Sayan Ranu
@SayanRanu
Followers
741
Following
656
Media
40
Statuses
209
Associate Professor in CS@IIT Delhi. Interested in Machine learning for graphs. Hobbies: Cricket, fitness, Traveling.
New Delhi, India
Joined July 2022
Advice for PhD applicants : who you work with matters way more than what you work on. (For some reason - this aspect doesn't get talked about much). When choosing a PI - Prestige matters. Field matters. But fit matters even more. And don’t just look at fit with your PI - try
22
66
913
Our work “GNNXemplar: Exemplars to Explanations – Natural Language Rules for Global GNN Interpretability” is accepted as an oral at @NeurIPSConf. Exemplar-based + LLM-driven rules → scalable, faithful, human-readable GNN explanations. 📄 https://t.co/ocr04HyWmY
@cseiitd
0
2
16
Rejecting papers in #AI Conferences because of "resource constraints" is shooting ourselves in the foot as a community; use Findings.. #SundayHarangue By now, we have all know that top AI conferences are oversubscribed (in terms of paper submissions), and have heard that that
8
8
81
The rebuttal process @NeurIPSConf was too collegial and productive, so a bunch of papers whose process ended on a positive note will be rejected.
2
10
127
@icmlconf @pcastr @neuro_kim @kevinmiller10 @SayanRanu GRAIL: Graph Edit Distance and Node Alignment using LLM-Generated Code . See you at poster East Exhibition Hall A-B #E-1701, Tue 15 Jul 11 a.m. PDT — 1:30 p.m. PDT https://t.co/28aLtTXQK1 (4|5)
1
1
4
We are conducting a survey as part of an ongoing project on the explainability of GNNs. We aim to explore which form of explanation—textual descriptions or visual subgraphs—is more intuitive from the perspective of non-experts. Please participate! https://t.co/BXUeEUwHJa
docs.google.com
👋🏼 Thank you for participating in this study on the explainability of Graph Neural Networks (GNNs)! In this study, you will explore how a trained GNN classifies nodes into particular classes. For...
0
1
7
Excited to attend @iclr_conf ! We'll present 3 works. 1. Graph Condensation ( https://t.co/CSXe9mNVYQ). 2. Algorithm discovery ( https://t.co/61aHSFJdXt) at DL4C workshop 3. Fusing GNN models ( https://t.co/FDXOMRP33x) at Neural Network Weights workshop. #ICLR25
arxiv.org
Model merging has gained prominence in machine learning as a method to integrate multiple trained models into a single model without accessing the original training data. While existing approaches...
0
1
31
🚀 Excited to host the @Indiaacm Summer School 2025 on AI for Social Good at IIT Gandhinagar @iitgn (June 2–13)! Website: https://t.co/ed3SdS4g1j 🌍 Focus: AI for Healthcare, Sustainability, & Agriculture 🎤 Keynotes: @ManishGuptaMG1 (Google DeepMind India) & @VNPadmanabhan
1
5
44
Oooooh. A rebuttal acknowledgment! I feel so special! Someone clicked a button!
4
6
169
Tonight we celebrate Dr. @sahim1992! Super proud to witness your journey from student to scholar. The world is ready for your brilliance!
1
2
23
Bonsai will appear at @iclr_conf! Most works on graph condensation are a "scam." What's the point if condensation requires full dataset training anyway? Bonsai provides the much-needed course correction! PDF & Code: https://t.co/cKPSOiBFD6
@500kmph @haribamsuri #ICLR2025
openreview.net
Graph condensation has emerged as a promising avenue to enable scalable training of GNNs by compressing the training dataset while preserving essential graph characteristics. Our study uncovers...
Graph distillation compresses massive graph datasets into tiny versions that train GNNs as effectively as the original. But current methods have a huge problem.. They require training on the full data first—which defeats the whole purpose! Enter Bonsai( https://t.co/holnYG4SVq)
2
3
22
Honored and humbled to receive the ACM India Early Career Researcher (ECR) 2024 Award, Honorable Mention.
🎉 ACM India ECR Award 2024 🏆 Winner: Dr. Arkaprava Basu (IISc) for breakthroughs in memory management for GPUs/CPUs. 🎖️ Honorable Mention: Dr. Sayan Ranu (IIT Delhi) for pioneering graph ML applications. 💡 Recognizing early-career innovators in computing! 👏 Congrats!
5
0
64
Excited to announce that FUGAL (Feature-fortified Unrestricted Graph Alignment) will be presented at @NeurIPSConf today! 📍 West Ballroom A-D, Booth #5900 🗓️ Dec 11th, 4:30 p.m. PST — 7:30 p.m. Let's chat if you're at NeurIPS! 💬 @VNSAditya2002 @DavideMottin
#NeurIPS2024
0
2
16
Excited to share that our work on explaining GNNs is being presented at @NeurIPSConf today! Catch us at: 🗓️ When: 11 a.m. - 2 p.m. PST 📍 Where: East Exhibit Hall A-C, Booth #3107 Come by to chat! 💬 with @sourav_medya @Armagaan7 @ManthanDalmia
#NeurIPS2024
2
1
18
The LoG New Delhi meetup is under way at IT Delhi @YardiScAI - amazing venue and organisation! #LoGNewDelhi @LogConference
1
6
24
@iclr_conf All ICLR AC/SAC/Chairs: Please ignore all reviews and scores with no response after author rebuttals.
0
3
23