no code implementations • 5 Feb 2025 • Fred Zhangzhi Peng, Zachary Bezemek, Sawan Patel, Sherwood Yao, Jarrid Rector-Brooks, Alexander Tong, Pranam Chatterjee
In this paper, we investigate how the order in which tokens are unmasked during masked diffusion models (MDMs) inference affects generative quality.
no code implementations • 23 Dec 2024 • Marta Skreta, Lazar Atanackovic, Avishek Joey Bose, Alexander Tong, Kirill Neklyudov
The Cambrian explosion of easily accessible pre-trained diffusion models suggests a demand for methods that combine multiple different pre-trained diffusion models without incurring the significant computational burden of re-training a larger combined model.
1 code implementation • 28 Oct 2024 • Xi Zhang, Yuan Pu, Yuki Kawamura, Andrew Loza, Yoshua Bengio, Dennis L. Shung, Alexander Tong
To address this, we propose Trajectory Flow Matching (TFM), which trains a Neural SDE in a simulation-free manner, bypassing backpropagation through the dynamics.
no code implementations • 10 Oct 2024 • Jarrid Rector-Brooks, Mohsin Hasan, Zhangzhi Peng, Zachary Quinn, Chenghao Liu, Sarthak Mittal, Nouha Dziri, Michael Bronstein, Yoshua Bengio, Pranam Chatterjee, Alexander Tong, Avishek Joey Bose
Generative modeling of discrete data underlies important applications spanning text-based agents like ChatGPT to the design of the very building blocks of life in protein sequences.
no code implementations • 26 Aug 2024 • Lazar Atanackovic, Xi Zhang, Brandon Amos, Mathieu Blanchette, Leo J. Lee, Yoshua Bengio, Alexander Tong, Kirill Neklyudov
Flow-based models allow for learning these dynamics at the population level - they model the evolution of the entire distribution of samples.
1 code implementation • 16 Jul 2024 • Alessandro Palma, Till Richter, Hanyi Zhang, Manuel Lubetzki, Alexander Tong, Andrea Dittadi, Fabian Theis
Generative modeling of single-cell RNA-seq data has shown invaluable potential in community-driven tasks such as trajectory inference, batch effect removal and gene expression generation.
2 code implementations • 20 Jun 2024 • Chen Liu, Ke Xu, Liangbo L. Shen, Guillaume Huguet, Zilong Wang, Alexander Tong, Danilo Bzdok, Jay Stewart, Jay C. Wang, Lucian V. Del Priore, Smita Krishnaswamy
We validate ImageFlowNet on three longitudinal medical image datasets depicting progression in geographic atrophy, multiple sclerosis, and glioblastoma, demonstrating its ability to effectively forecast disease progression and outperform existing methods.
1 code implementation • 30 May 2024 • Guillaume Huguet, James Vuckovic, Kilian Fatras, Eric Thibodeau-Laufer, Pablo Lemos, Riashat Islam, Cheng-Hao Liu, Jarrid Rector-Brooks, Tara Akhound-Sadegh, Michael Bronstein, Alexander Tong, Avishek Joey Bose
Proteins are essential for almost all biological processes and derive their diverse functions from complex 3D structures, which are in turn determined by their amino acid sequences.
1 code implementation • 23 May 2024 • Kacper Kapuśniak, Peter Potaptchik, Teodora Reu, Leo Zhang, Alexander Tong, Michael Bronstein, Avishek Joey Bose, Francesco Di Giovanni
Matching objectives underpin the success of modern generative models and rely on constructing conditional paths that transform a source distribution into a target distribution.
1 code implementation • 9 Feb 2024 • Tara Akhound-Sadegh, Jarrid Rector-Brooks, Avishek Joey Bose, Sarthak Mittal, Pablo Lemos, Cheng-Hao Liu, Marcin Sendera, Siamak Ravanbakhsh, Gauthier Gidel, Yoshua Bengio, Nikolay Malkin, Alexander Tong
Efficiently generating statistically independent samples from an unnormalized probability distribution, such as equilibrium samples of many-body systems, is a foundational problem in science.
1 code implementation • 4 Dec 2023 • Danqi Liao, Chen Liu, Benjamin W. Christensen, Alexander Tong, Guillaume Huguet, Guy Wolf, Maximilian Nickel, Ian Adelstein, Smita Krishnaswamy
Entropy and mutual information in neural networks provide rich information on the learning process, but they have proven difficult to compute reliably in high dimensions.
1 code implementation • 16 Oct 2023 • Kirill Neklyudov, Rob Brekelmans, Alexander Tong, Lazar Atanackovic, Qiang Liu, Alireza Makhzani
The dynamical formulation of the optimal transport can be extended through various choices of the underlying geometry (kinetic energy), and the regularization of density paths (potential energy).
no code implementations • 5 Oct 2023 • Trang Nguyen, Alexander Tong, Kanika Madan, Yoshua Bengio, Dianbo Liu
Understanding causal relationships within Gene Regulatory Networks (GRNs) is essential for unraveling the gene interactions in cellular processes.
1 code implementation • 3 Oct 2023 • Avishek Joey Bose, Tara Akhound-Sadegh, Guillaume Huguet, Kilian Fatras, Jarrid Rector-Brooks, Cheng-Hao Liu, Andrei Cristian Nica, Maksym Korablyov, Michael Bronstein, Alexander Tong
The computational design of novel protein structures has the potential to impact numerous scientific disciplines greatly.
1 code implementation • 7 Jul 2023 • Alexander Tong, Nikolay Malkin, Kilian Fatras, Lazar Atanackovic, Yanlei Zhang, Guillaume Huguet, Guy Wolf, Yoshua Bengio
We present simulation-free score and flow matching ([SF]$^2$M), a simulation-free objective for inferring stochastic dynamics given unpaired samples drawn from arbitrary source and target distributions.
no code implementations • 5 Jun 2023 • Samuel Leone, Aarthi Venkat, Guillaume Huguet, Alexander Tong, Guy Wolf, Smita Krishnaswamy
GFMMD is defined via an optimal witness function that is both smooth on the graph and maximizes difference in expectation between the pair of distributions on the graph.
1 code implementation • 1 Jun 2023 • Oluwadamilola Fasina, Guillaume Huguet, Alexander Tong, Yanlei Zhang, Guy Wolf, Maximilian Nickel, Ian Adelstein, Smita Krishnaswamy
Although data diffusion embeddings are ubiquitous in unsupervised learning and have proven to be a viable technique for uncovering the underlying intrinsic geometry of data, diffusion embeddings are inherently limited due to their discrete nature.
1 code implementation • International Conference on Machine Learning Workshop on TAGML 2023 • Danqi Liao*, Chen Liu*, Alexander Tong, Guillaume Huguet, Guy Wolf, Maximilian Nickel, Ian Adelstein, Smita Krishnaswamy
We also see that there is an increase in DSMI with the class label over time.
1 code implementation • NeurIPS 2023 • Guillaume Huguet, Alexander Tong, Edward De Brouwer, Yanlei Zhang, Guy Wolf, Ian Adelstein, Smita Krishnaswamy
Finally, we show that parameters of our more general method can be configured to give results similar to PHATE (a state-of-the-art diffusion based manifold learning method) as well as SNE (an attraction/repulsion neighborhood based method that forms the basis of t-SNE).
1 code implementation • NeurIPS 2023 • Lazar Atanackovic, Alexander Tong, Bo wang, Leo J. Lee, Yoshua Bengio, Jason Hartford
In this paper we leverage the fact that it is possible to estimate the "velocity" of gene expression with RNA velocity techniques to develop an approach that addresses both challenges.
3 code implementations • 1 Feb 2023 • Alexander Tong, Kilian Fatras, Nikolay Malkin, Guillaume Huguet, Yanlei Zhang, Jarrid Rector-Brooks, Guy Wolf, Yoshua Bengio
CFM features a stable regression objective like that used to train the stochastic flow in diffusion models but enjoys the efficient inference of deterministic flow models.
no code implementations • 2 Nov 2022 • Guillaume Huguet, Alexander Tong, María Ramos Zapatero, Christopher J. Tape, Guy Wolf, Smita Krishnaswamy
Efficient computation of optimal transport distance between distributions is of growing importance in data science.
no code implementations • 15 Aug 2022 • Alexander Tong, Frederik Wenkel, Dhananjay Bhaskar, Kincaid MacDonald, Jackson Grady, Michael Perlmutter, Smita Krishnaswamy, Guy Wolf
We propose a new graph neural network (GNN) module, based on relaxations of recently proposed geometric scattering transforms, which consist of a cascade of graph wavelet filters.
no code implementations • 29 Jun 2022 • Guillaume Huguet, D. S. Magruder, Alexander Tong, Oluwadamilola Fasina, Manik Kuchroo, Guy Wolf, Smita Krishnaswamy
In GAE the latent space distance between points is regularized to match a novel multiscale geodesic distance on the data manifold that we define.
no code implementations • 28 Mar 2022 • Guillaume Huguet, Alexander Tong, Bastian Rieck, Jessie Huang, Manik Kuchroo, Matthew Hirn, Guy Wolf, Smita Krishnaswamy
From a geometric perspective, we obtain convergence bounds based on the smallest transition probability and the radius of the data, whereas from a spectral perspective, our bounds are based on the eigenspectrum of the diffusion kernel.
1 code implementation • 19 Nov 2021 • Michal Gerasimiuk, Dennis Shung, Alexander Tong, Adrian Stanley, Michael Schultz, Jeffrey Ngu, Loren Laine, Guy Wolf, Smita Krishnaswamy
In particular, in EHR data, some variables are {\em missing not at random (MNAR)} but deliberately not collected and thus are a source of information.
no code implementations • 26 Jul 2021 • Alexander Tong, Guillaume Huguet, Dennis Shung, Amine Natik, Manik Kuchroo, Guillaume Lajoie, Guy Wolf, Smita Krishnaswamy
We propose to compare and organize such datasets of graph signals by using an earth mover's distance (EMD) with a geodesic cost over the underlying graph.
1 code implementation • 25 Feb 2021 • Alexander Tong, Guillaume Huguet, Amine Natik, Kincaid MacDonald, Manik Kuchroo, Ronald Coifman, Guy Wolf, Smita Krishnaswamy
Here, Diffusion EMD can derive distances between patients on the manifold of cells at least two orders of magnitude faster than equally accurate methods.
no code implementations • 12 Feb 2021 • Manik Kuchroo, Abhinav Godavarthi, Alexander Tong, Guy Wolf, Smita Krishnaswamy
We propose a method called integrated diffusion for combining multimodal datasets, or data gathered via several different measurements on the same system, to create a joint data diffusion operator.
no code implementations • 6 Oct 2020 • Alexander Tong, Frederik Wenkel, Kincaid MacDonald, Smita Krishnaswamy, Guy Wolf
We propose a new graph neural network (GNN) module, based on relaxations of recently proposed geometric scattering transforms, which consist of a cascade of graph wavelet filters.
2 code implementations • 12 Jun 2020 • Egbert Castro, Andrew Benz, Alexander Tong, Guy Wolf, Smita Krishnaswamy
We propose a geometric scattering autoencoder (GSAE) network for learning such graph embeddings.
2 code implementations • ICML 2020 • Alexander Tong, Jessie Huang, Guy Wolf, David van Dijk, Smita Krishnaswamy
To address this issue, we establish a link between continuous normalizing flows and dynamic optimal transport, that allows us to model the expected paths of points over time.
1 code implementation • 14 Nov 2019 • Michael Perlmutter, Alexander Tong, Feng Gao, Guy Wolf, Matthew Hirn
As a result, the proposed construction unifies and extends known theoretical results for many of the existing graph scattering architectures.
no code implementations • 26 May 2019 • Alexander Tong, Guy Wolf, Smita Krishnaswamy
We show that this procedure successfully detects unseen anomalies with guarantees on those that have a certain Wasserstein distance from the data or corrupted training set.
no code implementations • ICLR 2019 • Alexander Tong, David van Dijk, Jay Stanley, Guy Wolf, Smita Krishnaswamy
First, we show a synthetic example that the graph-structured layer can reveal topological features of the data.
1 code implementation • ICLR 2019 • Alexander Tong, David van Dijk, Jay S. Stanley III, Matthew Amodio, Kristina Yim, Rebecca Muhle, James Noonan, Guy Wolf, Smita Krishnaswamy
Taking inspiration from spatial organization and localization of neuron activations in biological networks, we use a graph Laplacian penalty to structure the activations within a layer.