Taraneh Younesian

PhD researcher @vuamsterdam | Machine Learning | Knowledge Graphs

[Taraneh Younesian @TYounesian]

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:

[Emile van Krieken @EmilevanKrieken]

#2
🍇 GRAPES: At Tuesday's ELLIS Unconference poster session.
We study adaptive graph sampling for scaling GNNs!

Work with @TYounesian, @danieldazac, @ThiviyanSingam, @pbloemesquire
https://t.co/5vaqGfhnEl

[Taraneh Younesian @TYounesian]

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:

[Taraneh Younesian @TYounesian]

Link to the paper: https://t.co/P8ZOntDwUM
Collaboration with @danieldazac, @EmilevanKrieken,@ThiviyanSingam, @pbloemesquire

[Taraneh Younesian @TYounesian]

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:

[Taraneh Younesian @TYounesian]

🍇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.

[SEMANTiCS Conference @SemanticsConf]

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!

[Taraneh Younesian @TYounesian]

This work was done together with @pbloemesquire and Stefan Schlobach.

[Taraneh Younesian @TYounesian]

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: https://t.co/ZkfNXTf3Ng

[Taraneh Younesian @TYounesian]

#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 @jesfrellsen]

This year, the fabulous @jmtomczak gave the closing remarks for our second #GenAI summer school (https://t.co/YPpyaiQrpT) and revealed that we are brining GeMSS to home of the fantastic @pamattei in Nice in 2025!

#GeMSS

[Thiviyan Thanapalasingam @ThiviyanSingam]

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

[Taraneh Younesian @TYounesian]

Work done by me, @ThiviyanSingam, @EmilevanKrieken, @danieldazac, and @pbloemesquire.

[Taraneh Younesian @TYounesian]

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: https://t.co/S7vQOXT5eJ

[Daniel Daza @danieldazac]

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 https://t.co/FudDaZ2hAP
🍇 GRAPES: Scaling GNN training with GFlowNets
https://t.co/qnwHTqxKfv

Feel free to reach out!

[Thiviyan Thanapalasingam @ThiviyanSingam]

Great news! Our hybrid workshop on Neurosymbolic Generative Models was accepted at ICLR 2023🎉🎉🎉

More details on https://t.co/mIf3jm7swD

[Christoph Molnar 🦋 christophmolnar.bsky.social @ChristophMolnar]

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:

[Taraneh Younesian @TYounesian]

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

[uai2026 @UncertaintyInAI]

The afternoon session started with Mihaela's keynote on "New frontiers in machine learning interpretability". Thanks for the inspiring talk!

[Frank van Harmelen @FrankVanHarmele]

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! https://t.co/xTT5GTmOja

[Jia-Bin Huang @jbhuang0604]

*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."

[Taraneh Younesian @TYounesian]

@MShahbazi_ Many congrats Mohammad!

[Jenn Wortman Vaughan @jennwvaughan]

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: