38 citations · 125 across the 49 of their papers we have counts for
51 papers
NEST: Nested Embedding Representation for Multiscale Clustering
Zhanqi Zhang, Mikio Aoi, Gal Mishne
Real-world data often exhibits cluster structure at multiple resolutions, yet existing methods typically learn a single partition or construct an explicit hierarchy. Inspired by Ma…
Neural Algorithmic Reasoning for Graph Saddle Point Problems
Samantha Chen, Jesse He, Coleman Clougherty +2
Neural algorithmic reasoning, or aligning a neural network with an algorithmic paradigm, has emerged as an approach to solving polynomial-time-solvable and computationally harder c…
Reassessing Muon for Matrix Factorization
Ali Parviz, Gal Mishne, Alex Cloninger
Muon has recently emerged as a strong optimizer for large-scale deep learning, where it reshapes gradient updates through approximate orthogonalization and has been reported to out…
ALIGN: Adversarial Learning for Generalizable Speech Neuroprosthesis
Zhanqi Zhang, Shun Li, Bernardo L. Sabatini +2
Intracortical brain-computer interfaces (BCIs) can decode speech from neural activity with high accuracy when trained on data pooled across recording sessions. In realistic deploym…
MINAR: Mechanistic Interpretability for Neural Algorithmic Reasoning
Jesse He, Helen Jenne, Max Vargas +4
The recent field of neural algorithmic reasoning (NAR) studies the ability of graph neural networks (GNNs) to emulate classical algorithms like Bellman-Ford, a phenomenon known as…
Multi-Integration of Labels across Categories for Component Identification (MILCCI)
Noga Mudrik, Yuxi Chen, Gal Mishne +1
Many fields collect large-scale temporal data through repeated measurements (trials), where each trial is labeled with a set of metadata variables spanning several categories. For…
Unsupervised Feature Selection Through Group Discovery
Shira Lifshitz, Ofir Lindenbaum, Gal Mishne +2
Unsupervised feature selection (FS) is essential for high-dimensional learning tasks where labels are not available. It helps reduce noise, improve generalization, and enhance inte…
Coupled Transformer Autoencoder for Disentangling Multi-Region Neural Latent Dynamics
Ram Dyuthi Sristi, Sowmya Manojna Narasimha, Jingya Huang +4
Simultaneous recordings from thousands of neurons across multiple brain areas reveal rich mixtures of activity that are shared between regions and dynamics that are unique to each…
Revisiting Meta-Learning with Noisy Labels: Reweighting Dynamics and Theoretical Guarantees
Yiming Zhang, Chester Holtz, Gal Mishne +1
Learning with noisy labels remains challenging because over-parameterized networks memorize corrupted supervision. Meta-learning-based sample reweighting mitigates this by using a…
Robust Tangent Space Estimation via Laplacian Eigenvector Gradient Orthogonalization
Dhruv Kohli, Sawyer J. Robertson, Gal Mishne +1
Estimating the tangent spaces of a data manifold is a fundamental problem in geometric data analysis. The standard approach, Local Principal Component Analysis (LPCA), struggles in…
RnGCam: High-speed video from rolling & global shutter measurements
Kevin Tandi, Xiang Dai, Chinmay Talegaonkar +2
Compressive video capture encodes a short high-speed video into a single measurement using a low-speed sensor, then computationally reconstructs the original video. Prior implement…
Cluster and then Embed: A Modular Approach for Visualization
Elizabeth Coda, Ery Arias-Castro, Gal Mishne
Dimensionality reduction methods such as t-SNE and UMAP are popular methods for visualizing data with a potential (latent) clustered structure. They are known to group data points…
Low-dimensional embeddings of high-dimensional data
Cyril de Bodt, Alex Diaz-Papkovich, Michael Bleher +18
Large collections of high-dimensional data have become nearly ubiquitous across many academic fields and application domains, ranging from biology to the humanities. Since working…
Explaining GNN Explanations with Edge Gradients
Jesse He, Akbar Rafiey, Gal Mishne +1
In recent years, the remarkable success of graph neural networks (GNNs) on graph-structured data has prompted a surge of methods for explaining GNN predictions. However, the state-…
Learning Kronecker-Structured Graphs from Smooth Signals
Changhao Shi, Gal Mishne
Graph learning, or network inference, is a prominent problem in graph signal processing (GSP). GSP generalizes the Fourier transform to non-Euclidean domains, and graph learning is…
Robust Graph-Based Semi-Supervised Learning via -Conductances
Sawyer Jack Robertson, Chester Holtz, Zhengchao Wan +2
We study the problem of semi-supervised learning on graphs in the regime where data labels are scarce or possibly corrupted. We propose an approach called -conductance learning…
Joint Hierarchical Representation Learning of Samples and Features via Informed Tree-Wasserstein Distance
Ya-Wei Eileen Lin, Ronald R. Coifman, Gal Mishne +1
High-dimensional data often exhibit hierarchical structures in both modes: samples and features. Yet, most existing approaches for hierarchical representation learning consider onl…
Elucidating Flow Matching ODE Dynamics with Respect to Data Geometries and Denoisers
Zhengchao Wan, Qingsong Wang, Gal Mishne +1
Flow matching (FM) models extend ODE sampler based diffusion models into a general framework, significantly reducing sampling steps through learned vector fields. However, the theo…
Robust boundary detection and density estimation using doubly stochastic scaling of the Gaussian kernel
Dhruv Kohli, Jesse He, Chester Holtz +2
This paper addresses the problem of detecting boundary points and estimating the sampling density of a dataset derived from a compact manifold with boundary, potentially in the pre…
Tree-Wasserstein Distance for High Dimensional Data with a Latent Feature Hierarchy
Ya-Wei Eileen Lin, Ronald R. Coifman, Gal Mishne +1
Finding meaningful distances between high-dimensional data samples is an important scientific task. To this end, we propose a new tree-Wasserstein distance (TWD) for high-dimension…
Multiway Multislice PHATE: Visualizing Hidden Dynamics of RNNs through Training
Jiancheng Xie, Lou C. Kohler Voinov, Noga Mudrik +2
Recurrent neural networks (RNNs) are a widely used tool for sequential data analysis; however, they are still often seen as black boxes. Visualizing the internal dynamics of RNNs i…
Deep and shallow data science for multi-scale optical neuroscience
Gal Mishne, Adam Charles
Optical imaging of the brain has expanded dramatically in the past two decades. New optics, indicators, and experimental paradigms are now enabling in-vivo imaging from the synapti…
Learning Cartesian Product Graphs with Laplacian Constraints
Changhao Shi, Gal Mishne
Graph Laplacian learning, also known as network topology inference, is a problem of great interest to multiple communities. In Gaussian graphical models (GM), graph learning amount…
Comparing Graph Transformers via Positional Encodings
Mitchell Black, Zhengchao Wan, Gal Mishne +2
The distinguishing power of graph transformers is closely tied to the choice of positional encoding: features used to augment the base transformer with information about the graph.…