MemDA: Forecasting Urban Time Series with Memory-based Drift Adaptation
- URL: http://arxiv.org/abs/2309.14216v1
- Date: Mon, 25 Sep 2023 15:22:28 GMT
- Title: MemDA: Forecasting Urban Time Series with Memory-based Drift Adaptation
- Authors: Zekun Cai, Renhe Jiang, Xinyu Yang, Zhaonan Wang, Diansheng Guo,
Hiroki Kobayashi, Xuan Song and Ryosuke Shibasaki
- Abstract summary: 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.
Our design significantly outperforms state-of-the-art methods and can be well generalized to existing prediction backbones.
- Score: 24.284969264008733
- License: http://creativecommons.org/licenses/by/4.0/
- 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.
Related papers
- Robust Traffic Forecasting against Spatial Shift over Years [11.208740750755025]
We investigate state-temporal-the-art models using newly proposed traffic OOD benchmarks.
We find that these models experience significant decline in performance.
We propose a novel of Mixture Experts framework, which learns a set of graph generators during training and combines them to generate new graphs.
Our method is both parsimonious and efficacious, and can be seamlessly integrated into anytemporal model.
arXiv Detail & Related papers (2024-10-01T03:49:29Z) - Physics-guided Active Sample Reweighting for Urban Flow Prediction [75.24539704456791]
Urban flow prediction is a nuanced-temporal modeling that estimates the throughput of transportation services like buses, taxis and ride-driven models.
Some recent prediction solutions bring remedies with the notion of physics-guided machine learning (PGML)
We develop a atized physics-guided network (PN), and propose a data-aware framework Physics-guided Active Sample Reweighting (P-GASR)
arXiv Detail & Related papers (2024-07-18T15:44:23Z) - Addressing Concept Shift in Online Time Series Forecasting: Detect-then-Adapt [37.98336090671441]
Concept textbfDrift textbfDetection antextbfD textbfAdaptation (D3A)
It first detects drifting conception and then aggressively adapts the current model to the drifted concepts after the detection for rapid adaption.
It helps mitigate the data distribution gap, a critical factor contributing to train-test performance inconsistency.
arXiv Detail & Related papers (2024-03-22T04:44:43Z) - Rethinking Urban Mobility Prediction: A Super-Multivariate Time Series
Forecasting Approach [71.67506068703314]
Long-term urban mobility predictions play a crucial role in the effective management of urban facilities and services.
Traditionally, urban mobility data has been structured as videos, treating longitude and latitude as fundamental pixels.
In our research, we introduce a fresh perspective on urban mobility prediction.
Instead of oversimplifying urban mobility data as traditional video data, we regard it as a complex time series.
arXiv Detail & Related papers (2023-12-04T07:39:05Z) - Learning Robust Precipitation Forecaster by Temporal Frame Interpolation [65.5045412005064]
We develop a robust precipitation forecasting model that demonstrates resilience against spatial-temporal discrepancies.
Our approach has led to significant improvements in forecasting precision, culminating in our model securing textit1st place in the transfer learning leaderboard of the textitWeather4cast'23 competition.
arXiv Detail & Related papers (2023-11-30T08:22:08Z) - Temporal Domain Generalization with Drift-Aware Dynamic Neural Network [12.483886657900525]
We propose a Temporal Domain Generalization with Drift-Aware Dynamic Neural Network (DRAIN) framework.
Specifically, we formulate the problem into a Bayesian framework that jointly models the relation between data and model dynamics.
It captures the temporal drift of model parameters and data distributions and can predict models in the future without the presence of future data.
arXiv Detail & Related papers (2022-05-21T20:01:31Z) - DDG-DA: Data Distribution Generation for Predictable Concept Drift
Adaptation [34.03849669133438]
We propose a novel method DDG-DA, that can effectively forecast the evolution of data distribution.
Specifically, we first train a predictor to estimate the future data distribution, then leverage it to generate training samples, and finally train models on the generated data.
arXiv Detail & Related papers (2022-01-11T16:34:29Z) - Back2Future: Leveraging Backfill Dynamics for Improving Real-time
Predictions in Future [73.03458424369657]
In real-time forecasting in public health, data collection is a non-trivial and demanding task.
'Backfill' phenomenon and its effect on model performance has been barely studied in the prior literature.
We formulate a novel problem and neural framework Back2Future that aims to refine a given model's predictions in real-time.
arXiv Detail & Related papers (2021-06-08T14:48:20Z) - Learning Interpretable Deep State Space Model for Probabilistic Time
Series Forecasting [98.57851612518758]
Probabilistic time series forecasting involves estimating the distribution of future based on its history.
We propose a deep state space model for probabilistic time series forecasting whereby the non-linear emission model and transition model are parameterized by networks.
We show in experiments that our model produces accurate and sharp probabilistic forecasts.
arXiv Detail & Related papers (2021-01-31T06:49:33Z) - On Robustness and Transferability of Convolutional Neural Networks [147.71743081671508]
Modern deep convolutional networks (CNNs) are often criticized for not generalizing under distributional shifts.
We study the interplay between out-of-distribution and transfer performance of modern image classification CNNs for the first time.
We find that increasing both the training set and model sizes significantly improve the distributional shift robustness.
arXiv Detail & Related papers (2020-07-16T18:39:04Z)
This list is automatically generated from the titles and abstracts of the papers in this site.
This site does not guarantee the quality of this site (including all information) and is not responsible for any consequences.