Shenghao Yang @shenghao_yang
PhD student @UWCheritonCS. Machine learning and optimization over graphs. https://t.co/zUfRiSeMCZ cs.uwaterloo.ca/~s286yang Waterloo, Ontario Joined February 2021-
Tweets48
-
Followers171
-
Following71
-
Likes275
Positional Attention is accepted at ICML 2025! Thanks to all co-authors for the hard work (64 pages). If you’d like to read the paper, check the quoted post. That's a comprehensive study on the expressivity for parallel algorithms, their in- and out-of-distribution learnability,…
Positional Attention is accepted at ICML 2025! Thanks to all co-authors for the hard work (64 pages). If you’d like to read the paper, check the quoted post. That's a comprehensive study on the expressivity for parallel algorithms, their in- and out-of-distribution learnability,…
Our new work Spectral Journey arxiv.org/abs/2502.08794 shows a surprising finding: when a 2-layer Transformer is learned to predict the shortest path of a given graph, 1️⃣it first implicitly computes the spectral embedding for each edge, i.e. eigenvectors of Normalized Graph…
My PhD thesis is now available on UWspace: uwspace.uwaterloo.ca/items/291d10bc…. Thanks to my advisors @kfountou and Aukosh Jagannath for their support throughout my PhD. We introduce a statistical perspective for node classification problems. Brief details are below.
"Energy continuously flows from being concentrated, to becoming dispersed, spread out, wasted and useless." ⚡➡️🌬️ Sharing our work on the inability of softmax in Transformers to _robustly_ learn sharp functions out-of-distribution. Together w/ @cperivol_ @fedzbar & Razvan!
Positional Attention: Out-of-Distribution Generalization and Expressivity for Neural Algorithmic Reasoning We propose calculating the attention weights in Transformers using only fixed positional encodings (referred to as positional attention). These positional encodings remain…
I wrote a blog @Medium on "Random Data and Graph Neural Networks" Link: medium.com/@kimon.fountou… I cover a range of topics: 1. How a single averaging graph convolution changes the mean and variance of the data. 2. How it improves linear classification. 3. How multiple…
For those participating in the Complex Networks in Banking and Finance Workshop, I’ll be presenting our work on Local Graph Clustering with Noisy Labels tomorrow at 9:20 AM EDT at the Fields Institute. Hope to see you there :) arxiv.org/abs/2310.08031
Paper: Analysis of Corrected Graph Convolutions We study the performance of a vanilla graph convolution from which we remove the principal eigenvector to avoid oversmoothing. 1) We perform a spectral analysis for k rounds of corrected graph convolutions, and we provide results…
.@backdeluca is at ICLR and he will present his joint work with @shenghao_yang on "Local Graph Clustering with Noisy Labels". Date: Friday 10th of May. Time: 4:30pm - 6:30pm CEST. Place: Halle B #175.
Emergence in LLMs is a mystery. Emergence in physics is linked to phase transitions. We identify a phase transition between semantic and positional learning in a toy model of dot-product attention. Very excited about this one! arxiv.org/pdf/2402.03902…
The November issue of SIAM News is now available! In this month's edition, @n_veldt finds that even a seemingly minor generalization of the standard #hypergraph cut penalty yields a rich space of theoretical questions and #complexity results. Check it out! sinews.siam.org/Details-Page/g…
Graph Attention Retrospective is live at JMLR jmlr.org/papers/v24/22-…. The revised version has additional results: 1) Beyond perfect node classification, we provide a positive result on graph attention’s robustness against structural noise in the graph. In particular, our…
Graph Attention Retrospective is live at JMLR jmlr.org/papers/v24/22-…. The revised version has additional results: 1) Beyond perfect node classification, we provide a positive result on graph attention’s robustness against structural noise in the graph. In particular, our…
Here's our new work on the optimality of message-passing architectures for node classification on sparse feature-decorated graphs! Thanks to my advisors and co-authors @kfountou and Aukosh Jagannath. Details within the quoted tweet.
Here's our new work on the optimality of message-passing architectures for node classification on sparse feature-decorated graphs! Thanks to my advisors and co-authors @kfountou and Aukosh Jagannath. Details within the quoted tweet.
Alright, I have some important news (at least for me). Now there exists an accelerated personalized PageRank method which is strongly local!! It's running time does not depend on the size of the graph but rather only on the number of nonzeros at uwspace.uwaterloo.ca/handle/10012/1……
SIAM Conference on Applied and Computational Discrete Algorithms (ACDA23) May 31 – June 2, 2023 Seattle, Washington, U.S. New submission due dates: Registering a submission: Jan 16; Paper submission deadline; Jan 23.
SIAM Conference on Applied and Computational Discrete Algorithms (ACDA23), May 31 -- June 2, 2023 siam.org/conferences/cm… Important dates: Short Abstract and Submission Registration: Jan 9, 2023 Papers and Presentations-without-papers: Jan 16, 2023 #SIAMACDA23
Open problem: accelerated methods for l1-regularized PageRank. proceedings.mlr.press/v178/open-prob…
Does it matter where you place the graph convolutions (GCs) in a deep network? How much better is a deep GCN vs an MLP? When are 2 or 3 GCs better than 1 GC? We answer those for node class., and a nonlinearly separable contextual stochastic block model. arxiv.org/pdf/2204.09297….
New video with Prof. @kfountou explaining his paper "Graph Attention Retrospective" is now available! youtu.be/duWVNO8_sDM Check it out to learn what GATs can and cannot learn for node classification in a stochastic block model setting!
Tomorrow's GraphML discussion will be with Prof @kfountou about his paper "Graph Attention Retrospective": arxiv.org/abs/2202.13060 One of the most central topics! Sign up to join on Zoom at 11am EST hannes-stark.com/logag-reading-… With Amit Levi @shenghao_yang @aseemrb Aukosh Jagannath
James Flaherty @JamezzzBuilds
59 Followers 980 Following Quit my 9-5 to build https://t.co/XldtaYxOYM. Scaling to $30K/mo 🎯 Documenting my journey ⚡
Adam @Adammmm12310
109 Followers 6K Following
Sethu Priya @sethu_priya_
133 Followers 6K Following
Mahmud ElHuseyni 🇵... @mahmut_cv
27 Followers 2K Following AI Research Engineer @ https://t.co/c0mfHm4GPy | MSc @medipolunv | RA @Tubitak | Vision + Language
Hhb @undead5438
1 Followers 54 Following
Bala @zenithbala
22 Followers 1K Following
eulers mask @OMEDGE
102 Followers 3K Following
Thatchaphol Saranurak @eig
2K Followers 343 Following Assistant Professor at @UMichCSE. I design fast graph algorithms in dynamic/distributed/local settings.
Muntasir R Rahman @muntasirraihan
196 Followers 2K Following Principal Machine Learning Engineer @ Keystone Strategies
Cursilaso De La Vega @Un_Santajaro
672 Followers 1K Following Matemáticas & ML | Me gusta la poesía 💜🧡 Avanti. Levantemos La Tribuna.
OnTheSpec - e/acc @OnTheSpecdrum
45 Followers 3K Following \sin(\pi^3 x) \cdot \sqrt{\frac{e^2 - x^2}{2}} + \sqrt{|x|}
Manoj Acharya @manoja328
629 Followers 7K Following Mostly Interested in safe and aligned (neural inspired) Machine Intelligence ; PhD from Rochester Institute of Technology
Jeffery Wang @xxxhhhhhh00
6 Followers 165 Following This is Jeffery Wang, as well as Lr-2002. I'm now a PhD student in USTC. My research interests are about Robotics, Embodied AI
Yigal Weinberger @yigalpage
2K Followers 7K Following Posts about LLM's, Data Science, Finance and Personal Growth. While I'm not here, the CTO Of Analysta - AI for risk estimation for the commodities market
Lilith Karapetyan @Lilit_HRAndTech
389 Followers 7K Following HR Generalist. Love to read books. Interested in art, psychology and linguistics. Lets benefit working together 🤝🔥
István Kerek @istvankerek
396 Followers 7K Following University Lecturer, Founder of the ChatGPT Hungarian Facebook Group and @ai2knowit, AI Business Development Expert
johnnycat @johnnycat4225
461 Followers 975 Following Former Democrat, former psychiatric nursing assistant
I07XNbUI4 @DeepFeed2
88 Followers 6K Following
Tegan Jegede @jegede_tegan
208 Followers 7K Following Tegan = print( “👨🏾💻passionate engineer ,AI/ML enthusiast , Real Madrid ,arsenal ⚽️ and GSW🏀: ”)
Black Jaguar @MrTrickC
46 Followers 734 Following Trader 🚀| Python developer 🐍 | Building AI solutions for Latam 🔥 | 🇵🇪
long @copermaxim
6 Followers 3K Following
Lucas Antonio II @LucasAntonioII
188 Followers 1K Following
VegetaAvatar @VeGeTaX29
20 Followers 6K Following
zhiqiang xu @xu_zhiqiang
48 Followers 1K Following
manikanta alluri @manikantaallur2
65 Followers 651 Following
Yug Borana @yugb_twt
1K Followers 4K Following
edeegoo @douebs
228 Followers 6K Following algorithm, complexity, tcs, mma, history, politics. bust brainless CEOs/VCs/prof.s. NYU alumni.
سعدی روشنای... @wolfofroshanaei
193 Followers 2K Following
Dara @dara_tourt
14 Followers 7K Following
juxiliu789 @juxiliu789
78 Followers 7K Following
O'Neill Joseph @MetTetSystems
8 Followers 117 Following I make Custom Small Batch Style LORAs for artist, DM me if you're interested in purchasing a LORA for SDXL or SD 1.5. I also train personal LORAs
I'm blue Da ba dee da... @ErroritaX
159 Followers 3K Following
KyleYoung @KyleYoung_ymj
20 Followers 199 Following CS PhD candidate at Renmin University of China https://t.co/krQZz02S2Z
Phaninder Esrapu @Phaninder_v
12 Followers 1K Following
David Manzano-Macho @davmanzano
138 Followers 2K Following PhD on AI. Leading Data Science and Artificial Intelligence Strategy and Development.
Mohammad Raihan Uddin @_RaihanMohammad
368 Followers 8K Following MS in UAH’25, ML\AI, Quantum Computing Learning, Wireless Communications, Privacy & Security.
Zhiyong Wang @Zhiyong16403503
784 Followers 4K Following Ph.D. candidate at CUHK. Former Visiting Scholar at Cornell. Working on reinforcement learning and multi-armed bandits.
Akshya Kumar Sahu @AkshyaK98687017
2 Followers 203 Following
Chaim Baskin @ChaimBaskin
594 Followers 2K Following Assistant Prof @ BGU | Efficient & Robust ML • GNNs • Foundation Models | AC ICLR • LoG • WACV | Member of ELLIS | IEEE Sr. Member
Marko Njegomir @MarkoNjegomir
450 Followers 1K Following PhD student | TA | Machine learning, graph neural networks, software engineering, medical neuroscience. The limits of my compute mean the limits of my world.
George Giapitzakis @ggiapitz
32 Followers 90 Following Master's student in CS @uwaterloo | Onassis Foundation Scholar | Prev: Research Assistant @quantumlah | https://t.co/pGpvW97csM
Valentio Iverson @viverson2004
111 Followers 394 Following 4th year UWaterloo undergraduate interested in machine learning theory
Abir HARRASSE @AHarrasse1906
16 Followers 302 Following Research Intern @MPI_IS | Ex-research intern @withmartian | Final year engineering student @UM6P_officiel | IInto Interpretability & Reasoning 🧩🧠
George Giapitzakis @ggiapitz
32 Followers 90 Following Master's student in CS @uwaterloo | Onassis Foundation Scholar | Prev: Research Assistant @quantumlah | https://t.co/pGpvW97csM
David Manzano-Macho @davmanzano
138 Followers 2K Following PhD on AI. Leading Data Science and Artificial Intelligence Strategy and Development.
Federico Barbero @fedzbar
3K Followers 293 Following I like Transformers and graphs. I also like chess and a few other things as well @googledeepmind @compscioxford
Marko Njegomir @MarkoNjegomir
450 Followers 1K Following PhD student | TA | Machine learning, graph neural networks, software engineering, medical neuroscience. The limits of my compute mean the limits of my world.
Thiago Serra (@thserr... @thserra
3K Followers 944 Following Assistant professor at @UIowa, formerly at @BucknellU, mathematical optimizer with #orms PhD from @CarnegieMellon, proud father of two
Berkeley Lab @BerkeleyLab
92K Followers 2K Following Official account of Lawrence Berkeley National Laboratory (LBNL), a U.S. Department of @ENERGY national lab.
Lenka Zdeborova @zdeborova
15K Followers 448 Following Professor at EPFL. Une mathémaphysinformaticienne. Passionate mushroom hunter. Tamer of two little dragons.
Calc Consulting @CalcCon
4K Followers 2K Following Calculation Consulting is a boutique consultancy that specializes in machine learning, AI, and data science
Western Math @westernuMath
256 Followers 185 Following The Department of Mathematics is part of SMSS at @WesternU. We offer undergraduate and graduate programs and are known for excellence in teaching and research.
Ruisi Cai @ccccrs_0908
405 Followers 276 Following Ph.D. student @UTAustin; Research Intern @NVIDIA @CitadelSecurities; BS @USTC; NVIDIA fellowship 2025 recipient
VITA Group @VITAGroupUT
1K Followers 3K Following VITA Group @UTAustin w/ Prof Atlas Wang | https://t.co/Wi3tJXf1mg Run by VITA students (PI is busy changing diapers😄). Tweets only reflect personal views
Peter Wang @peihao_wang
103 Followers 223 Following 🎓PhD Student @utexasece @WNCG_UT @VITAGroupUT🎄@ccccrs_0908
Hannes Stärk @HannesStaerk
12K Followers 407 Following @MIT PhD student • ML for molecules and biology https://t.co/hEtGZrEHqu
Steinar @Steinarlaenen
56 Followers 290 Following Computer Science Ph.D. student at University of Edinburgh, former research intern @_FiveAI.
Daniel Severo @_dsevero
2K Followers 1K Following Research Engineer FAIR @AIatMeta / PhD @UofT @VectorInst / Former @GoogleAI student researcher and @UFSC 🇧🇷 undergrad
Haggai Maron @HaggaiMaron
2K Followers 269 Following Assistant Professor @TechnionLive. Senior research scientist at @nvidia. Learning with group symmetries, graphs and weight spaces.Views do not represent nvidia.
Dan Roy @roydanroy
57K Followers 2K Following ML / AI researcher. Research Director and Canada CIFAR AI Chair, @VectorInst. Professor, @UofT (Statistics/CS).
XY Han @XYHan_
2K Followers 1K Following Assistant Professor @ChicagoBooth | Papers: “Neural Collapse in Deep Nets” & “Survey Descent: Nonsmooth GD” | BSE @Princeton, MS @Stanford, PhD @Cornell
Nathan Kallus @nathankallus
2K Followers 238 Following 🏳️🌈👨👨👧👦 Assoc Prof @Cornell @Cornell_Tech @Netflix @NetflixResearch causal inference, experimentation, optimization, RL, statML, econML, fairness
Miaolan Xie @Miaolan_Xie
37 Followers 94 Following
Nate Veldt @n_veldt
236 Followers 75 Following Assistant Professor in the Department of Computer Science and Engineering at Texas A&M University
Waterloo Mathematics @WaterlooMath
7K Followers 983 Following Tweets from the University of Waterloo's Faculty of Mathematics.
Yann LeCun @ylecun
955K Followers 765 Following Professor at NYU. Chief AI Scientist at Meta. Researcher in AI, Machine Learning, Robotics, etc. ACM Turing Award Laureate.
Jiaming Zhou @jmZhou18
14 Followers 277 Following
João Pedro Mattos @joaopedromatt
259 Followers 2K Following 🇧🇷|🇺🇸 CS PhD Student @ Rice University - Graph ML and Data Mining. Prev.: ICMC - USP @[email protected]
Richard Peng @rpeng233
2K Followers 330 Following Associate Professor @SCSatCMU, works on efficient graph/sparse matrix algorithms. Adjunct Professor @UWCheritonCS.
Jatin Chauhan @chauhanjatin100
294 Followers 689 Following Research @Fujitsu, Previously - Research @Microsoft, @GoogleAI, @Triomicsinc, @CS_UCLA
Blue Mountain Resort @BlueMtnResort
30K Followers 12K Following Ontario's favourite four season destination ⛷️❄️🏔️🥾 #DreamBigger 📍Ontario, Canada
Andreas Loukas @loukasa_tweet
2K Followers 483 Following machine learning biology. doesn't work on LLMs yet. likes to think about how machines learn
Alex Dimakis @AlexGDimakis
21K Followers 2K Following Professor, UC berkeley | Founder @bespokelabsai |
Bill Gates @BillGates
66.3M Followers 571 Following Sharing things I'm learning through my foundation work and other interests.
Jason Lee @jasondeanlee
18K Followers 4K Following Associate Professor at UC Berkeley. Former Research Scientist at Google DeepMind. ML/AI Researcher working on foundations of LLMs and deep learning.
Petar Veličković @PetarV_93
41K Followers 555 Following Senior Staff Research Scientist @GoogleDeepMind | Affiliated Lecturer @Cambridge_Uni | Assoc @clarehall_cam | GDL Scholar @ELLISforEurope. Monoids. 🇷🇸🇲🇪🇧🇦
Gabriele Corso @GabriCorso
8K Followers 709 Following PhD student @MIT • Research on Generative Models and Geometric Deep Learning for Biophysics • BA @CambridgeUni • Former @TwitterResearch, @DEShawGroup and @IBM
Bill Cook @wjcook
3K Followers 222 Following Combinatorics and Optimization, University of Waterloo. Past Chair of the Mathematical Optimization Society.
Jure Leskovec @jure
44K Followers 396 Following Professor of #computerscience @Stanford; Co-founder at https://t.co/hhm1j5wP0f #machinelearning #graphs.
Michael Bronstein @mmbronstein
54K Followers 6K Following #DeepMind Professor of #AI @UniofOxford / Director #AITHYRA / Chief Scientist @vant_ai / https://t.co/kZpGpDzYeV (opinions are mine) 🤖🧪🧬🎶🐎
Max Welling @wellingmax
39K Followers 472 Following
PS5 Restocks Canada @PS5stockCanada
50K Followers 19 Following Will notify about PS5 restocks in Canada. Follow w/ notifications or join the Telegram: https://t.co/E81WSCr8k1 Personal account: @_MaxKing
PlayStation Canada @PlayStationCA
143K Followers 417 Following Official Canadian Twitter updates on PlayStation, PS4, PS5, PS VR, PlayStation Store and more. Support: @AskPlayStation
EB Games Canada @ebgamescan
164K Followers 712 Following Live support Mon-Fri 9am-5pm ET | Assistance en direct lun-ven, 9am-5pm. HE ! Reach us//contactez nous: [email protected]
BBY Canada Gamers @BBYC_Gamers
189K Followers 1K Following The official Twitter handle for Best Buy Canada Gaming deals. Follow for hot gaming offers, latest news, giveaways & more!
Walmart Canada Gaming @WalmartCAGaming
169K Followers 324 Following The official X page of Walmart Canada Gaming. Follow us for gaming news, product information and more! | Customer service needs should message @WalmartCanada.
Cristian Bodnar @crisbodnar
6K Followers 2K Following Co-founder @SilurianAI. Training big neural nets to simulate the world. Previously @MSFTResearch, @Google Brain, @Theteamatx | ML PhD from @Cambridge_Uni
Junteng Jia @junteng_jia
92 Followers 81 Following PhD student at Cornell University. Interested in Network Science, Machine LearningTrends for United States
You might like
