Haggai Maron

I am an Assistant Professor at the Faculty of Electrical and Computer Engineering at the Technion. I am also a senior research scientist at NVIDIA Research and a member of NVIDIA's TLV lab. My primary research interest is in machine learning, with a focus on deep learning for structured data. Specifically, I study how to apply deep learning techniques to sets, graphs, point clouds, surfaces, weight spaces and other mathematical objects that have an inherent symmetry structure. My goal is twofold: first, to understand and design deep learning architectures from a theoretical perspective, for example, by analyzing their expressive power; and second, to demonstrate their practical effectiveness on real-world problems involving structured data. I completed my Ph.D. in 2019 at the Weizmann Institute of Science under the supervision of Prof. Yaron Lipman.
You can get an idea of what I am working on by taking a look at these three recent talks I gave:

You can also listen to a recent podcast with me on graph neural networks (hebrew).

Email: hmaron (at) nvidia.com, Google scholar page, GitHub page

Group

Fabrizio Frasca (Postdoc, 2024-today), Yam Eitan (PhD, 2024 - today), Guy Bar-Shalom (PhD, 2023 - today, joint supervision with Ran El-Yaniv), Matan Ostrovsky (PhD, 2023 - today), Yoav Gelberg (PhD, 2024-today, joint supervision with Michael Bronstein), Ran Elbaz (Msc, 2023-today), Ofir Haim (MSc, 2023-today, joint supervision with Shie Mannor), Yaniv Galron (MSc, 2023-today, joint supervision with Eran Treister), Edan Kinderman (MSc, 2023-today, joint supervision with Daniel Soudry), Yuval Aidan (MSc, 2023-today, joint supervision with Ayellet Tal).
Close student / postdoc collaborators: Beatrice Bevilacqua (2021-today), Derek Lim (2021-today), Moshe Eliasof (2022-today), Aviv Navon (2021-today), Aviv Shamsian (2022-today).

News

4 papers accepted to NeurIPS 2024.
Proud to be the recipient of the Alon scholarship for the Integration of Outstanding Faculty.
5 papers accepted to ICML 2024.
See my recent talk on Equivaraint architectures for learning in deep weight spaces .
A new blog post on Equivaraint architectures for learning in deep weight spaces .
I will serve as an area chair at NeurIPS 2023.
See our recent tutorial on Exploring the practical and theoretical landscape of expressive graph neural networks given at the Learning on Graphs Conference . With With Fabrizio Frasca and Beatrice Bevilacqua.
A new blog post on Subggraph GNNs on Towards Data Science.
Our ICML 2020 paper On Learning Sets of Symmetric Elements received the Outstanding paper award (best paper award). See this interview for more details.

Teaching

2024/winter (Technion): Topics in learning on graphs
2024/Spring (Technion): Deep Learning and groups
2023/winter (Technion): Topics in learning on graphs
2019/spring (WIS): Geometric and Algebraic Methods in Deep Learning
2018/winter (WIS): Geometry and Deep Learning

Tweets by HaggaiMaron

Publications

Topological Blind Spots: Understanding and Extending Topological Deep Learning Through the Lens of Expressivity

Yam Eitan, Yoav Gelberg, Guy Bar-Shalom, Fabrizio Frasca, Michael Bronstein, Haggai Maron
Technical report

Abstract Paper

A Flexible, Equivariant Framework for Subgraph GNNs via Graph Products and Graph Coarsening

Guy Bar-Shalom, Yam Eitan, Fabrizio Frasca, Haggai Maron
38th Annual Conference on Neural Information Processing Systems (NeurIPS 2024)

Abstract Paper

Fast Encoder-Based 3D from Casual Videos via Point Track Processing

Yoni Kasten, Wuyue Lu, Haggai Maron
38th Annual Conference on Neural Information Processing Systems (NeurIPS 2024)

Abstract Paper

GRANOLA: Adaptive Normalization for Graph Neural Networks

Moshe Eliasof, Beatrice Bevilacqua, Carola-Bibiane Schönlieb, Haggai Maron
38th Annual Conference on Neural Information Processing Systems (NeurIPS 2024)

Abstract Paper

The Empirical Impact of Neural Parameter Symmetries, or Lack Thereof

Derek Lim*, Theo (Moe) Putterman*, Robin Walters, Haggai Maron, Stefanie Jegelka
38th Annual Conference on Neural Information Processing Systems (NeurIPS 2024)
(A shorter version also appeared in HiLD 2024: 2nd Workshop on High-dimensional Learning Dynamics @ ICML 2024 winning the Best paper award)

Abstract Paper (Workshop version) Paper (Full version)

Future Directions in Foundations of Graph Machine Learning

Christopher Morris, Nadav Dym, Haggai Maron, İsmail İlkan Ceylan, Fabrizio Frasca, Ron Levie, Derek Lim, Michael Bronstein, Martin Grohe, Stefanie Jegelka
International Conference on Machine Learning (ICML) 2024

Abstract Paper

On the Expressive Power of Spectral Invariant Graph Neural Networks

Bohang Zhang, Lingxiao Zhao, Haggai Maron
International Conference on Machine Learning (ICML) 2024

Abstract Paper

Equivariant Deep Weight Space Alignment

Aviv Navon, Aviv Shamsian, Ethan Fetaya, Gal Chechik, Nadav Dym, Haggai Maron
International Conference on Machine Learning (ICML) 2024

Abstract Paper GitHub

Subgraphormer: Unifying Subgraph GNNs and Graph Transformers via Graph Products

Guy Bar-Shalom, Beatrice Bevilacqua, Haggai Maron
International Conference on Machine Learning (ICML) 2024
(A preliminary version appeared in NeurIPS 2023 New Frontiers in Graph Learning Workshop )

Abstract Paper

Improved Generalization of Weight Space Networks via Augmentationss

Aviv Shamsian, Aviv Navon, David W. Zhang, Yan Zhang, Ethan Fetaya, Gal Chechik, Haggai Maron
International Conference on Machine Learning (ICML) 2024
(A preliminary version appeared in Symmetry and Geometry in Neural Representations Workshop, 37th Annual Conference on Neural Information Processing Systems (NeurIPS 2023) as an Oral Presentation).

Abstract Paper GitHub

Efficient Subgraph GNNs by Learning Effective Selection Policies

Beatrice Bevilacqua, Moshe Eliasof, Eli Meirom, Bruno Ribeiro, Haggai Maron
International Conference on Learning Representations (ICLR) 2024

Abstract Paper

Graph Metanetworks for Processing Diverse Neural Architectures

Derek Lim, Haggai Maron, Marc T. Law, Jonathan Lorraine, James Lucas
International Conference on Learning Representations (ICLR) 2024

Spotlight Presentation

Abstract Paper

Expressive Sign Equivariant Networks for Spectral Geometric Learning

Derek Lim, Joshua Robinson, Stefanie Jegelka, Haggai Maron
37th Annual Conference on Neural Information Processing Systems (NeurIPS 2023)

Spotlight Presentation

Abstract Paper

Norm-guided latent space exploration for text-to-image generation

Dvir Samuel, Rami Ben-Ari, Nir Darshan, Haggai Maron, Gal Chechik
37th Annual Conference on Neural Information Processing Systems (NeurIPS 2023)

Abstract Paper Code

Equivariant Architectures for Learning in Deep Weight Spaces

Aviv Navon, Aviv Shamsian, Idan Achituve, Ethan Fetaya, Gal Chechik, Haggai Maron
International Conference on Machine Learning (ICML) 2023

Oral Presentation

Abstract Paper Talk Code Blog

Graph Positional Encoding via Random Feature Propagation

Moshe Eliasof, Fabrizio Frasca, Beatrice Bevilacqua, Eran Treister, Gal Chechik, Haggai Maron
International Conference on Machine Learning (ICML) 2023

Abstract Paper

Equivariant Polynomials for Graph Neural Networks

Omri Puny, Derek Lim, Bobak T. Kiani, Haggai Maron, Yaron Lipman
International Conference on Machine Learning (ICML) 2023

Oral Presentation

Abstract Paper Code

Sign and Basis Invariant Networks for Spectral Graph Representation Learning

Derek Lim*, Joshua Robinson*, Lingxiao Zhao, Tess Smidt, Suvrit Sra, Haggai Maron, Stefanie Jegelka
International Conference on Learning Representations (ICLR 2023)

notable-top-25% paper (AKA Spotlight)

Abstract Paper Code

Understanding and Extending Subgraph GNNs by Rethinking Their Symmetries

Fabrizio Frasca*, Beatrice Bevilacqua*, Michael M. Bronstein, Haggai Maron
36th Annual Conference on Neural Information Processing Systems (NeurIPS 2022)

Oral presentation (1.7% acceptance rate)

Abstract Paper Code Talk

Generalized Laplacian Positional Encoding for Graph Representation Learning

Sohir Maskey*, Ali Parviz*, Maximilian Thiessen, Hannes Stärk, Ylli Sadikaj, Haggai Maron
NeurIPS 2022 Workshop on Symmetry and Geometry in Neural Representations

Abstract Paper

A Simple and Universal Rotation Equivariant Point-cloud Network

Ben Finkelshtein, Chaim Baskin, Haggai Maron, Nadav Dym
Workshop on Topology, Algebra, and Geometry in Learning, ICML 2022

Abstract Paper Code

Multi-Task Learning as a Bargaining Game

Aviv Navon, Aviv Shamsian, Idan Achituve, Haggai Maron, Kenji Kawaguchi,Gal Chechik,Ethan Fetaya
International Conference on Machine Learning (ICML) 2022

Abstract Paper

Optimizing Tensor Network Contraction Using Reinforcement Learning

Eli A Meirom, Haggai Maron, Shie Mannor, Gal Chechik
International Conference on Machine Learning (ICML) 2022
Also in The Multi-disciplinary Conference on Reinforcement Learning and Decision Making, RLDM 2022

Abstract Paper

Federated Learning with Heterogeneous Architectures using Graph HyperNetworks

Or Litany, Haggai Maron, David Acuna, Jan Kautz, Gal Chechik, Sanja Fidler
Technical report, January 2022

Abstract Paper

Equivariant Subgraph Aggregation Networks

Beatrice Bevilacqua*, Fabrizio Frasca*, Derek Lim*, Balasubramaniam Srinivasan, Chen Cai, Gopinath Balamurugan, Michael M. Bronstein, Haggai Maron (*equal contribution)
International Conference on Learning Representations (ICLR) 2022

Spotlight presentation (5% acceptance rate)

Abstract Paper GitHub Blog post Talk

Weisfeiler and Leman go Machine Learning: The Story so far

Christopher Morris, Yaron Lipman, Haggai Maron, Bastian Rieck, Nils M. Kriege, Martin Grohe, Matthias Fey, Karsten Borgwardt
Technical report, December 2021

Abstract Paper

StyleGAN-NADA: CLIP-Guided Domain Adaptation of Image Generators

Rinon Gal, Or Patashnik , Haggai Maron , Gal Chechik , Daniel Cohen-Or
ACM SIGGRAPH 2022

Abstract Paper Code Interactive demo

Deep Permutation Equivariant Structure from Motion

Dror Moran, Hodaya Koslowsky, Yoni Kasten, Haggai Maron, Meirav Galun, Ronen Basri
International Conference on Computer Vision (ICCV) 2021

Oral presentation (3% acceptance rate)

Abstract Paper Code

Secondary Vertex Finding in Jets with Neural Networks

Jonathan Shlomi, Sanmay Ganguly, Eilam Gross, Kyle Cranmer, Yaron Lipman, Hadar Serviansky, Haggai Maron, Nimrod Segol
European Physical Journal C, 2021

Abstract Paper

Scene-Agnostic Multi-Microphone Speech Dereverberation

Yochai Yemini, Ethan Fetaya, Haggai Maron, Sharon Gannot
INTERSPEECH 2021

Abstract Paper Code

From Local Structures to Size Generalization in Graph Neural Networks

Gilad Yehudai, Ethan Fetaya, Eli Meirom, Gal Chechik, Haggai Maron
International Conference on Machine Learning (ICML) 2021

Abstract Paper

Controlling Graph Dynamics with Reinforcement Learning and Graph Neural Networks

Eli A Meirom, Haggai Maron, Shie Mannor, Gal Chechik
International Conference on Machine Learning (ICML) 2021

Abstract Paper

On the Universality of Rotation Equivariant Point Cloud Networks

Nadav Dym, Haggai Maron
International Conference on Learning Representations (ICLR) 2021

Abstract Paper

Auxiliary Learning by Implicit Differentiation

Aviv Navon*, Idan Achituve*, Haggai Maron, Gal Chechik**, Ethan Fetaya** (*/** equal contribution)
International Conference on Learning Representations (ICLR) 2021

Abstract Paper GitHub

Self-Supervised Learning for Domain Adaptation on Point-Clouds

Idan Achituve, Haggai Maron, Gal Chechik
Winter Conference on Applications of Computer Vision (WACV), 2021

Abstract Paper GitHub

Set2Graph: Learning Graphs From Sets

Hadar Serviansky, Nimrod Segol, Jonathan Shlomi, Kyle Cranmer, Eilam Gross, Haggai Maron, Yaron Lipman
34th Annual Conference on Neural Information Processing Systems (NeurIPS 2020)

Abstract Paper Code

On Learning Sets of Symmetric Elements

Haggai Maron, Or Litany, Gal Chechik, Ethan Fetaya
International Conference on Machine Learning (ICML) 2020

ICML 2020 outstanding paper award

Abstract Paper Code Video Slides Interview

Learning Algebraic Multigrid Using Graph Neural Networks

Ilay Luz, Meirav Galun, Haggai Maron, Ronen Basri, Irad Yavneh
International Conference on Machine Learning (ICML) 2020

Abstract Paper Video+Slides Code

Open Problems: Approximation Power of Invariant Graph Networks

Haggai Maron, Heli Ben-Hamu, Yaron Lipman
NeurIPS 2019 Graph Representation Learning Workshop

Abstract Paper Slides Talk (go to 1:15:00)

Ph.D. Thesis

Haggai Maron
Weizmann Institute of Science, 2019

Abstract Paper

Deep and Convex Shape Analysis

Haggai Maron
SIGGRAPH 2019 Doctoral Consortium

Abstract Paper Poster

Provably Powerful Graph Networks

Haggai Maron*, Heli Ben-Hamu*, Hadar Serviansky*, Yaron Lipman (*equal contribution)
33rd Annual Conference on Neural Information Processing Systems (NeurIPS 2019)

Abstract Arxiv GitHub (TensorFlow) GitHub (PyTorch) Blog post Poster

Controlling Neural Level Sets

Matan Atzmon, Niv Haim, Lior Yariv, Ofer Israelov, Haggai Maron, Yaron Lipman
33rd Annual Conference on Neural Information Processing Systems (NeurIPS 2019)

Abstract Arxiv Code Poster

Surface Networks via General Covers

Niv Haim*, Nimrod Segol*, Heli Ben-Hamu, Haggai Maron, Yaron Lipman (*equal contribution)
International Conference on Computer Vision (ICCV) 2019

Abstract Arxiv

On the Universality of Invariant Networks

Haggai Maron, Ethan Fetaya, Nimrod Segol, Yaron Lipman
International Conference on Machine Learning (ICML) 2019

Abstract Arxiv Poster Video Blog post

Invariant and Equivariant Graph Networks

Haggai Maron, Heli Ben-Hamu, Nadav Shamir and Yaron Lipman
International Conference on Learning Representations (ICLR) 2019

Abstract Arxiv GitHub Poster Blog post

Sinkhorn Algorithm for Lifted Assignment Problems

Yam Kushinsky, Haggai Maron, Nadav Dym and Yaron Lipman
SIAM Journal on Imaging Sciences, 2019

Abstract Arxiv

(Probably) Concave Graph Matching

Haggai Maron and Yaron Lipman
32nd Annual Conference on Neural Information Processing Systems (NeurIPS 2018)

spotlight presentation (3.5% acceptance rate)

Abstract Arxiv Poster Short Video GitHub

Multi-chart Generative Surface Modeling

Heli Ben-Hamu, Haggai Maron, Itay Kezurer, Gal Avineri and Yaron Lipman
ACM SIGGRAPH Asia 2018

Abstract Arxiv GitHub

Point Convolutional Neural Networks by Extension Operators

Matan Atzmon*, Haggai Maron* and Yaron Lipman (*equal contribution)
ACM SIGGRAPH 2018

Abstract Arxiv GitHub Slides

DS++: A Flexible, Scalable and Provably Tight Relaxation for Matching Problems

Nadav Dym*, Haggai Maron* and Yaron Lipman (*equal contribution)
ACM SIGGRAPH ASIA 2017

Abstract Arxiv GitHub Slides

Convolutional Neural Networks on Surfaces via Seamless Toric Covers

Haggai Maron, Meirav Galun, Noam Aigerman, Miri Trope, Nadav Dym, Ersin Yumer, Vladimir G. Kim and Yaron Lipman
ACM SIGGRAPH 2017

Abstract Paper (low res) GitHub Data Slides Video

Point Registration via Efficient Convex Relaxation

Haggai Maron, Nadav Dym, Itay Kezurer, Shahar Kovalsky and Yaron Lipman
ACM SIGGRAPH 2016

Abstract Paper (low res) GitHub Slides Video

Passive Light and Viewpoint Sensitive Display of 3D Content

Anat Levin, Haggai Maron and Michal Yarom
International Conference on Computational Photography (ICCP) 2016

Abstract Paper Paper+Supplementary