Asiri Wijesinghe

ML Researcher | PhD in CS | CSIRO (Data61) | Former Senior Data Scientist

[Asiri Wijesinghe @wokas36]

@MontefioreD @wokisw @BehnazEl @IsuruWijesingh @LeedsCancerRes @UniversityLeeds @LeedsHospitals Great work @wokisw 🎉

[David Sebag (he/him) 🇺🇦💙 @MontefioreD]

2/3 And two more from @BehnazEl and @IsuruWijesingh - excellent posters all!
@LeedsCancerRes @UniversityLeeds @LeedsHospitals #RadConf2023

[Asiri Wijesinghe @wokas36]

@wokisw Awesome 👌

[Isuru Wijesinghe @wokisw]

I’m super excited about presenting my research @RadConf23. The weather is outstanding in Glasgow, and I’m enthusiastic about learning new technologies in radiotherapy and connecting with new people during the upcoming days. #RadConf23 #CRUK #Adaptiveradiotherapy #AI

[Asiri Wijesinghe @wokas36]

We are delighted to inform that our paper entitled "Neighborhood WL Hierarchy of Expressivity for Graph Neural Networks" has been accepted to ICLR 2023 (CORE ranking A*). Many congratulations to all co-authors. #ICLR2023 #GNNs

https://t.co/N2Rvv1VBrb

[Jure Leskovec @jure]

Excited to announce the 2nd edition of OGB-LSC (large-scale graph ML challenge) at NeurIPS 2022, following the success of our last OGB-LSC at the KDD Cup 2021! The competition ends on Nov 1st. Looking forward to your participation! https://t.co/4JHTfjyRuu

[Google DeepMind @GoogleDeepMind]

Join us at the SMILES workshop to hear an exciting lineup of speakers discuss best practices for evaluating ML research, covering reproducibility and rigour, slow vs fast science, and incentives for better evaluation.
https://t.co/EmYrYbaj8M #ICLR2022

[ICLR @iclr_conf]

Thank you all for making #ICLR2022 a huge success! We look forward to seeing you next year in Kigali, Rwanda!

[ICLR @iclr_conf]

Two parallel oral sessions starts in 30minutes: "Learning from distribution shift" and "Meta-learning and adaptation". Do not miss the outstanding paper presentation on "Bootstrapped Meta-Learning".

[ICLR @iclr_conf]

Got a job offer in industry (or maybe not yet)? Join us in the unique #ICLR2022 social on "How to Negotiate Industry Offers in AI". https://t.co/vAhWycMrAw"

[Google DeepMind @GoogleDeepMind]

Congratulations to the team for their #ICLR2022 Outstanding Paper Award. Opening a new direction in meta-learning, “Bootstrapped meta-learning”, proposes an algorithm that enables an agent to learn how to learn by teaching itself: https://t.co/dbXfRLBALg 1/

[ICLR @iclr_conf]

Counting down to the start of #ICLR2022. Join us this coming week for an exciting program of invited talks, latest research insights, socials, workshops and so much more!

[Asiri Wijesinghe @wokas36]

I'm thrilled to share that our ICLR 2022 paper has been selected as an oral presentation. This year ICLR accepted 54 papers out of 3391 submissions for oral presentation. This is my second oral presentation acceptance for a A* conference.

#ICLR2022 #GraphSNN #GNN

[Michael Galkin @michael_galkin]

🎄 A new winter holiday longread - what happened in the Graph ML field in 2021? What to expect in 2022? We reflect upon a dozen of research trends - brought by yours truly, @epsiloncorrect and @SergeyI49013776 (and a surprise cameo appearance in the end)

https://t.co/lbKryKU16B

[Asiri Wijesinghe @wokas36]

Today our paper "A Regularized Wasserstein Framework for Graph Kernels" was presented at ICDM 2021, which resurrects a novel Wasserstein kernel trick on graph structured data.

Paper: https://t.co/UPiXWKi0zY
RWK code: https://t.co/pZtY89kPTL

[Michael Bronstein @mmbronstein]

Over-squashing is a common plight of GNNs occurring when message passing fails to propagate information efficiently on the graph. In a new post, we discuss how this phenomenon can be understood and remedied through the concept of Ricci curvature

https://t.co/sXVWL2Ydok

[Isuru Wijesinghe @wokisw]

RadNet City of London PhD student networking event is happening right now @CRUKCOLcentre #CRUK #RadNet

[Papers with Code @paperswithcode]

🎉 Papers with Code partners with arXiv! Code links are now shown on arXiv articles, and authors can submit code through arXiv. Read more: https://t.co/kO6zhWAWGH

[Thomas Kipf @tkipf]

My PhD thesis "Deep Learning with Graph-Structured Representations" is now available for download: https://t.co/hyz0cnoewZ -- It covers a range of emerging topics in Deep Learning: from graph neural nets (and graph convolutions) to structure discovery (objects, relations, events)

[Emtiyaz Khan @EmtiyazKhan]

I have had an amazing reaction for my NeurIPS tutorial. I thank you all for your encouraging comments. Links to the video and the paper attached below.
https://t.co/GVEczpZo1f
https://t.co/iTyPJgFsN4