Today I started my research internship in Redmond with the Microsoft Microsoft Gray Systems Lab. Looking forward to an amazing summer!

How fast can we unlearn data from recommendation models for the #righttobeforgotten? We unlearn interactions from kNN models on 1m users & 250m interactions with sub-second latency in our upcoming short paper SIGIR 2024 dl.acm.org/doi/10.1145/35… Joint work w/ Mozhdeh Ariannezhad Maarten de Rijke

Awesome paper by xiaozhong lyu Stefan Grafberger @ce__zhang Sebastian shows how #RAG can be improved through data importance learning. The approach learns weights for data sources based on their performance on a validation set and then re-weights or prunes the corpus. 1/3

This is heart breaking: a detroit woman has been jailed while 8 months pregnant after false AI facial recognition. democracynow.org/2023/8/9/porch…

Going to VLDB 2025 🇬🇧 ? Don't miss our demo on "mlwhatif: What If You Could Stop Re-Implementing Your Machine Learning Pipeline Analyses Over and Over?" Joint work with Stefan Grafberger and Shubha vldb.org/pvldb/vol16/p4…

Checkout our vision on "Red Onions, Soft Cheese and Data: From Food Safety to Data Traceability for Responsible AI" sites.computer.org/debull/A24mar/… We ask what reponsible data management can learn from the existing regulations and processes for food safety (w/ Stefan Grafberger & Ce Zhang)

Joint work with Stefan Grafberger Zhang Zeyu and Ce Zhang !

Our paper "Towards Interactively Improving ML Data Preparation Code via 'Shadow Pipelines'" has been accepted for the DEEM Workshop @ SIGMOD at SIGMOD! 🎉 In this vision paper, we present our initial ideas for my next research project. Joint work with Sebastian and Paul Groth.

LLMs show a huge potential for data wrangling. But how we can we increase their parameter-, compute- and sample efficiency for real-world use cases? Zhang Zeyu will present our ideas for this at the DBML workshop at #icde2024 IEEE ICDE Conference today! wis.ewi.tudelft.nl/assets/files/d…

Session-based recommendation with low-latency prediction times for millions of products is a challenging problem in e-commerce Barrie Kersbergen from bol will detail our work on finding cost-efficient deployment options for this scenario at #icde2024 today github.com/bkersbergen/et…

To PhD students attending #icde2024: I am looking for a **postdoc** to join my upcoming research group at bifold.berlin Ping me if you are interested to move to Berlin to work on problems at the intersection of data management and ML and help to build up the group.

We can't wait for DEEM Workshop @ SIGMOD 2024 to get started @sigmodconf! Join us tomorrow Sunday 9 June from 9am in the Tupungato room!! Check out the full program at: deem-workshop.github.io 🇨🇱

Looking forward to presenting our vision "Towards Interactively Improving ML Data Preparation Code via 'Shadow Pipelines'" at the DEEM Workshop @ SIGMOD today! The talk will be around 10:40 a.m. in the Tupungato room. stefan-grafberger.com/shadow-pipelin…

📢Im hiring a PhD researcher!🚀 Interested in representation and generative learning for tables & DBs to make insights from structured data accessible? Come do a PhD @cwinl in beautiful Amsterdam! ⏰ Apply 21 July '24 📅 Start Fall '24 🔗 cwi.nl/en/jobs/vacanc… Please share🙏

Life update: After three amazing years in Amsterdam, I moved to Berlin to finish my PhD with Sebastian at BIFOLD. Very excited to join the data management community in Berlin!

Pls RT: We have a PhD opening on "Responsible Data Engineering for ML" in Berlin! Join the newly founded DEEM Lab at BIFOLD and TU Berlin to work on making AI/ML applications easier to build and ensuring that they adhere to laws and regulations. deem.berlin/#jobs-33124

Pls RT: We have a PhD opening in Berlin on "Enforcing the Right-to-Be-Forgotten in Recommender Systems", co-supervised by Maarten de Rijke from Amsterdam. Join the newly founded DEEM Lab at BIFOLD to work on giving users back the control over their data. deem.berlin/#jobs-30424

📢 Excited to share Feature Clock, an open-source library and paper accepted at IEEE VIS! Feature Clock enhances the explainability and compactness of visualizations of high-dimensional effects in two-dimensional plots. Big thanks to my co-authors Valentina Boeva and Rita Sevastjanova!

Next week, Stefan Grafberger and me will be in China for VLDB 2024 to present various contributions from the DEEM Lab at BIFOLD. Looking forward to meeting lots of people in person again! (1/6)