DisenHCN: Disentangled Hypergraph Convolutional Networks for Spatiotemporal Activity Prediction

by   Yinfeng Li, et al.
Tsinghua University

Spatiotemporal activity prediction, aiming to predict user activities at a specific location and time, is crucial for applications like urban planning and mobile advertising. Existing solutions based on tensor decomposition or graph embedding suffer from the following two major limitations: 1) ignoring the fine-grained similarities of user preferences; 2) user's modeling is entangled. In this work, we propose a hypergraph neural network model called DisenHCN to bridge the above gaps. In particular, we first unify the fine-grained user similarity and the complex matching between user preferences and spatiotemporal activity into a heterogeneous hypergraph. We then disentangle the user representations into different aspects (location-aware, time-aware, and activity-aware) and aggregate corresponding aspect's features on the constructed hypergraph, capturing high-order relations from different aspects and disentangles the impact of each aspect for final prediction. Extensive experiments show that our DisenHCN outperforms the state-of-the-art methods by 14.23 verify the rationality of each component in our DisenHCN.


Inhomogeneous Social Recommendation with Hypergraph Convolutional Networks

Incorporating social relations into the recommendation system, i.e. soci...

Bundle Recommendation with Graph Convolutional Networks

Bundle recommendation aims to recommend a bundle of items for a user to ...

Self-Supervised Hypergraph Convolutional Networks for Session-based Recommendation

Session-based recommendation (SBR) focuses on next-item prediction at a ...

Revisiting Selectional Preferences for Coreference Resolution

Selectional preferences have long been claimed to be essential for coref...

Multi-Modal Subjective Context Modelling and Recognition

Applications like personal assistants need to be aware ofthe user's cont...

USTAR: Online Multimodal Embedding for Modeling User-Guided Spatiotemporal Activity

Building spatiotemporal activity models for people's activities in urban...

Towards Fine-Grained Reasoning for Fake News Detection

The detection of fake news often requires sophisticated reasoning skills...

Please sign up or login with your details

Forgot password? Click here to reset