Search Results for author:
Found 12 papers, 3 papers with code
A Revisit of Total Correlation in Disentangled Variational Auto-Encoder with Partial Disentanglement
A fully disentangled variational auto-encoder (VAE) aims to identify disentangled latent components from observations.
Exploring Behavior-Relevant and Disentangled Neural Dynamics with Generative Diffusion Models
To tackle this limitation, our approach, named ``BeNeDiff'', first identifies a fine-grained and disentangled neural subspace using a behavior-informed latent variable model.
Learning Time-Varying Multi-Region Communications via Scalable Markovian Gaussian Processes
Understanding and constructing brain communications that capture dynamic communications across multiple regions is fundamental to modern system neuroscience, yet current methods struggle to find time-varying region-level communications or scale to large neural datasets with long recording durations.
Multi-Region Markovian Gaussian Process: An Efficient Method to Discover Directional Communications Across Multiple Brain Regions
Consequently, the model achieves a linear inference cost over time points and provides an interpretable low-dimensional representation, revealing communication directions across brain regions and separating oscillatory communications into different frequency bands.
A Differentiable Partially Observable Generalized Linear Model with Forward-Backward Message Passing
For (1), we propose a new differentiable POGLM, which enables the pathwise gradient estimator, better than the score function gradient estimator used in existing works.
Forward $χ^2$ Divergence Based Variational Importance Sampling
Maximizing the log-likelihood is a crucial aspect of learning latent variable models, and variational inference (VI) stands as the commonly adopted method.
Extraction and Recovery of Spatio-Temporal Structure in Latent Dynamics Alignment with Diffusion Models
Specifically, the latent dynamics structures of the source domain are first extracted by a diffusion model.
Task Aligned Meta-learning based Augmented Graph for Cold-Start Recommendation
In this paper, we propose a Task aligned Meta-learning based Augmented Graph (TMAG) to address cold-start recommendation.
Extracting Attentive Social Temporal Excitation for Sequential Recommendation
In this paper, we propose a novel time-aware sequential recommendation framework called Social Temporal Excitation Networks (STEN), which introduces temporal point processes to model the fine-grained impact of friends' behaviors on the user s dynamic interests in an event-level direct paradigm.
ICPE: An Item Cluster-Wise Pareto-Efficient Framework for Recommendation Debiasing
In detail, we define our item cluster-wise optimization target as the recommender model should balance all item clusters that differ in popularity, thus we set the model learning on each item cluster as a unique optimization objective.
DemiNet: Dependency-Aware Multi-Interest Network with Self-Supervised Graph Learning for Click-Through Rate Prediction
In this paper, we propose a novel model named DemiNet (short for DEpendency-Aware Multi-Interest Network) to address the above two issues.
SAR Image Change Detection via Spatial Metric Learning with an Improved Mahalanobis Distance
In this letter, we proposed a spatial metric learning method to obtain a difference image more robust to the speckle by learning a metric from a set of constraint pairs.
