Scholarly Works - Preprints
Preprint
·
July 25, 2026
Automated sleep staging is increasingly used in large-scale studies to derive sleep-architecture endpoints: total sleep time, REM latency, sleep efficiency, and bout-duration statistics. Deep learning models achieve epoch-level accuracy approaching inter-r ...
Link to item
Cite
Preprint
·
May 30, 2026
Online link recommendation on evolving graphs is performative: by choosing which candidate links to show users, the system changes which links form and what feedback it later observes. Consequently, fairness estimates from logged outcomes can be misleading ...
Link to item
Cite
Preprint
·
April 3, 2026
Diffusion models often degrade in latent spaces, yet the formal causes remain poorly understood. We quantify latent-space diffusability via the rate of change of the Minimum Mean Squared Error (MMSE) along the diffusion trajectory. Our framework decomposes ...
Link to item
Cite
Preprint
·
December 15, 2025
Recent years have witnessed significant advancements in machine learning methods on graphs. However, transferring knowledge effectively from one graph to another remains a critical challenge. This highlights the need for algorithms capable of applying info ...
Link to item
Cite
Preprint
·
October 22, 2025
Infants discover categories, detect novelty, and adapt to new contexts without supervision-a challenge for current machine learning. We present a brain-inspired perspective on configurations, a finite-resolution clustering framework that uses a single reso ...
Link to item
Cite
Preprint
·
October 22, 2025
Clustering-based features are widely used in machine learning, but most methods must choose a resolution -- a choice that is global, fixed, and ad hoc. Recent work shows that varying the resolution parameter produces only a finite set of structurally stabl ...
Link to item
Cite
Preprint
·
August 14, 2025
Graph anomaly detection (GAD) has become an increasingly important task across various domains. With the rapid development of graph neural networks (GNNs), GAD methods have achieved significant performance improvements. However, fairness considerations in ...
Link to item
Cite
Preprint
·
February 5, 2025
Unsupervised domain adaptation (UDA) aims to improve model performance on an unlabeled target domain using a related, labeled source domain. A common approach aligns source and target feature distributions by minimizing a distance between them, often using ...
Link to item
Cite
Preprint
·
January 16, 2025
Generative modeling aims to generate new data samples that resemble a given dataset. When using diffusion models for this task, one of the main challenges is solving the problem in the input space, which tends to be very high-dimensional. To address this, ...
Link to item
Cite
Preprint
·
October 22, 2024
Hyperbolic neural networks (HNNs) have been proved effective in modeling complex data structures. However, previous works mainly focused on the Poincaré ball model and the hyperboloid model as coordinate representations of the hyperbolic space, often negle ...
Link to item
Cite
Preprint
·
July 15, 2024
Hyperbolic representations have shown remarkable efficacy in modeling inherent hierarchies and complexities within data structures. Hyperbolic neural networks have been commonly applied for learning such representations from data, but they often fall short ...
Link to item
Cite
Preprint
·
March 6, 2024
Graph anomaly detection plays a vital role for identifying abnormal instances in complex networks. Despite advancements of methodology based on deep learning in recent years, existing benchmarking approaches exhibit limitations that hinder a comprehensive ...
Link to item
Cite
Preprint
·
November 2, 2023
Generative adversarial networks (GANs) are popular for generative tasks; however, they often require careful architecture selection, extensive empirical tuning, and are prone to mode collapse. To overcome these challenges, we propose a novel model that ide ...
Link to item
Cite
Preprint
·
June 15, 2023
Learning representations according to the underlying geometry is of vital importance for non-Euclidean data. Studies have revealed that the hyperbolic space can effectively embed hierarchical or tree-like data. In particular, the few past years have witnes ...
Link to item
Cite
Preprint
·
August 19, 2022
The recent rapid growth in mobile data traffic entails a pressing demand for improving the throughput of the underlying wireless communication networks. Network node deployment has been considered as an effective approach for throughput enhancement which, ...
Link to item
Cite
Preprint
·
February 4, 2022
Image generative models can learn the distributions of the training data and consequently generate examples by sampling from these distributions. However, when the training dataset is corrupted with outliers, generative models will likely produce examples ...
Link to item
Cite
Preprint
·
January 30, 2022
With the recent advance of geometric deep learning, neural networks have been extensively used for data in non-Euclidean domains. In particular, hyperbolic neural networks have proved successful in processing hierarchical information of data. However, many ...
Link to item
Cite
Preprint
·
June 9, 2020
We propose a new method for novelty detection that can tolerate high corruption of the training points, whereas previous works assumed either no or very low corruption. Our method trains a robust variational autoencoder (VAE), which aims to generate a mode ...
Link to item
Cite
