Xavier Bresson @xbresson Twitter profile

Last Seen Profiles

@Santosh34274425

@bokeplokalmalam

@megalodonna

@LopeAriyo

@RestySaya

@VSlifko42585

@fuckingcharls

@Sandra390431234

@Mewskung77

@EmilyXHarlow

@Epolchefile

@fastbreakbreak

@Klassicheskiy

@Smoalot12696

@mrplaifa_

@Snayeon2

@yua_chin0217

@riona404094804

@Tr0414

@yoyo440802

@stwmaniax

@jesss1805

@beyondanyform

@JesseASweeney

@KasihLudah

@vip35477

@_typedev

@KasihLudah

@EACrobertburns

@_scsl

@tandfonline

@notexisthikamer

@Husein164650143

@miggythetechguy

@HH_M_AD

@sportCT

Xavier Bresson

@xbresson

4 years

One distribution to rule them all !

30

879

4K

Xavier Bresson

@xbresson

1 year

My 15-year-old daughter just sent me a photo of my old phd thesis she found at my parents' home 🥰

43

73

2K

Xavier Bresson

@xbresson

4 years

My main talks on Graph Neural Networks in 2020 1. Introduction to GNNs 2. Recent developments in GNNs 3. Benchmarking GNNs Hope they can be useful. Happy new year to everyone !

8

382

2K

Xavier Bresson

@xbresson

4 years

Sharing my lecture slides on "Recent Developments of Graph Network Architectures" from my deep learning course. It is a review of some exciting works on GNNs published in 2019-2020. #feelthelearn

12

254

1K

Xavier Bresson

@xbresson

3 months

I will be teaching "Deep Learning" and "Graph Machine Learning" next academic year 😀 Thank you all for your support and advice!

17

47

1K

Xavier Bresson

@xbresson

3 years

Sharing my lecture slides on Attention Nets/Transformers with two simple codes for (1) Language Modeling and (2) Sequence-To-Sequence Modeling to understand Transformers from scratch. Slides : Codes :

8

217

1K

Xavier Bresson

@xbresson

4 years

Happy to deliver a remote lecture on "Graph Convolutional Networks" tomorrow for the NYU Deep Learning course of @ylecun and @alfcnz . Slides and video will be made available.

9

185

1K

Xavier Bresson

@xbresson

7 years

Deep learning era - do not forget to cite *future* relevant papers in your paper :)

13

313

1K

Xavier Bresson

@xbresson

1 year

My lecture notes on regularization techniques in machine learning Check out the section on double descent suggested by @ylecun :)

13

156

1K

Xavier Bresson

@xbresson

2 years

Our paper "Benchmarking Graph Neural Networks" has been accepted for publication at Journal of Machine Learning Research @JmlrOrg ! (after rejection from NeurIPS, ICLR and ICML :)

13

132

988

Xavier Bresson

@xbresson

1 year

My lecture notes on variance and bias in machine learning.

6

134

787

Xavier Bresson

@xbresson

3 months

My 10 Favorite Algorithms • K-means and spectral clustering • FFT • Random forest and gradient boosting • Personalized PageRank • ADMM and primal-dual optimization • EVD and SVD • Backpropagation and SGD • Convnet and transformer • Reinforce algorithm • Diffusion model

22

49

690

Xavier Bresson

@xbresson

1 month

Notebooks 💻 for Lecture 6 on Graph-based Visualization Lab1: PCA Lab2: Robust PCA Lab3: LLE Lab4: Laplacian eigenmaps Lab5: TSNE Lab6: UMAP Lab7: Visualization with deep learning

3

135

676

Xavier Bresson

@xbresson

2 years

Our Graph Transformer is discussed in the latest version of The Batch of @AndrewYNg 😀

5

116

659

Xavier Bresson

@xbresson

3 months

Notebooks for Lecture 5 on Recommendation on Graphs Lab1: Google PageRank Lab2: Collaborative/low-rank recom Lab3: Content/graph-Dirichlet recom Lab4: Hybrid recom

4

123

655

Xavier Bresson

@xbresson

8 months

Let's get started!😀 Lecture 1 offers a high-level introduction to Graph Machine Learning. Additionally, check out the top-tier books by @mmbronstein , @TacoCohen , @PetarV_93 , and outstanding computing libraries by @DGLGraph , @PyG_Team to learn GML.

7

112

648

Xavier Bresson

@xbresson

7 months

Favorite feedbacks from Reviewer 2 :

16

49

626

Xavier Bresson

@xbresson

1 year

My lecture slides on linear learning and support vector machine.

3

92

604

Xavier Bresson

@xbresson

3 months

My new favorite easy-to-use interactive 3D visualization library is Plotly! Here is a visualization of the CIFAR dataset where images are first projected into 2,048-dimensional hidden vectors using InceptionV3 and then reduced to 3D using UMAP.

13

85

565

Xavier Bresson

@xbresson

2 years

Sharing my lecture slides on Generative Models with VAE and GAN. I present the models from scratch and provide simple codes to understand the core ideas. Slides : Codes :

6

111

553

Xavier Bresson

@xbresson

8 months

I will be sharing soon my course material on Graph Machine Learning from last year. Initially, I planned to wait for a 2nd iteration of the course for polishing and improving, but considering I may not teach it again, I have decided to share the first version :)

9

82

546

Xavier Bresson

@xbresson

7 months

Instructions for running the course notebooks with GitHub, Google Colab or local installation: Course's repo : It is remarkable how much easier it has become to run DL codes compared to when I began teaching it back in 2014!

2

110

478

Xavier Bresson

@xbresson

5 years

New paper on benchmarking graph neural networks w/ @vijaypradwi @chaitjo T. Laurent and Y. Bengio Our goal was to identify trends and good building blocks for GNNs.

8

134

468

Xavier Bresson

@xbresson

1 year

Ever wanted to code Graph Transformer (GT) from *scratch* using a few lines of code with @PyTorch and @DGLGraph ? :) See below my course material Slides: GitHub: Paper: Coding GT step-by-step 👇

12

101

455

Xavier Bresson

@xbresson

1 month

Graph Machine Learning course Lecture 6 presents Graph-based Visualization 🌟 PCA, Robust PCA, Graph PCA are notable examples of linear dimensionality reduction and LLE, Laplacian Eigenmaps, TSNE, UMAP are outstanding non-linear dim reduction techniques

3

78

458

Xavier Bresson

@xbresson

1 year

My lecture slides on kNN techniques with vanilla kNN, k-d tree, decision tree, random forest and gradient boosting.

4

68

427

Xavier Bresson

@xbresson

4 years

. @ylecun @wellingmax @OriolVinyalsML @69alodi @PeterWBattaglia @StefanieJegelka @WoodyOsher and I are organizing next week the @ipam_ucla workshop on "Deep Learning and Combinatorial Optimization" Great line-up of speakers :)

Deep Learning and Combinatorial Optimization - IPAM

www.ipam.ucla.edu

2

106

414

Xavier Bresson

@xbresson

5 years

An amazing finding in 2019 was the double-descent of M Belkin. This is not only a deep theoretical result in machine learning- it has also a great practical interest => Make your net large, learn long enough and that's it! Bye bye early stopping :) Video:

3

103

409

Xavier Bresson

@xbresson

6 months

Notebooks for Lecture 3 on Graph Clustering Lab1: k-means Lab2: Metis Lab3/4: NCut/PCut Lab5: Louvain

2

86

404

Xavier Bresson

@xbresson

5 years

My lecture slides on "Attention Neural Networks". I introduce the popular families of attention nets with MemoryNets, Transformers (seq2seq and language modeling) and BERT: I've also upgraded the demo of A. Rush to PyTorch 1.1:

1

102

400

Xavier Bresson

@xbresson

4 months

"As part of the requirements for my doctoral degree, I need to publish 15 research papers" 😲

41

19

393

Xavier Bresson

@xbresson

1 year

If new with graph learning, here is a warm-up notebook to learn to use graphs: • Build graph w/ features and compute basic message-passing function w/ @DGLGraph • Convert into graph formats w/ DGL, NetworkX, dense/sparse PyTorch • Visualize graph Code:

4

97

388

Xavier Bresson

@xbresson

4 years

Slides of my talk "The Transformer Network for the Traveling Salesman Problem" for @ipam_ucla workshop "Deep Learning and Combinatorial Optimization". We have improved recent learned heuristics for TSP50 w/ optimality gap of 0.004% and 0.39% for TSP100.

7

86

387

Xavier Bresson

@xbresson

5 months

Notebooks for Lecture 4 on Graph SVM Lab1: Standard/Linear SVM Lab2: Soft-Margin SVM Lab3: Kernel/Non-Linear SVM Lab4: Graph SVM

2

88

397

Xavier Bresson

@xbresson

3 years

I've moved to the School of Computing at the National University of Singapore. @NUSingapore @NUSComputing Contact me if you are interested in a PhD/Postdoc in GraphNNs+X

15

25

390

Xavier Bresson

@xbresson

7 months

Lecture 2 introduces Graph Science 🌟 Topics include: Graph theory, graph categories, basic definitions, curse of dimensionality, blessing of structure, manifolds and graphs, spectral graph theory.

4

79

389

Xavier Bresson

@xbresson

5 years

My lecture slides on "Deep Reinforcement Learning". I explain step-by-step the popular RL algorithms DQN, REINFORCE, QAC, AAC: And theory is supported by PyTorch implementations :)

4

93

387

Xavier Bresson

@xbresson

6 months

Graph Machine Learning course Lecture 4 presents Graph SVM 🌟 The celebrated Support Vector Machine (SVM) coupled with kernel method and graph Dirichlet regularization is one of the best classification models (in the absence of feature learning :)

4

61

363

Xavier Bresson

@xbresson

2 years

I joined the AI lab @SeaGroup as Head of Graph Machine Learning. I will explore theory and applications of GNNs. If you want to work on this exciting topic, there are opportunities for full-time RS/RE, industrial PhDs (w/ NUS), interns, etc. Pls, contact me at bressonx @sea .com

26

28

353

Xavier Bresson

@xbresson

1 year

Course material to learn DeepWalk, a node embedding technique for graphs. Slides: Code: Paper:

5

78

344

Xavier Bresson

@xbresson

3 years

Our workshop on Graph Neural Networks and Systems is next Friday, April 9th 7am-4pm PST. Workshop schedule #MLSys2021 #GNNSys2021

4

61

326

Xavier Bresson

@xbresson

4 months

Graph Machine Learning course Lecture 5 presents Recommendation on Graphs 🌟 Google PageRank, collaborative & content recommendation, low-rank matrix completion, graph diffusion filtering, non-negative matrix factorization are the prominent techniques.

2

59

324

Xavier Bresson

@xbresson

1 year

Nesterov stands among the giants of optimization. His recent interview offers substantial food for thought.

2

55

316

Xavier Bresson

@xbresson

7 months

Notebooks for Lecture 2 on Graph Science Lab1: Generate LFR social networks Lab2: Visualize spectrum of point cloud & grid Lab3/4: Graph construction for two-moon & text documents

3

70

312

Xavier Bresson

@xbresson

3 years

I recently spoke with a journalist about applications of Graph Neural Networks. I made a few slides to facilitate the discussion. I share them here -- hopefully they can be useful :)

GNN_applications_Jun21.pdf

Shared with Dropbox

www.dropbox.com

1

74

294

Xavier Bresson

@xbresson

3 years

Scikit-learn is one of the best machine learning tools! I teach this library to my undergraduate students. Great news -- the developers offer a free course (in English) from May 18 to July 14. Register here:

Inria

@Inria

3 years

Tout savoir sur @scikit_learn , le 3e logiciel libre de #machinelearning le plus utilisé au monde 🚀 Du 18 mai au 14 juillet ses créateurs proposent leur MOOC en anglais et gratuit, pour apprendre à construire des modèles prédictifs ! 📍 Inscriptions

1

76

147

6

72

285

Xavier Bresson

@xbresson

3 years

Accepted at #ICLR2022

Vijay Dwivedi

@vijaypradwi

3 years

Presenting new work on GNNs/(Graph)Transformers: "Graph Neural Networks with Learnable Structural and Positional Representations" with Anh Tuan Luu, Thomas Laurent, Yoshua Bengio and @xbresson . Paper: Code: #2minutebrief 👇

9

95

433

5

33

253

Xavier Bresson

@xbresson

4 years

I will give a series of lectures on Graph Neural Networks this week for the 5th Int'l Summer School on Data Science (SSDS 2020). The summer school was scheduled to be in the beautiful city of Split, Croatia, but given the situation it will be virtual.

5

52

250

Xavier Bresson

@xbresson

3 months

The LLM industry relies on Transformers w/ O(n^2) complexity. GNNs are O(E)~O(n) for sparse graphs. Industry application: Google Maps ETA developed by @PetarV_93 et-al

Traffic prediction with advanced Graph Neural Networks

By partnering with Google, DeepMind is able to bring the benefits of AI to billions of people all over the world. From reuniting a speech-impaired user with his original voice, to helping users...

deepmind.google

Romee Panchal

@romitheguru

3 months

@xbresson I have not seen much applications of graph machine learning in industry. Also, GNN are too expensive to run.

1

0

4

5

25

245

Xavier Bresson

@xbresson

6 months

Lecture 3 reviews Graph Clustering 🌟 Clustering is a cornerstone topic that beautifully connnects combinatorial optimization, continuous optimization, graph theory and spectral theory.

1

51

241

Xavier Bresson

@xbresson

1 year

Michael Bronstein @mmbronstein , Physics-inspired learning on graphs #ICLR2023 Workshop on Physics for Machine Learning

2

24

237

Xavier Bresson

@xbresson

4 years

Positional encodings are essential for two reasons: 1. They guarantee Transformers/graphNNs to be universal approximators for functions invariant by index permutation. Most real-world graphs have natural symmetries, like the line graph for Transformers.

François Fleuret

@francoisfleuret

4 years

There is the feeling that positional encodings are far more important than you would guess at first, and that they are slowly making convolutions irrelevant.

3

2

68

3

31

232

Xavier Bresson

@xbresson

3 years

Stéphane Mallat is a prodigious researcher & teacher. He has a new course on math for high-dim data (in French ;) His previous courses 2021: 2020: 2019: 2018:

3

41

228

Xavier Bresson

@xbresson

1 year

Course material to learn GIN, a MP-GNN as powerful as the WL graph isomorphism test. Slides: Code: Paper: A student asked me why GIN cannot classify CSL graphs?

4

46

222

Xavier Bresson

@xbresson

4 years

List of unsolved problems in graph theory:

1

45

223

Xavier Bresson

@xbresson

1 year

Final lecture for my course on Graph Machine Learning! Thanks a lot to the students who attended and posed engaging questions 😁

8

7

222

Xavier Bresson

@xbresson

4 years

Actually it can be shown that convolution and transformer/attention are (almost) equivalent for graphs. Architectures like Transformers and ConvNets are slowly but happily converging.

Oriol Vinyals

@OriolVinyalsML

4 years

Recent conversation with a friend: @ilyasut : what's your take on ? @OriolVinyalsML : my take is: farewell convolutions : )

11

187

875

3

39

221

Xavier Bresson

@xbresson

5 years

I am still puzzled why some people are so alarmist about our limited understanding of AI? Along this line, they should also be alarmist about planes as our air turbulence understanding is quite limited!

22

42

216

Xavier Bresson

@xbresson

3 years

I was asked about self-attention and cross-attention. See slides 53-58 that intuitively describe SA & CA (w/ adaptative context, reception field, hierarchy) and why it is essential to use multiple layers for deep representation and multi-step reasoning.

1

37

215

Xavier Bresson

@xbresson

4 years

I will give a talk today on "Learning to Solve the Traveling Salesman Problem with Transformers" at the @RealAAAI workshop on Deep Learning on Graphs.

2

20

201

Xavier Bresson

@xbresson

1 month

Terence Tao discusses "AI and Mathematics" at IMO 2024: He provided clear examples of the deep connections between mathematics and computers throughout history. He also expressed the view that "AI is disruptive, but there is also a sense of continuity".

0

44

193

Xavier Bresson

@xbresson

4 years

. @ylecun @OriolVinyalsML @wellingmax @PeterWBattaglia @69alodi S. Jegelka S. Osher and I are organizing an exciting workshop on the intersection of deep learning and combinatorial optimization at @ipam_ucla on Feb 22-26 2021.

1

40

182

Xavier Bresson

@xbresson

2 years

New paper w/ @he_xiaoxin @BryanHooi1 T Laurent @AdamPerold @ylecun We introduce Graph MLP-Mixer, a GNN w/ three key properties: 1) captures long-range dependency 2) keeps low linear speed/memory complexity as MP-GNNs 3) provides high expressivity

5

39

176

Xavier Bresson

@xbresson

1 year

New paper "Feature Collapse" w/ Thomas Laurent James von Brecht ArXiv: GitHub: Feature learning is a critical mechanism in deep learning, enabling generalization. But a comprehensive understanding of this mechanism remains elusive.

4

45

179

Xavier Bresson

@xbresson

7 months

Sharing my slides for the workshop "AI for Science in Singapore"

Xavier Bresson

@xbresson

7 months

I am speaking tomorrow at the "AI for Science" workshop at the NRF. It will be engaging! Local folks are welcome to join us at CREATE Tower Level 2, Singapore 138602

0

4

24

2

26

174

Xavier Bresson

@xbresson

6 months

ICML Reviewer2 "The paper is well-structured and easy to follow" ⇒ Presentation: 1 poor ".. is a significant contribution" ⇒ Contribution: 2 fair "Due to my limited time to review, I did not catch up with the most novel point in the paper" ⇒ Rating: 1 Very Strong Reject 😞

8

10

171

Xavier Bresson

@xbresson

10 months

Trying my best efforts to convince my committee to teach Deep Learning and Graph Machine Learning but without any success so far.. What is the purpose of having any research expertise if you cannot share and teach it? Any recommendation?

18

4

171

Xavier Bresson

@xbresson

4 years

Excited to release a major update of our project "Benchmarking Graph Neural Networks" Paper: GitHub: 1/

GitHub - graphdeeplearning/benchmarking-gnns: Repository for benchmarking graph neural networks

Repository for benchmarking graph neural networks. Contribute to graphdeeplearning/benchmarking-gnns development by creating an account on GitHub.

github.com

Xavier Bresson

@xbresson

5 years

New paper on benchmarking graph neural networks w/ @vijaypradwi @chaitjo T. Laurent and Y. Bengio Our goal was to identify trends and good building blocks for GNNs.

8

134

468

1

44

169

Xavier Bresson

@xbresson

2 years

End of the workshop "Artificial Intelligence and Discrete Optimization" Thanks again to @ipam_ucla , the speakers and the participants for an exceptional workshop! All talks will be available at

1

39

167

Xavier Bresson

@xbresson

3 years

Thrilled to give two talks at ACM #KDD2021 . 1. Deep Learning on Graphs (DGL-KDD’21) Talk on Aug 14th 7pm PST 2. Applied Data Science (ADS) Talk on Aug 15th 10:45pm PST @kdd_news

1

26

157

Xavier Bresson

@xbresson

1 year

Gil Strang is one of the smartest and kindest individuals I have met. During my postdoc at UCLA, Gil made me grasped the beauty of graphs. He's always been supportive to young people, at each career step. His signature: "Best wishes and send any papers I should know about!" 😁

MIT Mathematics

@MITMath

1 year

Prof. Gil Strang's last lecture is ... Monday! Watch it via live stream:

229

2K

11K

1

16

161

Xavier Bresson

@xbresson

4 years

I recommend to watch the talk of @lipmanya about equivariant GraphNNs. Wonderful talk, technical and accessible (w/ nice illustrative figures to explain the math concepts).

1

40

157

Xavier Bresson

@xbresson

6 years

Wow - geometric deep learning is going mainstream! Great job on the introductory video @sirajraval ! In addition, a perfect documentary video of researchers doing geometric deep learning :)

Siraj Raval

@sirajraval

6 years

Deep Learning generally works well on Euclidean data, but it turns out that graphs & 3D objects are not in that category. Geometric Deep Learning offers us a powerful solution to this problem!

5

52

197

0

37

160

Xavier Bresson

@xbresson

2 years

Working on the icml rebuttal and still surprised by the reviewers' critics with the "not new", "too simple", "not theoretical", "not SOTA". Let me use the example of Transformer (TR).

4

23

161

Xavier Bresson

@xbresson

1 year

Slides on graph datasets (from my course) with graph type, #graphs , #nodes (mean), #edges (mean), #node / #edge features, graph/node/link task, web link Slides: GitHub:

6

29

141

Xavier Bresson

@xbresson

2 years

Excited to present deep learning for genome assembly ! A new project at the intersection of genomics, graph neural networks and combinatorial optimization. Data, code, arxiv available below. My recent talk on this topic

Lovro Vrček

@lovrovrcek

2 years

After many months, I'm proud to share our work on untangling genome assembly graphs with GNNs. Or, GNNome Assembly (sorry not sorry)🧬 Paper: Code/Data: with @xbresson , T. Laurent, @Martin_fschmitz , and @msikic . Read more in 🧵

6

79

235

0

24

134

Xavier Bresson

@xbresson

10 months

Reviewer: Compare with techniques x and y, datasets z and w Us: We did and got significant better results R: Whatever, I think the novelty is low Takeaway: When you want to reject a paper and lack good reasons, use novelty. Novelty cannot be rebutted by experiments!

9

15

132

Xavier Bresson

@xbresson

4 years

My ICLR20 talk at the workshop "Integration of Deep Neural Models & Differential Equations" is online Video(starts at slide 3): Slides: Thanks & appreciation to @TanNguyen689 @rbaraniuk @animesh_garg S Osher @AnimaAnandkumar B Wang

1

36

126

Xavier Bresson

@xbresson

1 year

We are lucky to have a second talk by @mmbronstein "Geometric ML for designing new molecules" at #ICML2023

1

11

129

Xavier Bresson

@xbresson

5 years

Causality For Machine Learning by Bernhard Schölkopf "The article argues that the hard open problems of machine learning and AI are intrinsically related to causality, and explains how the field is beginning to understand them." A review paper with 136 references.

Stat.ML Papers

@StatMLPapers

5 years

Causality for Machine Learning. (arXiv:1911.10500v1 [cs.LG])

0

68

280

0

40

126

Xavier Bresson

@xbresson

3 years

Slides of my talk at DGL-KDD'21 : Video : with @vijaypradwi , L.Tuan, T.Laurent, Y.Bengio Built upon the works of @brunofmr , @loukasa_tweet , @julienmairal , @mialon_gregoire , @tianle_cai , @dom_beaini

Xavier Bresson "Graph Neural Networks with Learnable Structural and...

Workshop : Deep Learning on Graphs at KDD2021 (DGL-KDD’21)https://deep-learning-graphs.bitbucket.io/dlg-kdd21Abstract : Graph neural networks have become the...

www.youtube.com

Xavier Bresson

@xbresson

3 years

Thrilled to give two talks at ACM #KDD2021 . 1. Deep Learning on Graphs (DGL-KDD’21) Talk on Aug 14th 7pm PST 2. Applied Data Science (ADS) Talk on Aug 15th 10:45pm PST @kdd_news

1

26

157

0

35

124

Xavier Bresson

@xbresson

1 year

Terrific talk by @mmbronstein "Graph Rewiring in GNNs" #ICML2023

0

9

123

Xavier Bresson

@xbresson

7 months

Favorite feedbacks from Reviewer 2 :

Xavier Bresson

@xbresson

7 months

Favorite feedbacks from Reviewer 2 :

16

49

626

4

8

125

Xavier Bresson

@xbresson

1 month

. @JeffDean presenting "Exciting Trends in Machine Learning" at @NUSingapore 's Department of Computer Science. Jeff also generously spent time after his talk engaging with (very happy) students 😀

2

10

126

Xavier Bresson

@xbresson

1 year

On my way to #ICLR2023 in Rwanda! Thomas Laurent, James von Brecht and I will present "Long-Tailed Learning Requires Feature Learning" We introduce a theoretical study that demonstrates the importance of feature learning in achieving effective generalization.

4

13

125

Xavier Bresson

@xbresson

4 years

Well.. I have never received such a kind student feedback so I feel compelled to brag about it as it really made my day! 😅

4

1

121

Xavier Bresson

@xbresson

3 years

Just finished the teaching semester. One student wrote me a very kind and warm feedback :) This feels like the best teaching award!

2

119

Xavier Bresson

@xbresson

10 months

Minjie Wang @DGLGraph , Graph Neural Network at Scale: A Tale of Productivity and Efficiency

0

9

117

Xavier Bresson

@xbresson

1 year

An excellent introduction to the human genome, outlining the intricate process of genetic information flow DNA → mRNA → protein

0

28

116

Xavier Bresson

@xbresson

3 months

I was blown away deep learning can understand physics and chemistry differently from standard theories like PDEs, differential geometry etc As a physicist trained w/ these giant theories, I found it incredible how @ylecun , Y. Bengio, @geoffreyhinton have revolutionized science!

Mathieu Alain

@miniapeur

3 months

Tell me about one of the important turning points in your research career.

8

6

53

4

9

113

Xavier Bresson

@xbresson

4 months

Two exciting updates for the Learning on Graphs Conference! 1) Virtual conference from Nov 26th 2024 2) Join the first in-person conference from Sept 28-30 2025 Don't miss out on the opportunity to receive high-quality reviews!

Learning on Graphs Conference 2024

@LogConference

4 months

LoG Conference 2024 is back !!!👉 We are looking for more reviewers! We have a special emphasis on review quality via monetary rewards, a more focused conference topic, and low reviewer load (max 3 papers). But for this we need your help! Sign up here: !

2

50

120

2

24

114

Xavier Bresson

@xbresson

1 year

Our two recent submissions: 1. Theoretical paper is not good because it does not provide real-world SOTA and does not improve existing algorithms. 2. New algorithm paper with real-world SOTA is not good because it is not theoretical and not novel enough. 🙃

5

2

115

Xavier Bresson

@xbresson

4 years

My favorite textbooks on convex optimization: - Convex Optimization, S.Boyd, L.Vandenberghe Video lectures: - Introductory Lectures on Convex Optimization, Y.Nesterov Video lectures:

Course "Modern Algorithmic Optimization" (Yuriy Nesterov)

In this course, we present the most important research directions in modern optimization theory. The main topics of our interest are related to the provable ...

www.youtube.com

Xavier Bresson

@xbresson

4 years

Great talk by @ofirnachum on casting the RL Bellman dynamic programming problem as an unconstrained Fenchel-Rockafeller primal-dual convex optimization problem (easier to solve).

2

14

61

1

23

114

Xavier Bresson

@xbresson

2 years

Huge congrats to DGL team on this milestone release! The (sparse) matrix formulation of GNNs is quite exciting (more intuitive than MP) @DGLGraph @wenmingye @smolix And big thanks for implementing our graph Transformers @vijaypradwi w/ 10 lines of code😁

DeepGraphLibrary

@DGLGraph

2 years

DGL 1.0 has arrived! Huge milestone of the past 3+ years of development. 👉Check out the blog for the release summary and the highlight of the brand new DGL-Sparse package #DGL #GML

2

31

94

2

28

114

Xavier Bresson

@xbresson

5 months

Indeed, graphs are a scam -- an invention from mathematicians to control people! I can prove it -- it is well-known that data is truly i.i.d. (written in all machine learning textbooks). So there exists no relationship between data and graph representation is just an illusion.

Franz Srambical (no, not at icml any more)

@lemergenz

5 months

@xbresson graph learning is a scam, change my mind

1

4

6

8

113

Xavier Bresson

@xbresson

5 years

I taught my students Deep Graph Library (DGL) in my lecture on "Graph Neural Networks" today. It is a great resource to develop GNNs with @PyTorch . Kudos to the team @GraphDeep !

1

25

110

Xavier Bresson

@xbresson

1 year

New paper w/ @he_xiaoxin , T. Laurent, @BryanHooi1 "Explanations as Features: LLM-Based Features for Text-Attributed Graphs" ArXiv: GitHub:

2

31

108

Xavier Bresson

@xbresson

7 months

As a physicist, I was trained to simplify models to unveil their underlying first principles. Unfortunately, simplicity is the enemy of reviewer #2 in ML conferences. "Obscure technique and theorem are the touchstone in accepting new ML papers."

Physics In History

@PhysInHistory

7 months

26

177

1K

2

12

105

Xavier Bresson

@xbresson

4 years

I'd love @NeurIPSConf @icmlconf to adopt @openreviewnet bc it'd provide a great discussion forum for authors, reviewers and the AI *community*. I'd feel mentally better if I knew my answers could be seen/discussed by all researchers interested in my project.

0

9

105

Xavier Bresson

@xbresson

2 years

Steve Brunton @eigensteve (University of Washington) "Machine Learning for Scientific Discovery, with Examples in Fluid Mechanics"

3

2

104