31 citations · 64 across the 14 of their papers we have counts for
7 papers · 1 filter
Deep Learning From Crowdsourced Labels: Coupled Cross-entropy Minimization, Identifiability, and Regularization
Shahana Ibrahim, Tri Nguyen, Xiao Fu
Using noisy crowdsourced labels from multiple annotators, a deep learning-based end-to-end (E2E) system aims to learn the label correction mechanism and the neural classifier simul…
Under-Counted Tensor Completion with Neural Incorporation of Attributes
Shahana Ibrahim, Xiao Fu, Rebecca Hutchinson +1
Systematic under-counting effects are observed in data collected across many disciplines, e.g., epidemiology and ecology. Under-counted tensor completion (UC-TC) is well-motivated…
Deep Clustering with Incomplete Noisy Pairwise Annotations: A Geometric Regularization Approach
Tri Nguyen, Shahana Ibrahim, Xiao Fu
The recent integration of deep learning and pairwise similarity annotation-based constrained clustering -- i.e., (DCC) -- has proven effectiv…
Provable Subspace Identification Under Post-Nonlinear Mixtures
Qi Lyu, Xiao Fu
Unsupervised mixture learning (UML) aims at identifying linearly or nonlinearly mixed latent components in a blind manner. UML is known to be challenging: Even learning linear mixt…
On Finite-Sample Identifiability of Contrastive Learning-Based Nonlinear Independent Component Analysis
Qi Lyu, Xiao Fu
Nonlinear independent component analysis (nICA) aims at recovering statistically independent latent components that are mixed by unknown nonlinear functions. Central to nICA is the…
Communication-Efficient Federated Linear and Deep Generalized Canonical Correlation Analysis
Sagar Shrestha, Xiao Fu
Classic and deep generalized canonical correlation analysis (GCCA) algorithms seek low-dimensional common representations of data entities from multiple ``views'' (e.g., audio and…
Understanding Latent Correlation-Based Multiview Learning and Self-Supervision: An Identifiability Perspective
Qi Lyu, Xiao Fu, Weiran Wang +1
Multiple views of data, both naturally acquired (e.g., image and audio) and artificially produced (e.g., via adding different noise to data samples), have proven useful in enhancin…