4 papers
A Causal Disentangled Multi-Granularity Graph Classification Method
Yuan Li, Li Liu, Penggang Chen +2
Graph data widely exists in real life, with large amounts of data and complex structures. It is necessary to map graph data to low-dimensional embedding. Graph classification, a cr…
Graph Signal Processing for Heterogeneous Change Detection Part II: Spectral Domain Analysis
Yuli Sun, Lin Lei, Dongdong Guan +2
This is the second part of the paper that provides a new strategy for the heterogeneous change detection (HCD) problem, that is, solving HCD from the perspective of graph signal pr…
Graph Signal Processing for Heterogeneous Change Detection Part I: Vertex Domain Filtering
Yuli Sun, Lin Lei, Dongdong Guan +2
This paper provides a new strategy for the Heterogeneous Change Detection (HCD) problem: solving HCD from the perspective of Graph Signal Processing (GSP). We construct a graph for…
Advanced Conditional Variational Autoencoders (A-CVAE): Towards interpreting open-domain conversation generation via disentangling latent feature representation
Ye Wang, Jingbo Liao, Hong Yu +3
Currently end-to-end deep learning based open-domain dialogue systems remain black box models, making it easy to generate irrelevant contents with data-driven models. Specifically,…