Weihua Hu
@weihua916
Followers
5,975
Following
1,067
Media
47
Statuses
6,913
Graphs. Deep Learning. Currently @perplexity_ai . CS Ph.D. @Stanford BS/MS University of Tokyo. Previously @Meta @GoogleDeepMind
Stanford, CA
Joined April 2013
Don't wanna be here?
Send us removal request.
Explore trending content on Musk Viewer
Luka
• 287381 Tweets
Dallas
• 63922 Tweets
Gobert
• 63575 Tweets
Mavs
• 57158 Tweets
Soto
• 27688 Tweets
Naz Reid
• 25038 Tweets
Anthony Edwards
• 24534 Tweets
Mavericks
• 23126 Tweets
DPOY
• 22866 Tweets
サクナヒメ
• 17429 Tweets
Draymond
• 17134 Tweets
Marlon
• 17097 Tweets
マイフリ
• 14663 Tweets
Lively
• 13904 Tweets
Feliz 25
• 13693 Tweets
#loksabhaelections24
• 13511 Tweets
レイちゃん
• 12055 Tweets
清宮卒業
• 12001 Tweets
クマフェス
• 11518 Tweets
Derbez
• 11459 Tweets
#超超超超ゲーマーズday1
• 11344 Tweets
Viva la Patria
• 10129 Tweets
🚀🎉 Excited to announce 🌟 PyTorch Frame 🌟 - our new open-source initiative in PyTorch! Dive into multi-modal tabular deep learning like never before!
Link:
#PyTorch
#OpenSource
(1/6)
5
122
562
Super excited to share Open Graph Benchmark (OGB)! OGB provides large-scale, diverse graph datasets to catalyze graph ML research. The datasets are easily accessible via OGB Python package with unified evaluation protocols and public leaderboards.
Paper:
2
112
409
論文引用数が1000の大台にのった！！
数値面でずっと目標にしてきたので嬉しい．インパクトが大きい仕事ができるようにもっともっと精進する！
5
13
338
Going to intern at
@DeepMind
for the summer, focusing on GNNs for physical simulation.
Londonにいらっしゃる方がいましたらぜひ会いましょう！かなり楽しみ．
6
5
324
Happy to find that the CS224w lecture on "Limitations of Graph Neural Networks" is out on YouTube. I helped making the slides :) The entire course is highly recommended for folks interested in graph ML!
Video:
Course website:
4
59
315
Our paper "How powerful are graph neural networks?" was accepted as ICLR oral! Joint work with Keyulu Xu, Jure Leskovec and Stefanie Jegelka. Check out our paper here:
#iclr2019
6
55
312
Excited to announce that "Open Graph Benchmark: Datasets for ML on Graphs" has been accepted to
#NeurIPS
as a spotlight!
If you are working on Graph ML, please check it out for your next conference submission :)
Website:
Paper:
7
50
288
Last day at my Stanford office (w/ my officemates). Thank you for the amazing 4 years. Time to go back to Japan over the winter break.
3
0
259
Stanford博士課程の振り返りと今後の進路について，船井の卒業報告書に書きました：
興味がありましたら読んでみてください．
2
15
245
日本の皆さん：８月５日午前10時から，Graph Neural Networkについて，(Virtual) Talkをするので，興味がある方はぜひご参加ください．
0
60
234
ありがたいことに"Forbes Japan 30 Under 30"に選出していただきました。
最近は日本での活動が少なくなってるけど、すごく好きな国なので、何か機会を見つけて貢献したいな
#u30fj
9
12
203
Excited to share new work, TuneUp!
Many GNN models developed but their training strategies remain simplistic. We present TuneUp to better train your GNN and improve its predictive performance on a wide range of node-/edge-level tasks!
Paper:
(1/N)
4
38
198
Super excited to share our work "Pre-training Graph Neural Networks."
We explore effective strategies for pre-training GNNs, significantly boosting predictive performance across many downstream tasks in two scientific domains (chemistry and biology).
1
48
195
Excited to share our spotlight paper at
#ICLR2020
"Strategies for Pre-training GNNs." We develop effective strategy/methods for pre-training GNNs and systematically study its effectiveness.
Web site:
Paper:
1
29
179
GNNs for graph classification are NOT simply performing low-pass filters. See our ICLR paper "How powerful are graph neural networks?"
2
33
169
Poster presented at ICLR 2019 on "How Powerful are Graph Neural Networks?"
1
28
165
そういえば，今年の夏にFacebookでインターンしてました！タフだったけど，すごく充実していた．給料はすごく良いし，研究もできるし，計算資源も豊富なので，特にCSのPh.D.学生はぜひ応募してみると良いと思います．
1
7
160
Check out our PyTorch Frame tech report
We aim to push tabular deep learning to handle complex multi-modal, multi-tabular data, beyond conventional single-tabular data. We do so by seamlessly integrating PyTorch Frame with LLMs and Graph Neural Nets!
🚀🎉 Excited to announce 🌟 PyTorch Frame 🌟 - our new open-source initiative in PyTorch! Dive into multi-modal tabular deep learning like never before!
Link:
#PyTorch
#OpenSource
(1/6)
5
122
562
1
24
127
Genuinely amazed by all the graph models/methods developed on the Open Graph Benchmark (). ~500 leaderboard submissions in 2.5 years, with reproducible code + technical reports. Incredible accuracy improvements across the board (some almost solved).
0
18
120
Excited to see that my molecular property predictor system "Pre-trained OGB-GIN" has just ranked top at the COVID-19 open task hosted by MIT AICures team . Thanks for the amazing effort, and it was exciting to apply my research to this timely problem.
2
13
111
Very excited to share our KDD 2022 paper "Learning Backward Compatibility Embeddings."
We formulate a unique challenge of using embeddings in large industrial organizations and present an effective solution to it.
Paper:
Code:
2
20
108
船井奨学金の留学報告書を公開しました．Facebookインターンシップ，最近のプロジェクト，研究者の評価について書きました．
Ph.D.も後半戦突入！もっと勢いをつけていきたい．
0
7
107
A nice summary of recent trends in Graph Machine Learning. It also touches upon our Query2box framework for answering complex queries over incomplete knowledge graphs :)
@ren_hongyu
@jure
1
29
106
AlphaFoldレベルのMLの成果を見せられると，9割方のMLの研究は何をやっているんだという気分になる．breakthroughかっこいい
0
6
104
Ph.D.期間中はひたすら代表作数(≠論文数)を最適化する．分野の研究者みんなが知っている仕事(e.g., 引用数>500)を3つやることが一つの目標．
0
7
100
Excited to give a contributed talk on "ForceNet: A GNN for Large-Scale Quantum Chemistry Calculations” at Deep Learning for Simulation Workshop at ICLR 2021
Paper:
Talk:
Done as part of Open Catalyst Project
3
16
88
Excited to have been part of the team working on global weather forecasting with GNNs!
Presenting GraphCast: our state-of-the-art AI model delivering 10-day weather forecasts with unprecedented accuracy in under one minute. 🌦️
It can even help predict the potential paths of cyclones further into the future.
Here's how it works. 🧵
38
402
2K
2
3
87
Amazing course on COVID-19 at Stanford!
3
33
85
人工知能学会誌のグローバルアイに寄稿しましたので，興味があればぜひ．「コンピュータ科学の本場！アメリカPh. D. への挑戦とそこで学んだこと」
0
14
81
Updates from the Open Graph Benchmark Large-Scale Challenge @ KDD Cup 2021.
- Over 500 teams registered.
- Initial test leaderboards released at
- Final test submission deadline on June 8.
Excited to see great progress in large-scale graph ML!
0
16
79
Very horned and excited to give a talk at KDD Deep Learning Day (Aug 24)!
I will present our recent advances in Graph Neural Networks: expressive power, pre-training, and OGB. Thanks for the organizers for kind invitation.
0
6
73
Excited to share my first work in my Ph.D.: "How powerful are graph neural networks?" We provide a theoretical framework for comparing the expressive power of Graph NNs. Great collaboration with Keyulu from MIT and our advisors, Jure and Stefanie! Link:
1
16
68
僕のStanfordの指導教員は，要求水準が非常に高いので，それに届くように必死に頑張っていると，自分でも自分の成長を感じる．ありがたい．
0
1
65
PFNインターンで取り組んだ論文。ニューラルネットワークを使った離散表現学習の手法。クラスタリングとハッシュ学習でstate-of-the-artの結果を達成！：
1
12
58
Check out our 2nd major release of OGB!
We have provided 5 new datasets, including a web-scale gigantic graph (with 100M+ nodes) and heterogeneous graphs.
Excited to announce 2nd major release of Open Grpah Benchmark (OGB), a collection of realistic, large-scale, and diverse benchmark datasets for machine learning with graphs.
1
106
358
1
22
57
Excited to collaborate with the Papers with Code! Thank you to the team
@paperswithcode
for the great initiative.
The Open Graph Benchmark (OGB) leaderboards are now on Papers with Code!
This provides a comprehensive way to compare models across graph-related tasks and datasets.
1
34
158
0
3
59
Just found the video recording of my talk on Graph Neural Networks at the KDD Deep Learning day available on YouTube!
It's a short 15min summary of the first half of my Ph.D. 🙃 Check it out if you are interested 😃
0
5
54
Tomorrow, we will present "Open Graph Benchmark: Datasets for ML on graphs" at Session 7 of NeurIPS2020! Come chat with us at the poster!
Spotlight (7:30pm--7:40pm PT):
Poster (9pm--11pm PT):
Website:
0
6
55
Excited to release our paper on the OGB Large-Scale Challenge (OGB-LSC) @ KDD Cup 2021 (on-going)!
Learn about our large datasets + extensive baseline analyses, showing that big expressive models are promising for large-scale graph data!
1
11
51
In OGB-LSC, we have prepared a set of three realistic and *extremely* large-scale graph datasets.
Looking forward to the innovative solutions from the community.
Organized with the amazing team:
@rusty1s
@ren_hongyu
@NakataMaho
@ericdongyx
@jure
0
17
48
A large-scale and practically-impactful dataset for graph representation learning! It has been an amazing experience to be part of the team.
Today Facebook AI and Carnegie Mellon are announcing the Open Catalyst Project, using AI to accelerate quantum mechanical simulations — and thus discover scalable ways to store and use renewable energy.
9
159
571
0
3
46
Graph ML folks, stay tuned for this year's KDD Cup from the Open Graph Benchmark, coming in the next few weeks.
0
0
47
Interested in large-scale graph ML? Check out our OGB-LSC paper accepted to NeurIPS benchmark track!
Excited to share that our Open Graph Benchmark Large-Scale Challenge (OGB-LSC) paper has been accepted to NeurIPS! We have updated our datasets and released public leaderboards:
Paper:
1
25
168
1
6
45
Lots of science papers in CS conferences are solving fake problems unless they are produced by collaboration with actual science people.
0
6
44
A day trip to Cambridge was a lot of fun! Felt 800 years of history in the university. Thank you
@chaitjo
for guiding me around.
2
0
43
(1) Strategies for Pre-training GNNs (spotlight) joint work with
@liubowen16
@marinkazitnik
@vijaypande
@percyliang
@jure
2
3
41
船井の留学報告書を公開しました．最近の研究，TA, Qualifying examなどについて書きました．もうすぐ４年目に突入！wow
0
3
40
Really excited to announce the winners of OGB-LSC!!
All the winning solutions (code and technical reports) are made publicly available. Learn about the state-of-the-art ML methods for large-scale graph data!
Winners of the OGB-LSC graph machine learning challenge have just been announced at
Congratulations to the winning teams from
@BaiduResearch
,
@DeepMind
,
@Synerise
, Harbin and Dalian Institutes of Technology and USTC!
4
51
222
2
5
39
今学期は膨大な時間を使ってTAしているんだけど，だんだんとTeachingの奥深さがわかってきた．合計300+枚のスライド作りはめっちゃしんどいけど，勉強になる... Conference talkのスライドと作り方が全然違う😭
1
0
38
Excited to announce TGB that expands the scope of OGB into temporal graphs! We welcome the community to explore the fruitful direction with our new benchmark!
I am delighted to announce the Temporal Graph Benchmark (TGB), a collection of challenging and diverse benchmark datasets for temporal graph learning, developed in collaboration with the OGB team!
4
43
161
0
1
38
It's great that DRO community is starting to embrace that naive DRO does not work and structural assumptions are really necessary.
It took us 6 conference rejects until the our negative results paper got accepted...
1
4
35
I really want my own office at school to stay focused. My commute time (from my bed to my desk) is less than 1 second.
3
0
37
Last night in Japan before I leave here for five years, flashing back great memories.
2
0
35
Found this very interesting course on deep learning, broadly covering its recent advances. Comes with YouTube lecture videos.
0
5
35
Almost done with my TA jobs for CS224W ()!
One big highlight was to see students innovating over Open Graph Benchmark datasets (). Impressed to see some SoTA performances achieved in one month!!
2
2
34
Check out the video recording of our NeurIPS 2022 workshop on the 2nd Open Graph Benchmark Large-Scale Challenge.
Workshop website:
YouTube:
0
3
32
The YouTube video of my talk on OGB-LSC is out!
Learn about our large-scale graph datasets, the recent KDD Cup, and the lessons we learned.
Thank you
@myamada0
for the invitation!
I will be giving a talk on the recent OGB Large-Scale Challenge at the KDD Cup 2021. Registration is here:
September 2nd 10am JST
September 1st 6pm PDT
日本の方もぜひ！
0
2
18
0
7
32
留学説明会でコンピュータ科学分野の海外Ph.D.出願について話します．興味がありましたらぜひご参加ください．
UT-OSACよりイベントのお知らせ
海外大学院留学説明会＠東京大学
日時：2021年7月11日（日）13:00 - 15:00
場所：オンライン
海外大学院に進学し、学位を得るという選択肢に目を向けてみませんか？
詳細・申込はこちら：
0
10
24
0
4
32
めっちゃ同感．博士課程の5年間で自分の価値をどこまで上げるか．博士課程中の手取りの給料は少ないけど，頑張り次第では，ある意味ものすごく給料をもらっている期間なのかもしれない．
東大医学部、河野玄斗さんの「1000時間勉強して将来の年収が100万円上がる場合、勉強の時給は100万円×40年÷1000時間＝時給4万円になるよ。なんでみんなそんなに勉強しないの？」っていう言葉、本当に好き。
12
2K
18K
0
3
31
Going to the KDD conference next week. It's been almost 4 years since I attended an in-person conference last time to present my first Ph.D. paper.
0
0
31
I asked my parents to bring miso soup but I did not ask for that much... 100 packs...
2
0
28
昨日OGBプロジェクトの最終原稿を提出して，1年がかりのプロジェクトがひとまずまとまった．完全に手探りの状態で始まって，途中で割と絶望的になりつつも，チーム一丸となってここまで仕上げたのは本当に感慨深い．感謝．
0
1
29
I'm in London, UK! Haven't been outside the U.S. for three years!
1
0
29
My first year has been amazing. Got into an exciting research field of graph representation learning, and aligned with the amazing advisor
@jure
0
0
27
Just realized that I entered my 3rd year in my Ph.D.... Feeling time is so fast
0
0
26
@liubowen16
@marinkazitnik
@vijaypande
@percyliang
@jure
(2) Query2box: Reasoning over Knowledge Graphs in Vector Space Using Box Embeddings
joint work with
@ren_hongyu
@jure
0
2
25
This is sooo well-deserved!!
0
3
25
I was listening to my advisor's talk at the SSL workshop (). The highlight for me was when he said "A molecule is a social network of atoms and bonds" 😂😂 Changes my perspective of looking at molecules.
0
2
24