Pengpeng Zhao

Multi-label active learning with label correlation for image classification

2015

Label correlation analysis is very important for multi-label classification. And there is no study to measure the label correlation for example-label based active learning. In this paper, from a statistical point of view, we proposed …

Where to Go Next: A Spatio-temporal LSTM model for Next POI Recommendation

2018 · arXiv (Cornell University)

Next Point-of-Interest (POI) recommendation is of great value for both location-based service providers and users. Recently Recurrent Neural Networks (RNNs) have been proved to be effective on sequential recommendation tasks. However, existing RNN solutions rarely …

Where to Go Next: A Spatio-Temporal Gated Network for Next POI Recommendation

2019 · Proceedings of the AAAI Conference on Artificial Intelligence

Next Point-of-Interest (POI) recommendation is of great value for both location-based service providers and users. However, the state-of-the-art Recurrent Neural Networks (RNNs) rarely consider the spatio-temporal intervals between neighbor check-ins, which are essential for modeling …

Recurrent Convolutional Neural Network for Sequential Recommendation

2019

The sequential recommendation, which models sequential behavioral patterns among users for the recommendation, plays a critical role in recommender systems. However, the state-of-the-art Recurrent Neural Networks (RNN) solutions rarely consider the non-linear feature interactions and …

Graph Contextualized Self-Attention Network for Session-based Recommendation

2019

Session-based recommendation, which aims to predict the user's immediate next action based on anonymous sessions, is a key task in many online services (e.g., e-commerce, media streaming). Recently, Self-Attention Network (SAN) has achieved significant success …

Feature-level Deeper Self-Attention Network for Sequential Recommendation

2019

Sequential recommendation, which aims to recommend next item that the user will likely interact in a near future, has become essential in various Internet applications. Existing methods usually consider the transition patterns between items, but …