Papers

Research Papers

* Denotes equal contribution or alphabetical authorship.

The Empirical Impact of Neural Parameter Symmetries, or Lack Thereof
Derek Lim*, Moe Putterman*, Robin Walters, Haggai Maron, Stefanie Jegelka
arXiv:2405.20231 (2024)
[arXiv]
Graph Metanetworks for Processing Diverse Neural Architectures
Derek Lim, Haggai Maron, Marc T. Law, Jonathan Lorraine, James Lucas
ICLR, Spotlight (2024)
[arXiv]
Structuring Representation Geometry with Rotationally Equivariant Contrastive Learning
Sharut Gupta*, Joshua Robinson*, Derek Lim, Soledad Villar, Stefanie Jegelka
ICLR (2024)
[arXiv] [code]
Expressive Sign Equivariant Networks for Spectral Geometric Learning
Derek Lim, Joshua Robinson, Stefanie Jegelka, Haggai Maron
NeurIPS, Spotlight (2023)
[arXiv] [code]
Equivariant Polynomials for Graph Neural Networks
Omri Puny*, Derek Lim*, Bobak Kiani*, Haggai Maron, Yaron Lipman
ICML, Oral (2023)
[arXiv] [code]
Graph Inductive Biases in Transformers without Message Passing
Liheng Ma*, Chen Lin*, Derek Lim, Adriana Romero-Soriano, Puneet K. Dokania, Mark Coates, Philip Torr, Ser-Nam Lim
ICML (2023)
[arXiv] [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
ICLR, Spotlight (2023)
[arXiv] [code] [workshop pdf] [LoGaG Reading Group Talk]
Understanding Doubly Stochastic Clustering
Tianjiao Ding, Derek Lim, René Vidal, Benjamin Haeffele
ICML (2022)
[pdf]
Equivariant Subgraph Aggregation Networks
Beatrice Bevilacqua*, Fabrizio Frasca*, Derek Lim*, Balasubramaniam Srinivasan, Chen Cai, Gopinath Balamurugan, Michael Bronstein, Haggai Maron
ICLR (2022), Spotlight (176 / 3391 submissions)
[pdf] [arXiv] [code]
[ML Street Talk Podcast] [WelcomeAIOverlords Interview] [LoGaG Reading Group Talk] [WeChat post (图与推荐)]
Counting Substructures with Higher-Order Graph Neural Networks: Possibility and Impossibility Results
Behrooz Tahmasebi, Derek Lim, Stefanie Jegelka
AISTATS, Oral (32 / 1689 submissions) (2023)
[arXiv]
Equivariant Manifold Flows
Isay Katsman*, Aaron Lou*, Derek Lim*, Qingxuan Jiang*, Ser-Nam Lim, Christopher De Sa
NeurIPS (2021)
Also in ICML INNF Workshop (2021)
[workshop pdf]

[arXiv]
Large Scale Learning on Non-Homophilous Graphs: New Benchmarks and Strong Simple Methods
Derek Lim*, Felix Hohne*, Xiuyu Li*, Sijia Linda Huang, Vaishnavi Gupta, Omkar Bhalerao, Ser-Nam Lim
NeurIPS (2021)
Previous version: New Benchmarks for Learning on Non-Homophilous Graphs
Workshop on Graph Learning Benchmarks (GLB 2021) at WWW (2021)
[workshop arXiv] [workshop pdf] [workshop data/code]

[arXiv] [data/code]
Doubly Stochastic Subspace Clustering
Derek Lim, René Vidal, Benjamin Haeffele
arXiv:2011.14859 (2020)
[arXiv] [code]
Neural Manifold Ordinary Differential Equations
Aaron Lou*, Derek Lim*, Isay Katsman*, Leo Huang*, Qingxuan Jiang, Ser-Nam Lim, and Christopher De Sa
NeurIPS (2020)
Also in ICML INNF Workshop, Spotlight (2020)
[arXiv] [code]
Expertise and Dynamics within Crowdsourced Musical Knowledge Curation: A Case Study of the Genius Platform
Derek Lim, and Austin R. Benson
International AAAI Conference on Web and Social Media, ICWSM (2021)
[arXiv] [code]
[Podcast] interview with Data Skeptic
\[HS(\rho_k(D_{2n})) = \Pi_{\frac{n}{\mathrm{gcd}(n,k)}} \cup \Pi_2\] \[HS(\rho(Q_8)) = \Pi_4\] Spectra of Convex Hulls of Matrix Groups
Eric Jankowski*, Charles R. Johnson*, and Derek Lim*
Linear Algebra and its Applications 593 (2020): 74-89
[arXiv] [doi]
The Doubly Stochastic Single Eigenvalue Problem: A Computational Approach
Amit Harlev*, Charles R. Johnson*, and Derek Lim*
Experimental Mathematics (2020)
[arXiv] [code] [doi]