithm-Selection Joeran Beel, Alan Griffin, Conor O’Shea Read more…
Update 2019-08-14 DAAD published a new website for the IFI programme: www.daad.de/ifi I was invited to join the scientific advisory board for the new IFI programme of the German Academic Exchange Service (Deutscher Akademischer Austauschdienst – DAAD). The IFI programme (German: “Internationale Forschungsaufenthalte für Informatiker_Innen”) is the successor of the Read more…
We are delighted to announce a seminar by Prof Theja Tulabandhula from the University of Illinois Chicago. The seminar will start at 10:00 am, Tuesday, 25 of June 2019 in the Small Conference Room in the O’Reilly Institute at Trinity College Dublin. Theja is visiting our lab and presents his Read more…
Trinity College Dublin has a new website and we are honored that our research about recommender-systems is featured as one of six research projects on TCD’s research page in the #researchMATTERS section.
A few months ago, we — Alan Griffin, Conor O’Shea, and I — started the private beta of our recommender-system as-a-service Darwin & Goliath. Now, we made it to the final round (10 start-ups) of The Ireland Funds Business Plan Competition, organized by NDRC. We are looking forward to a Read more…
I have been invited to give a talk at the LibTech Workshop at the 48th Annual LIBER Conference. The Library of Trinity College Dublin (TCD) has been cultivating an open innovation research model in partnership with a number of Trinity research centres. The ADAPT Centre and the Library are pleased Read more…
Google integrated our implementation of a Neural Turing Machine (NTM) into its official TensorFlow release 1.14.0. The implementation is based on the work of our student Mark Collier. The work was previously published at the 27th International Conference on Artificial Neural Networks Conference ICANN and received the best-paper award. Neural Read more…
The International Journal on Digital Libraries (IJDL) published our manuscript “Choice Overload and Recommendation Effectiveness in Related-Article Recommendations: Analyzing the Sowiport Digital Library”. The paper is freely available as open access via Springer. The paper is an extended version of a previous paper published at the 5th International Workshop on Read more…
Please note, this is a continuous program until 2022, with student intakes in September every year (and potentially in March). Hence, please feel free to apply at any time, or if the application page is currently closed, wait for a few weeks until applications are open again. If you have Read more…
Victor will be with us from the 1st of May to the end of July 2019. He’s a French Master’s student from the engineering school Polytech Clermont-Ferrand, which is attached to the university Clermont Auvergne. Victor studies Mathematics and Computer Science in the department of mathematics and modelling. Victor chooses Read more…
AMIR 2019 — The 1st Interdisciplinary Workshop on Algorithm Selection and Meta-Learning in Information Retrieval — is over, and it was a full success. We had many interesting presentations and around 20 attendees. The following photos give some impressions.
Update: Read the full manuscript, which was presented at the AutoML workshop, here. Introduction There is an ever-growing number of tools for automating the machine learning pipeline, both commercial and open source. Auto-sklearn [11, 15], Auto Weka [14], ML-Plan [18], and H2O.ai are only some examples. In addition, the auto* Read more…
The school of computer science and statistics appointed me as the Strand Lead for the Intelligent Systems Programme in the MSc in Computer Science course at Trinity College Dublin. I am looking forward to continuing to develop the programme and ensuring the highest quality in teaching, liaising with student representatives, Read more…
The ELITE-S initiative organizes a breakfast seminar to bring together potential applicants and supervisors. Every postdoctoral researcher, who is interested in standardization in the field of recommender systems, machine learning, and artificial intelligence, is sincerely invited to join the breakfast. During the seminar, you will learn more about the 2-year Read more…
I am not usually writing in this blog about my experience with software, but today I make an exception to prevent others from making the same bad experience that I had with Google File Stream, the enterprise version of Google Drive / GDrive. My research group is using Google File Read more…
Aicha is a PhD student of Computer Science at the University of Laghouat in Algeria. She arrives today and will work with us for 1.5 years. Aicha’s research interests include machine learning, natural language processing, and recommender systems. Aicha’s PhD topic is analyzing user engagement behaviour in online social networks Read more…
Ian will be joining us for 6 months starting today. Ian is currently enrolled as a master’s student of Computer and Information Science at the University of Konstanz in the south of Germany. Ian’s research interests include machine learning, natural language processing, information retrieval and recommender systems. Ian is currently Read more…
Update: Deadline extended to July 15th, 2019. ELITE-S provides up to 16 postdoctoral fellowships to work for 2 years in the ADAPT Research Centre at Trinity College Dublin, University College Dublin, or other Irish universities as well as with an industry partner. ELITE-S is a EU Marie Skłodowska-Curie COFUND Action. Read more…
The first beta version of Mr. DLib V2 has been released and is performing very well so far. With our partner JabRef, we have delivered over 70 thousand sets of recommendations (approximately 1,000 per day), or a total of over 450,000 individual recommendations. We have a click through rate (CTR) Read more…
Our lab is glad to welcome Hebatallah Mohamed as a visiting PhD student for three months. Hebatallah is a PhD student at the Department of Computer Science at the University of Roma Tre in Italy. In Rome, she is doing her PhD under the supervision of Prof. Alessandro Micarelli in Read more…