no code implementations • 26 Feb 2024 • Masatoshi Uehara, Yulai Zhao, Kevin Black, Ehsan Hajiramezanali, Gabriele Scalia, Nathaniel Lee Diamant, Alex M Tseng, Sergey Levine, Tommaso Biancalani
It is natural to frame this as a reinforcement learning (RL) problem, in which the objective is to fine-tune a diffusion model to maximize a reward function that corresponds to some property.
no code implementations • 23 Feb 2024 • Masatoshi Uehara, Yulai Zhao, Kevin Black, Ehsan Hajiramezanali, Gabriele Scalia, Nathaniel Lee Diamant, Alex M Tseng, Tommaso Biancalani, Sergey Levine
Diffusion models excel at capturing complex data distributions, such as those of natural images and proteins.
no code implementations • 29 Jan 2024 • Romain Lopez, Jan-Christian Huetter, Ehsan Hajiramezanali, Jonathan Pritchard, Aviv Regev
Finally, we introduce a novel methodology for fitting comparative DGMs that improves the treatment of multiple data sources via multi-objective optimization and that helps adjust the hyperparameter for the regularization in an interpretable manner, using constrained optimization.
1 code implementation • 1 Nov 2023 • Nathaniel Diamant, Ehsan Hajiramezanali, Tommaso Biancalani, Gabriele Scalia
SPICE is compatible with two different efficient-to-compute conformal scores, one oracle-optimal for marginal coverage (SPICE-ND) and the other asymptotically optimal for conditional coverage (SPICE-HPD).
1 code implementation • 11 May 2023 • Max W. Shen, Emmanuel Bengio, Ehsan Hajiramezanali, Andreas Loukas, Kyunghyun Cho, Tommaso Biancalani
We investigate how to learn better flows, and propose (i) prioritized replay training of high-reward $x$, (ii) relative edge flow policy parametrization, and (iii) a novel guided trajectory balance objective, and show how it can solve a substructure credit assignment problem.
no code implementations • 21 Oct 2022 • Max W. Shen, Ehsan Hajiramezanali, Gabriele Scalia, Alex Tseng, Nathaniel Diamant, Tommaso Biancalani, Andreas Loukas
How much explicit guidance is necessary for conditional diffusion?
no code implementations • 5 Aug 2022 • Talip Ucar, Ehsan Hajiramezanali
We conduct extensive experiments on a variety of synthetic and real-world data, demonstrating that the XTab can be used to obtain the global feature importance that is not sensitive to sub-optimal model initialisation.
no code implementations • ICLR 2022 • Arman Hasanzadeh, Ehsan Hajiramezanali, Nick Duffield, Xiaoning Qian
Multi-omics data analysis has the potential to discover hidden molecular interactions, revealing potential regulatory and/or signal transduction pathways for cellular processes of interest when studying life and disease systems.
no code implementations • 15 Dec 2021 • Arman Hasanzadeh, Mohammadreza Armandpour, Ehsan Hajiramezanali, Mingyuan Zhou, Nick Duffield, Krishna Narayanan
By learning distributional representations, we provide uncertainty estimates in downstream graph analytics tasks and increase the expressive power of the predictive model.
1 code implementation • NeurIPS 2021 • Talip Ucar, Ehsan Hajiramezanali, Lindsay Edwards
Self-supervised learning has been shown to be very effective in learning useful representations, and yet much of the success is achieved in data types such as images, audio, and text.
Ranked #4 on Unsupervised MNIST on MNIST
no code implementations • 29 Sep 2021 • Ehsan Hajiramezanali, Talip Ucar, Lindsay Edwards
First, they are not stochastic processes, leading to poor uncertainty estimations over their predictions.
1 code implementation • 4 Apr 2021 • Seyednami Niyakan, Ehsan Hajiramezanali, Shahin Boluki, Siamak Zamani Dadaneh, Xiaoning Qian
We develop a new method -- SimCD -- that explicitly models cell heterogeneity and dynamic differential changes in one unified hierarchical gamma-negative binomial (hGNB) model, allowing simultaneous cell clustering and differential expression analysis for scRNA-seq data.
1 code implementation • NeurIPS 2020 • Ehsan Hajiramezanali, Arman Hasanzadeh, Nick Duffield, Krishna R Narayanan, Xiaoning Qian
High-throughput molecular profiling technologies have produced high-dimensional multi-omics data, enabling systematic understanding of living systems at the genome scale.
1 code implementation • ICML 2020 • Arman Hasanzadeh, Ehsan Hajiramezanali, Shahin Boluki, Mingyuan Zhou, Nick Duffield, Krishna Narayanan, Xiaoning Qian
We propose a unified framework for adaptive connection sampling in graph neural networks (GNNs) that generalizes existing stochastic regularization methods for training GNNs.
no code implementations • 28 Oct 2019 • Ehsan Hajiramezanali, Arman Hasanzadeh, Nick Duffield, Krishna Narayanan, Mingyuan Zhou, Xiaoning Qian
Stochastic recurrent neural networks with latent random variables of complex dependency structures have shown to be more successful in modeling sequential data than deterministic deep models.
2 code implementations • NeurIPS 2019 • Ehsan Hajiramezanali, Arman Hasanzadeh, Nick Duffield, Krishna R. Narayanan, Mingyuan Zhou, Xiaoning Qian
Representation learning over graph structured data has been mostly studied in static graph settings while efforts for modeling dynamic graphs are still scant.
Ranked #2 on Dynamic Link Prediction on DBLP Temporal
1 code implementation • NeurIPS 2019 • Arman Hasanzadeh, Ehsan Hajiramezanali, Nick Duffield, Krishna R. Narayanan, Mingyuan Zhou, Xiaoning Qian
Compared to VGAE, the derived graph latent representations by SIG-VAE are more interpretable, due to more expressive generative model and more faithful inference enabled by the flexible semi-implicit construction.
no code implementations • NeurIPS 2018 • Ehsan Hajiramezanali, Siamak Zamani Dadaneh, Alireza Karbalayghareh, Mingyuan Zhou, Xiaoning Qian
Second, compared to the number of involved molecules and system complexity, the number of available samples for studying complex disease, such as cancer, is often limited, especially considering disease heterogeneity.
no code implementations • 7 Mar 2018 • Ehsan Hajiramezanali, Siamak Zamani Dadaneh, Paul de Figueiredo, Sing-Hoi Sze, Mingyuan Zhou, Xiaoning Qian
Next-generation sequencing (NGS) to profile temporal changes in living systems is gaining more attention for deriving better insights into the underlying biological mechanisms compared to traditional static sequencing experiments.