Here it is: the first Learning on Graphs Conference! 🎊 We think this new venue will be valuable for the Graph/Geometric Machine Learning community. What makes it so important+unique? See our blog post! michael-bronstein.medium.com/announcing-the… 1/6

Simple is beautiful. Simple is memorable. Simple is impactful 🤩 Reviews rejecting solely due to model simplicity send the absolutely wrong message. They force students to build unnecessarily complex solutions, even when novel yet "simple" solutions work. Please don't do this 🙏

💔

🎉Our paper selected for spotlight talk at the #NeurIPS2022 Temporal Graph Learning workshop! Congratulations to Kartik Sharma Rohit Sridhar Rakshit Trivedi 👏 Paper: Imperceptible Adversarial Attacks on Discrete-Time Dynamic Graph Models PDF coming soon

(1/n) Excited to share 2 papers that will appear at #AAAI23. 1. Sahil Manchanda and Sayan Ranu, "LIMIP: Lifelong Learning to solve Mixed Integer Programs" 2. Kartik Sharma, Samidha Verma, Sourav Medya, Arnab Bhattacharya and Sayan Ranu,"Task and Model Agnostic Adversarial Attack on GNNs"

📢 New paper and resource: A Survey of Graph Neural Networks for Social Recommender Systems Paper: arxiv.org/abs/2212.04481 GitHub repo: github.com/claws-lab/awes… We surveyed 80+ papers on GNNs for social recommendations, which is of high interest from the community!

These days, many people are interested in getting a PhD in ML. I think you should think really hard before committing to a PhD program in ML. Why? I'm going to summarize some thoughts in this thread: 1/10

One presentation at #AAAI2023 is a paper by our own Kartik Sharma. As part of his undergrad thesis, Sharma presents TANDIS, an algorithm that can defend graph neural networks from adversarial attacks by distorting node neighborhoods. Check it out here: arxiv.org/abs/2112.13267

Listen to my PhD student Kartik Sharma present #KDD2023 paper on Attacks on Dynamic Graph Neural Networks #GNNs Talk at 11:00am PT in Robust ML track. Paper: dl.acm.org/doi/10.1145/35… Code: github.com/claws-lab/TDAP Video: youtube.com/watch?v=CDbh1C…

📣New paper: "Representation Learning in Continuous-Time Dynamic Signed Networks" at ACM CIKM 2023! dl.acm.org/doi/pdf/10.114… Code: github.com/claws-lab/semba Kartik Sharma and Mohit presented the paper this week! GaTech CSE

I’ll be at #ACL2024NLP 🇹🇭 in person and can’t wait to catch up with old friends and meet new ones! 🙂 I am presenting two papers: ➡️ Investigating the role of cross-modal projection in multimodal LLMs ➡️ A community-centric study on violence-provoking speech A short 🧵 (1/5)

💡Do LLMs consider the speaker's ethnicity⁉️ Our paper which will be presented (orally) at the #NeurIPS2024 SafeGenAI workshop, investigates whether LLMs cater to certain ethnicities while classifying hate. link: arxiv.org/pdf/2410.20490 w: Kartik Sharma lynnette ng Shaily (1/5)

Personalized Layer Selection for Graph Neural Networks Kartik Sharma, Vineeth Rakesh, Yingtong Dou, Srijan Kumar, Mahashweta Das. Action editor: Sheng Li. openreview.net/forum?id=JyjTJ… #nodes #classify #classification