Learning Personalized Representations using Graph Convolutional Network

07/28/2022
by   Hongyu Shen, et al.
15

Generating representations that precisely reflect customers' behavior is an important task for providing personalized skill routing experience in Alexa. Currently, Dynamic Routing (DR) team, which is responsible for routing Alexa traffic to providers or skills, relies on two features to be served as personal signals: absolute traffic count and normalized traffic count of every skill usage per customer. Neither of them considers the network based structure for interactions between customers and skills, which contain richer information for customer preferences. In this work, we first build a heterogeneous edge attributed graph based customers' past interactions with the invoked skills, in which the user requests (utterances) are modeled as edges. Then we propose a graph convolutional network(GCN) based model, namely Personalized Dynamic Routing Feature Encoder(PDRFE), that generates personalized customer representations learned from the built graph. Compared with existing models, PDRFE is able to further capture contextual information in the graph convolutional function. The performance of our proposed model is evaluated by a downstream task, defect prediction, that predicts the defect label from the learned embeddings of customers and their triggered skills. We observe up to 41 to the baselines.

READ FULL TEXT

page 3

page 7

research
09/13/2020

GIKT: A Graph-based Interaction Model for Knowledge Tracing

With the rapid development in online education, knowledge tracing (KT) h...
research
11/24/2019

Which Channel to Ask My Question? Personalized Customer Service Request Stream Routing using Deep Reinforcement Learning

Customer services are critical to all companies, as they may directly co...
research
06/09/2020

DyHGCN: A Dynamic Heterogeneous Graph Convolutional Network to Learn Users' Dynamic Preferences for Information Diffusion Prediction

Information diffusion prediction is a fundamental task for understanding...
research
11/22/2020

AST-GCN: Attribute-Augmented Spatiotemporal Graph Convolutional Network for Traffic Forecasting

Traffic forecasting is a fundamental and challenging task in the field o...
research
06/07/2023

Data Augmentation for Improving Tail-traffic Robustness in Skill-routing for Dialogue Systems

Large-scale conversational systems typically rely on a skill-routing com...
research
01/31/2022

Evaluating Deep Vs. Wide Deep Learners As Contextual Bandits For Personalized Email Promo Recommendations

Personalization enables businesses to learn customer preferences from pa...
research
10/22/2022

PENTATRON: PErsonalized coNText-Aware Transformer for Retrieval-based cOnversational uNderstanding

Conversational understanding is an integral part of modern intelligent d...

Please sign up or login with your details

Forgot password? Click here to reset