@TYounesian

PhD researcher @vuamsterdam | Machine Learning | Knowledge Graphs

 Amsterdam
Joined February 2020
  • Tweets34
  • Following168
  • Followers133
1Media
If you want to reduce the size of your graph while still maintaining an accurate GNN, which nodes should you select? Which nodes are influential in a graph? Check out our TMLR paper, GRAPES, to get your answer:
2
4
2
12
1,907
#2 🍇 GRAPES: At Tuesday's ELLIS Unconference poster session. We study adaptive graph sampling for scaling GNNs! Work with @TYounesian, @danieldazac, @ThiviyanSingam, @pbloemesquire arxiv.org/abs/2310.03399
1
2
5
244
Taraneh Younesian retweeted
Taraneh Younesian@TYounesian23 Jul 2025
If you want to reduce the size of your graph while still maintaining an accurate GNN, which nodes should you select? Which nodes are influential in a graph? Check out our TMLR paper, GRAPES, to get your answer:
2
4
2
12
1,907
🍇GRAPES is a learnable and adaptive graph sampling method. It utilizes GFlowNets and reinforcement learning to learn which nodes to sample adaptively based on the task. We show that adaptive sampling is crucial in heterophilous and multi-label graphs.
1
107
Link to the paper: openreview.net/forum?id=QI0l… Collaboration with @danieldazac, @EmilevanKrieken,@ThiviyanSingam, @pbloemesquire
133
Struggling with scaling RGCNs on large knowledge graphs? Check out "ReWise: A Relation-Wise Sampling Framework" by @TYounesian, @pbloemesquire, and Stefan Schlobach from @VUamsterdam now live at #SemanticsConf! Discover this game-changing approach for efficient RGCN training!
3
5
556
This week, I'm presenting my work "ReWise" at @SemanticsConf. We introduce a graph sampling framework to scale Relational Graph Convolutional Networks to large multimodal knowledge graphs. Check out our paper at: ebooks.iospress.nl/doi/10.32…
1
1
5
272
This work was done together with @pbloemesquire and Stefan Schlobach.
1
65
#GeMSS was a great experience! I learned a lot about Generative AI and met really cool people. Don't miss it next year!
Jes Frellsen@jesfrellsen28 Jun 2024
This year, the fabulous @jmtomczak gave the closing remarks for our second #GenAI summer school (gemss.ai) and revealed that we are brining GeMSS to home of the fantastic @pamattei in Nice in 2025! #GeMSS
12
518
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 (@glfrontiers workshop) 1/4
1
5
19
2,457
If you’re going to #NeurIPS2023, check out our poster GRAPES in GLFrontiers workshop (December 15th)! 🍇 GRAPES is a GFlowNet-based adaptive graph sampling method to scale GNNs to large graphs. Paper: arxiv.org/abs/2310.03399
1
6
16
1,814
Work done by me, @ThiviyanSingam, @EmilevanKrieken, @danieldazac, and @pbloemesquire.
1
94
Taraneh Younesian retweeted
Daniel Daza@danieldazac9 Dec 2023
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!
8
1
36
3,819
Great news! Our hybrid workshop on Neurosymbolic Generative Models was accepted at ICLR 2023🎉🎉🎉 More details on nesygems.github.io/
1
12
3
50
11,344
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:
19
132
11
687
An interesting keynote by Mihaela van der Schaar @MihaelaVDS on interpretability and personalized explanations in UAI 2022! #UAI2022
uai2026@UncertaintyInAI2 Aug 2022
The afternoon session started with Mihaela's keynote on "New frontiers in machine learning interpretability". Thanks for the inspiring talk!
2
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-posit…
12
11
Taraneh Younesian retweeted
Jia-Bin Huang
@jbhuang060411 Jul 2022
*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."
1
9
1
178
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:
8
130
23
903
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/y… In this paper, we introduce an active learning-based method to relabel data with noisy labels in an efficient manner.

QActor: Active Learning on Noisy Labels

Noisy labeled data is more a norm than a rarity for self-generated content that is continuously published on the web and social media from non-experts. Activ...

proceedings.mlr.press
Load more