研究方向¶
主要以时序数据挖掘的研究为主。实验室发表的论文见：论文列表
连续时间序列¶
多时间序列数据挖掘¶
- 研究场景：通用时间序列预测、交通预测、空气质量预测、天气预测
- 代表工作：
- Ada-MSHyper: Adaptive multi-scale hypergraph transformer for time series forecasting, NeurIPS, 2024
- WeatherGNN: Exploiting meteo- and spatial-dependencies for local numerical weather prediction bias-correction, IJCAI, 2024
- Multi-scale adaptive graph neural network for multivariate time series forecasting, TKDE, 2023
- Deep citywide multi-source data fusion based air quality estimation, TCyber, 2023
- A multiscale interactive recurrent network for time-series forecasting, TCyber, 2021
- Multi-range attentive bicomponent graph convolutional network for traffic forecasting, AAAI, 2020
- Relational state-space model for stochastic multi-object systems, ICLR, 2020
- Deep multi-task learning based urban air quality index modelling, UbiComp, 2019
活动识别¶
- 研究场景：用传感器数据进行活动识别
- 代表工作：
- GOAT: A generalized cross-dataset activity recognition framework with natural language supervision, UbiComp, 2024
- Spatial-temporal masked autoencoder for multi-device wearable human activity recognition, UbiComp, 2023
- SWL-Adapt: An unsupervised domain adaptation model with sample weight learning for cross-user wearable human activity recognition, AAAI, 2023
- Towards a dynamic inter-sensor correlations learning framework for multi-sensor-based wearable human activity recognition, UbiComp, 2022
- SALIENCE: An unsupervised user adaptation model for multiple wearable sensors based human activity recognition, TMC, 2022
- METIER: A deep multi-task learning based activity and user recognition model using wearable sensors, UbiComp, 2020
- AROMA: A deep multi-task learning based simple and complex human activity recognition method using wearable sensors, UbiComp, 2018
离散时间事件¶
- 研究场景：时态知识图谱表示学习
- 代表工作：
- DECRL: A deep evolutionary clustering jointed temporal knowledge graph representation learning approach, NeurIPS, 2024
- DHyper: A recurrent dual hypergraph neural network for event prediction in temporal knowledge graphs, TOIS, 2024
- GTRL: An entity group-aware temporal knowledge graph representation learning method, TKDE, 2024
- DACHA: A Dual Graph Convolution Based Temporal Knowledge Graph Representation Learning Method Using Historical Relation, TKDD, 2022
