Deep Structural Knowledge Exploitation and Synergy for Estimating Node Importance Value on Heterogeneous Information Networks
The classic problem of node importance estimation has been conventionally studied with
homogeneous network topology analysis. To deal with practical network heterogeneity, a …
homogeneous network topology analysis. To deal with practical network heterogeneity, a …
A Diffusion-Based Pre-training Framework for Crystal Property Prediction
Many significant problems involving crystal property prediction from 3D structures have
limited labeled data due to expensive and time-consuming physical simulations or lab …
limited labeled data due to expensive and time-consuming physical simulations or lab …
LayerMatch: Do Pseudo-labels Benefit All Layers?
Deep neural networks have achieved remarkable performance across various tasks when
supplied with large-scale labeled data. However, the collection of labeled data can be time …
supplied with large-scale labeled data. However, the collection of labeled data can be time …
VOLTA: Improving Generative Diversity by Variational Mutual Information Maximizing Autoencoder
The natural language generation domain has witnessed great success thanks to
Transformer models. Although they have achieved state-of-the-art generative quality, they …
Transformer models. Although they have achieved state-of-the-art generative quality, they …
A game model for semi-supervised subspace clustering with dynamic affinity and label learning
T Qi, X Feng, W Wang - Signal Processing, 2024 - Elsevier
With the aid of partial supervised information, semi-supervised subspace clustering methods
aim to obtain affinity matrices directly derived from raw data, and then those affinity matrices …
aim to obtain affinity matrices directly derived from raw data, and then those affinity matrices …
[HTML][HTML] Shopping trajectory representation learning with pre-training for e-commerce customer understanding and recommendation
Understanding customer behavior is crucial for improving service quality in large-scale E-
commerce. This paper proposes C-STAR, a new framework that learns compact …
commerce. This paper proposes C-STAR, a new framework that learns compact …