This week I'm attending #ICLR2024 in Vienna 🇦🇹!
Would love to discuss about IR/recsys/fairness/evaluation, or a mix of those 😄

Skimming 'MagnusHammer: A Transformer-Based Approach to Premise Selection'

Amazing how similar it looks to a Ads/RecSys/Search/RAG stack. arxiv.org/pdf/2303.04488

Solving math and ads click prediction may not be unrelated problems.

The Able Archer war scare of 1983 is an important & much-debated episode. A new article drawing on KGB communications with Eastern Bloc services. It argues the scare was really an 'ongoing bureaucratic scramble within the KGB’s First Chief Directorate'
tandfonline.com/doi/full/10.10…

When I read papers that use LLMs for tasks like IR or RecSys, I always have the data pollution question: we can't guarantee that our evaluation data hasn't been used for training. For example, Lllama 3 confesses that it has been trained on both MSMARCO and TREC DL datasets.

📢📢 #recsys for good at #acmtors 🧑‍🏫 👇👇

We finally have an answer to why EC would be investigating consent-or-pay under the DSA! Answer: Article 38, which requires a RecSys (apparently includes ad targeting despite DSA using term '[ads] systems' alongside) alternative w/o profiling. Martin Husovec Fernando Hortal Foronda

Excellent closing of ECIR2024. Great tutorial on Transformers for RecSys by Craig Macdonald and Aleksandr V. Petrov. Thank you guys!

Had the pleasure of sharing about fairness evaluation in #recsys at today's DIKU Bits DIKU - Department of Computer Science, UCPH. Thanks for having me! Appreciated the interesting questions and discussions with the audience 😊

📷: Qiuchi

🚀 We have drafted a survey on the Self-Supervised Learning for Recommendation!

✨ Over 170 papers covering Contrastive, Generative, and Adversarial Learning in RecSys have been surveyed.

Paper: arxiv.org/abs/2404.03354
Repo: github.com/HKUDS/Awesome-…

Welcome to contribute! 🤗

🏅Recommender Systems' Primers • recsys.aman.ai

🔹Candidate Generation & Retrieval
🔹Candidate Ranking & Re-ranking
🔹Cold Start Problem
🔹Position Bias
🔹Content Moderation
🔹Evaluation Metrics and Loss
🔹Multi-Armed Bandits
🔹GNNs for RecSys
🔹Transformers for RecSys

The European Medicine Agency was aware that in rats a biodistribution beyond the injection site was occurring and that it was involving “most (selected) tissues”.
tandfonline.com/doi/full/10.10…

RecSys Challenge 2024 started?The task is News Recommendation.Seems interesting but I am not sure it is worth to do as last year was not good,wait for one month to see.

if you're not doing cloud-native development on Modal for a Weaviate • vector database vector DB-backed, Hugging Face embeddings-based recsys app while riding in the back of a Waymo, are you really living in 2024?

Two excellent updates:

ICTIR'24 is open for registration and will have it's own banquet! 🎉🍽️
ictir2024.org/attending/regi…

We are proud to announce our keynote speaker:
Minmin Chen

Minmin is a principal research scientist at Google Deepmind and leading figure in RL for RecSys.

📢 Excited to release PyG (PyTorch Geometric) v2.5, including distributed training, a dedicated graph tensor representation, RecSys support, PyTorch 2.2 and native compilation support 🎉

Release Notes 👇
github.com/pyg-team/pytor…

🧵 A thread [1/6]

My understanding of why item-knn remains a strong baseline for most recsys tasks.

RecSys Challenge 2024の評価指標、いろんな指標をごちゃまぜにした平均らしい。AUCとかnDCGとかだけじゃなくてserendipityとかcoverageとか入っててもうよく分からんな。
指標が複雑かつ曖昧で既に不穏な空気が…

📢We will be hosting the 1st EARL workshop on Evaluating and Applying Recommendation Systems with LLMs ( #earlworkshop ), in Recsys.com 2024! EARL explores LLMs in RSs, focusing on enhancements and challenges.
More info later: earl-workshop.github.io
⭐️ Stay Tuned!
#NLP #LLMs #AI

Our paper 'Formalizing Multimedia Recommendation through Multimodal Deep Learning' is now accepted in ACM Transactions on Recommender Systems (ACM TORS) 😍🚀
We survey, formalize, benchmark, and outline open questions in #multimodal #recsys ! A work w/ Claudio Pomo Giandomenico Cornacchia Felice Antonio Merra Tommaso Di Noia Eugenio Di Sciascio