2021: we can’t reproduce big lab’s research because we don’t have a 1000 GPUs
2022: we can’t reproduce this research because we don’t have a nuclear reactor.
I made an accessibility map of #Neurips2022. The country is marked in red if its resident can not get appointment in time from getting accepted to the conference (76 days).
🚨 Transformer theory alert 🚨
What algorithms can transformers execute efficiently?
Our preprint sheds some light on reasoning capabilities of transformers, now in 𝒓𝒆𝒂𝒍𝒊𝒔𝒕𝒊𝒄 𝒑𝒂𝒓𝒂𝒎𝒆𝒕𝒆𝒓 𝒓𝒆𝒈𝒊𝒎𝒆𝒔.
Paper: arxiv.org/abs/2405.18512
More in thread! 1/8
𝐋𝐞𝐭 𝐘𝐨𝐮𝐫 𝐆𝐫𝐚𝐩𝐡 𝐃𝐨 𝐭𝐡𝐞 𝐓𝐚𝐥𝐤𝐢𝐧𝐠: 𝐄𝐧𝐜𝐨𝐝𝐢𝐧𝐠 𝐒𝐭𝐫𝐮𝐜𝐭𝐮𝐫𝐞𝐝 𝐃𝐚𝐭𝐚 𝐟𝐨𝐫 𝐋𝐋𝐌𝐬
Don't know what to do with your graphs in 2024? Shove them to an LLM, of course, and let LLM figure out what to do!
arxiv.org/abs/2402.05862
Short thread (1/5):
My Ph.D. thesis is published and available online (and in the Bonn library)! It covers two main directions of my work: similarities and embeddings of nodes and graphs. How to do it in the most scalable ways possible? Link below ;)
bonndoc.ulb.uni-bonn.de/xmlui/handle/2…
As promised, a thread on our new paper with @johnpalowitch and @phanein called “Graph Clustering with Graph Neural Networks”. We, uh, show how to cluster graphs with GNNs, and how to do it well with DmON.
Paper: arxiv.org/abs/2006.16904
Code will be available soon™
(1/n)
🚨𝗗𝗼𝗻'𝘁 𝗙𝗼𝗿𝗴𝗲𝘁 𝘁𝗼 𝗖𝗼𝗻𝗻𝗲𝗰𝘁! 🚨
𝗜𝗺𝗽𝗿𝗼𝘃𝗶𝗻𝗴 𝗥𝗔𝗚 𝘄𝗶𝘁𝗵 𝗚𝗿𝗮𝗽𝗵-𝗯𝗮𝘀𝗲𝗱 𝗥𝗲𝗿𝗮𝗻𝗸𝗶𝗻𝗴
We introduce G-RAG, a reranker for RAG based on graph neural networks.
Paper link: arxiv.org/abs/2405.18414
🔥Internship opportunity (fall/summer'23) in the Graph Mining team @ Google! Join us to work on cutting edge research in graph ML 🤖.
🧠Prev interns🧠 published in NeurIPS, KDD, WWW, and more! Referral bonus: one (1) cookie 🍪.
#ml#internship
As promised, a thread on our new paper with @johnpalowitch and @phanein called “Graph Clustering with Graph Neural Networks”. We, uh, show how to cluster graphs with GNNs, and how to do it well with DmON.
Paper: arxiv.org/abs/2006.16904
Code will be available soon™
(1/n)
