no code implementations • 3 Feb 2024 • Christopher Morris, Nadav Dym, Haggai Maron, İsmail İlkan Ceylan, Fabrizio Frasca, Ron Levie, Derek Lim, Michael Bronstein, Martin Grohe, Stefanie Jegelka
Machine learning on graphs, especially using graph neural networks (GNNs), has seen a surge in interest due to the wide availability of graph data across a broad spectrum of disciplines, from life to social and engineering sciences.
no code implementations • 7 Dec 2023 • Derek Lim, Haggai Maron, Marc T. Law, Jonathan Lorraine, James Lucas
However, those works developed architectures tailored to specific networks such as MLPs and CNNs without normalization layers, and generalizing such architectures to other types of networks can be challenging.
1 code implementation • NeurIPS 2023 • Derek Lim, Joshua Robinson, Stefanie Jegelka, Haggai Maron
In this work, we demonstrate the benefits of sign equivariance for these tasks.
1 code implementation • 24 Jun 2023 • Sharut Gupta, Joshua Robinson, Derek Lim, Soledad Villar, Stefanie Jegelka
Specifically, in the contrastive learning setting, we introduce an equivariance objective and theoretically prove that its minima forces augmentations on input space to correspond to rotations on the spherical embedding space.
1 code implementation • 27 May 2023 • Liheng Ma, Chen Lin, Derek Lim, Adriana Romero-Soriano, Puneet K. Dokania, Mark Coates, Philip Torr, Ser-Nam Lim
Graph inductive biases are crucial for Graph Transformers, and previous works incorporate them using message-passing modules and/or positional encodings.
Ranked #1 on Node Classification on PATTERN
no code implementations • 22 Feb 2023 • Omri Puny, Derek Lim, Bobak T. Kiani, Haggai Maron, Yaron Lipman
This paper introduces an alternative expressive power hierarchy based on the ability of GNNs to calculate equivariant polynomials of a certain degree.
2 code implementations • 25 Feb 2022 • Derek Lim, Joshua Robinson, Lingxiao Zhao, Tess Smidt, Suvrit Sra, Haggai Maron, Stefanie Jegelka
We introduce SignNet and BasisNet -- new neural architectures that are invariant to two key symmetries displayed by eigenvectors: (i) sign flips, since if $v$ is an eigenvector then so is $-v$; and (ii) more general basis symmetries, which occur in higher dimensional eigenspaces with infinitely many choices of basis eigenvectors.
Ranked #10 on Graph Regression on ZINC-500k
3 code implementations • NeurIPS 2021 • Derek Lim, Felix Hohne, Xiuyu Li, Sijia Linda Huang, Vaishnavi Gupta, Omkar Bhalerao, Ser-Nam Lim
Many widely used datasets for graph machine learning tasks have generally been homophilous, where nodes with similar labels connect to each other.
Ranked #2 on Node Classification on wiki
Graph Learning Node Classification on Non-Homophilic (Heterophilic) Graphs
1 code implementation • ICLR 2022 • Beatrice Bevilacqua, Fabrizio Frasca, Derek Lim, Balasubramaniam Srinivasan, Chen Cai, Gopinath Balamurugan, Michael M. Bronstein, Haggai Maron
Thus, we propose to represent each graph as a set of subgraphs derived by some predefined policy, and to process it using a suitable equivariant architecture.
1 code implementation • NeurIPS 2021 • Isay Katsman, Aaron Lou, Derek Lim, Qingxuan Jiang, Ser-Nam Lim, Christopher De Sa
Tractably modelling distributions over manifolds has long been an important goal in the natural sciences.
1 code implementation • 3 Apr 2021 • Derek Lim, Xiuyu Li, Felix Hohne, Ser-Nam Lim
Much data with graph structures satisfy the principle of homophily, meaning that connected nodes tend to be similar with respect to a specific attribute.
Ranked #4 on Node Classification on Yelp-Fraud
no code implementations • 6 Dec 2020 • Behrooz Tahmasebi, Derek Lim, Stefanie Jegelka
While message passing Graph Neural Networks (GNNs) have become increasingly popular architectures for learning with graphs, recent works have revealed important shortcomings in their expressive power.
1 code implementation • 30 Nov 2020 • Derek Lim, René Vidal, Benjamin D. Haeffele
Many state-of-the-art subspace clustering methods follow a two-step process by first constructing an affinity matrix between data points and then applying spectral clustering to this affinity.
Ranked #1 on Image Clustering on UMist
3 code implementations • NeurIPS 2020 • Aaron Lou, Derek Lim, Isay Katsman, Leo Huang, Qingxuan Jiang, Ser-Nam Lim, Christopher De Sa
To better conform to data geometry, recent deep generative modelling techniques adapt Euclidean constructions to non-Euclidean spaces.
1 code implementation • 15 Jun 2020 • Derek Lim, Austin R. Benson
For example, expertise on song annotations follows a "U shape" where experts are both early and late contributors with non-experts contributing intermediately; we develop a user utility model that captures such behavior.
1 code implementation • 9 Aug 2019 • Amit Harlev, Charles R. Johnson, Derek Lim
The problem of determining $DS_n$, the complex numbers that occur as an eigenvalue of an $n$-by-$n$ doubly stochastic matrix, has been a target of study for some time.
Spectral Theory 15-04, 15A18, 15A29, 15B51