Smart City Gnosys
Smart city article details
| Title | Memda: Forecasting Urban Time Series With Memory-Based Drift Adaptation |
|---|---|
| ID_Doc | 36706 |
| Authors | Cai Z.; Jiang R.; Yang X.; Wang Z.; Guo D.; Kobayashi H.H.; Song X.; Shibasaki R. |
| Year | 2023 |
| Published | International Conference on Information and Knowledge Management, Proceedings |
| DOI | http://dx.doi.org/10.1145/3583780.3614962 |
| Abstract | Urban time series data forecasting featuring significant contributions to sustainable development is widely studied as an essential task of the smart city. However, with the dramatic and rapid changes in the world environment, the assumption that data obey Independent Identically Distribution is undermined by the subsequent changes in data distribution, known as concept drift, leading to weak replicability and transferability of the model over unseen data. To address the issue, previous approaches typically retrain the model, forcing it to fit the most recent observed data. However, retraining is problematic in that it leads to model lag, consumption of resources, and model re-invalidation, causing the drift problem to be not well solved in realistic scenarios. In this study, we propose a new urban time series prediction model for the concept drift problem, which encodes the drift by considering the periodicity in the data and makes on-the-fly adjustments to the model based on the drift using a meta-dynamic network. Experiments on real-world datasets show that our design significantly outperforms state-of-the-art methods and can be well generalized to existing prediction backbones by reducing their sensitivity to distribution changes. © 2023 Copyright held by the owner/author(s). Publication rights licensed to ACM. |
| Author Keywords | concept drift; domain adaptation; time series; urban computing |
Similar Articles
| Id | Similarity | Authors | Title | Published |
|---|---|---|---|---|
58197  | 0.884 | Zhang Z.; Ren S.; Qian X.; Duffield N. | Towards Invariant Time Series Forecasting In Smart Cities | WWW 2024 Companion - Companion Proceedings of the ACM Web Conference (2024) |
| 34890 | 0.862 | Yao H.; Liu Y.; Wei Y.; Tang X.; Li Z. | Learning From Multiple Cities: A Meta-Learning Approach For Spatial-Temporal Prediction | The Web Conference 2019 - Proceedings of the World Wide Web Conference, WWW 2019 (2019) |
| 57415 | 0.853 | Cribier-Delande P.; Puget R.; Noûs C.; Guigue V.; Denoyer L. | Time Series Prediction Generation From Disentangled Latent Factors: New Opportunities For Smart Cities | 2020 IEEE 23rd International Conference on Intelligent Transportation Systems, ITSC 2020 (2020) |
| 3327 | 0.85 | Mehmood H.; Khalid A.; Kostakos P.; Gilman E.; Pirttikangas S. | A Novel Edge Architecture And Solution For Detecting Concept Drift In Smart Environments | Future Generation Computer Systems, 150 (2024) |