#MLSS2020 made me realize how far I’ve got from my optimization/OR/and in general theoretical background, and how interesting these topics are for me! I’m planning to get back to my math roots thanks to the amazing talks in the summer school!

Such a nice experience! Hope to see all these great people in person!

Data is/are

Programming: 10% writing code. 90% figuring out why it doesn’t work Analyzing data and ML: 1% writing code. 9% figuring out why code doesn’t work. 90% figuring out what’s wrong with the data

How to make steady progress in my research? I worked so damn hard but "IT JUST DOESN'T WORK!"😤 How can I unblock myself quickly and make good progress toward the goals? Below I compiled a list of tips that I found useful. 👇

With some delay, I'm happy to announce that our paper "QActor: Active Learning on Noisy Labels" is accepted to ACML 2021! proceedings.mlr.press/v157/younesian… In this paper, we introduce an active learning-based method to relabel data with noisy labels in an efficient manner.

I want to talk about burnout. A brief 🧵... I was well aware I was burnt out in the fall, but it's hard to fully appreciate the impact of burnout in the moment. After 2 weeks of vacation and a month of aggressively blocking daily focus time, the impact has become more clear:

*Present Failures* ❌ "It doesn't work." ✅ "Here is HOW it fails. I feed X but somehow did not get Y. I believe the core issues lie in steps Z and W. I have ruled out W as the cause. Next, I will design experiments to isolate the step Z."

Wanna work at the most exciting boundary in modern AI (combine machine learning and symbolic reasoning), and use it to improve drug safety for kidney patients, in a leading AI team, jointly with medical researchers? Apply for our PhD vacancy before 1 Sep! werkenbij.vu.nl/ad/phd-positio…

An interesting keynote by Mihaela van der Schaar Mihaela van der Schaar on interpretability and personalized explanations in UAI 2022! #UAI2022

SHAP, LIME, PFI, ... you can interpret ML models with many different methods. It's all fun and games until two methods disagree. What if LIME says X1 has a positive contribution, SHAP says negative? A thread about the disagreement problem, and how to approach it:

Great news! Our hybrid workshop on Neurosymbolic Generative Models was accepted at ICLR 2023🎉🎉🎉 More details on nesygems.github.io

I'm at #NeurIPS2023 for the first time! With my collaborators, we'll be presenting 🕵️CQD-A: A data efficient method for answering knowledge graph queries arxiv.org/abs/2301.12313 🍇 GRAPES: Scaling GNN training with GFlowNets arxiv.org/abs/2310.03399 Feel free to reach out!

Attending #NeurIPS2023 this week? Interested in neurosymbolic reasoning or scaling GNNs to large graphs? Then, you might want to drop by our posters to learn about ⚡️ A-NESI and 🍇 GRAPES (Graph Learning Frontiers workshop) 1/4

#GeMSS was a great experience! I learned a lot about Generative AI and met really cool people. Don't miss it next year!

Struggling with scaling RGCNs on large knowledge graphs? Check out "ReWise: A Relation-Wise Sampling Framework" by Taraneh Younesian, Peter Bloem (@[email protected]), and Stefan Schlobach from Vrije Universiteit Amsterdam (inactief) now live at #SemanticsConf! Discover this game-changing approach for efficient RGCN training!