Multi-Channel Graph Neural Network (MuGNN)

25 May, 2020 by NExT

Patent Name: Multi-Channel Graph Neural Network (MuGNN)

Filing No: 10201906457S (SG)

Filing Date: 7 Nov 2019

Country to be Filed: SG

Description: This invention proposes a novel model Multi-Channel Graph Neural Network (MuGNN), which learns alignment-oriented embeddings by encoding graphs from different perspectives: completion and pruning, so as to be robust to structural differences. The key idea is to perform KG inference and alignment jointly, so that the heterogeneity of KGs is explicitly reconciled through completion by rule inference and transfer, and pruning via cross-KG attention, which benefits the utilization of seed alignments. Extensive experiments on five datasets and further ablation study demonstrate the effectiveness of our proposed model.

Patents

QLive: Low Latency Live Streaming Solution

25 May, 2020

Advanced Conversational Recommender System

25 May, 2020

Multi-Channel Graph Neural Network (MuGNN)

25 May, 2020

Food Recognition Enhanced Using Privileged Information

25 May, 2020

Knowledge Enhanced Translation-based User Preference Model (KTUP)

25 May, 2020

A Contextual Relation Networks for Mixed-Dish Recognition

25 May, 2020

Tree Enhanced Embedding Model Predictive Analysis Methods and Systems

25 May, 2020

Machine Learning Using Partial Order Hypergraphs

25 May, 2020

Video Visual Relation Detection

25 May, 2020

Object Trajectory Proposal

25 May, 2020

Neural Factorization Machines for Predictive Analytics

25 May, 2020

Attentional Factorization Machines: Learning the Weight of Feature Interactions via Attention Networks

22 May, 2020

Back