Self-Supervised Deconfounding Against Spatio-Temporal Shifts: Theory and Modeling

• URL: http://arxiv.org/abs/2311.12472v2
• Date: Wed, 6 Mar 2024 12:57:27 GMT
• Title: Self-Supervised Deconfounding Against Spatio-Temporal Shifts: Theory and Modeling
• Authors: Jiahao Ji, Wentao Zhang, Jingyuan Wang, Yue He and Chao Huang
• Abstract summary: In this work, we formalize the problem by constructing a causal graph of past traffic data, future traffic data, and external ST contexts. We show that the failure of prior arts in OOD traffic data is due to ST contexts acting as a confounder, i.e., the common cause for past data and future ones. We devise a Spatio-Temporal sElf-superVised dEconfounding (STEVE) framework to encode traffic data into two disentangled representations for associating invariant and variant ST contexts.
• Score: 48.09863133371918
• License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
• Abstract: As an important application of spatio-temporal (ST) data, ST traffic forecasting plays a crucial role in improving urban travel efficiency and promoting sustainable development. In practice, the dynamics of traffic data frequently undergo distributional shifts attributed to external factors such as time evolution and spatial differences. This entails forecasting models to handle the out-of-distribution (OOD) issue where test data is distributed differently from training data. In this work, we first formalize the problem by constructing a causal graph of past traffic data, future traffic data, and external ST contexts. We reveal that the failure of prior arts in OOD traffic data is due to ST contexts acting as a confounder, i.e., the common cause for past data and future ones. Then, we propose a theoretical solution named Disentangled Contextual Adjustment (DCA) from a causal lens. It differentiates invariant causal correlations against variant spurious ones and deconfounds the effect of ST contexts. On top of that, we devise a Spatio-Temporal sElf-superVised dEconfounding (STEVE) framework. It first encodes traffic data into two disentangled representations for associating invariant and variant ST contexts. Then, we use representative ST contexts from three conceptually different perspectives (i.e., temporal, spatial, and semantic) as self-supervised signals to inject context information into both representations. In this way, we improve the generalization ability of the learned context-oriented representations to OOD ST traffic forecasting. Comprehensive experiments on four large-scale benchmark datasets demonstrate that our STEVE consistently outperforms the state-of-the-art baselines across various ST OOD scenarios.

Related papers

• A Time Series is Worth Five Experts: Heterogeneous Mixture of Experts for Traffic Flow Prediction [9.273632869779929]
  We propose a Heterogeneous Mixture of Experts (TITAN) model for traffic flow prediction. Experiments on two public traffic network datasets, METR-LA and P-BAY, demonstrate that TITAN effectively captures variable-centric dependencies. It achieves improvements in all evaluation metrics, ranging from approximately 4.37% to 11.53%, compared to previous state-of-the-art (SOTA) models.
  arXiv  Detail & Related papers  (2024-09-26T00:26:47Z)
• OpenSTL: A Comprehensive Benchmark of Spatio-Temporal Predictive Learning [67.07363529640784]
  We propose OpenSTL to categorize prevalent approaches into recurrent-based and recurrent-free models. We conduct standard evaluations on datasets across various domains, including synthetic moving object trajectory, human motion, driving scenes, traffic flow and forecasting weather. We find that recurrent-free models achieve a good balance between efficiency and performance than recurrent models.
  arXiv  Detail & Related papers  (2023-06-20T03:02:14Z)
• Semantic-Fused Multi-Granularity Cross-City Traffic Prediction [17.020546413647708]
  We propose a Semantic-Fused Multi-Granularity Transfer Learning model to achieve knowledge transfer across cities with fused semantics at different granularities. In detail, we design a semantic fusion module to fuse various semantics while conserving static spatial dependencies. We conduct extensive experiments on six real-world datasets to verify the effectiveness of our STL model.
  arXiv  Detail & Related papers  (2023-02-23T04:26:34Z)
• Enhancing the Robustness via Adversarial Learning and Joint Spatial-Temporal Embeddings in Traffic Forecasting [11.680589359294972]
  We propose TrendGCN to address the challenge of balancing dynamics and robustness. Our model simultaneously incorporates spatial (node-wise) embeddings and temporal (time-wise) embeddings to account for heterogeneous space-and-time convolutions. Compared with traditional approaches that handle step-wise predictive errors independently, our approach can produce more realistic and robust forecasts.
  arXiv  Detail & Related papers  (2022-08-05T09:36:55Z)
• Continuous-Time and Multi-Level Graph Representation Learning for Origin-Destination Demand Prediction [52.0977259978343]
  This paper proposes a Continuous-time and Multi-level dynamic graph representation learning method for Origin-Destination demand prediction (CMOD) The state vectors keep historical transaction information and are continuously updated according to the most recently happened transactions. Experiments are conducted on two real-world datasets from Beijing Subway and New York Taxi, and the results demonstrate the superiority of our model against the state-of-the-art approaches.
  arXiv  Detail & Related papers  (2022-06-30T03:37:50Z)
• Detecting Owner-member Relationship with Graph Convolution Network in Fisheye Camera System [9.665475078766017]
  We propose an innovative relationship prediction method, DeepWORD, by designing a graph convolutional network (GCN) In the experiments we learned that the proposed method achieved state-of-the-art accuracy and real-time performance.
  arXiv  Detail & Related papers  (2022-01-28T13:12:27Z)
• Injecting Knowledge in Data-driven Vehicle Trajectory Predictors [82.91398970736391]
  Vehicle trajectory prediction tasks have been commonly tackled from two perspectives: knowledge-driven or data-driven. In this paper, we propose to learn a "Realistic Residual Block" (RRB) which effectively connects these two perspectives. Our proposed method outputs realistic predictions by confining the residual range and taking into account its uncertainty.
  arXiv  Detail & Related papers  (2021-03-08T16:03:09Z)
• Relation-Guided Representation Learning [53.60351496449232]
  We propose a new representation learning method that explicitly models and leverages sample relations. Our framework well preserves the relations between samples. By seeking to embed samples into subspace, we show that our method can address the large-scale and out-of-sample problem.
  arXiv  Detail & Related papers  (2020-07-11T10:57:45Z)
• Connecting the Dots: Multivariate Time Series Forecasting with Graph Neural Networks [91.65637773358347]
  We propose a general graph neural network framework designed specifically for multivariate time series data. Our approach automatically extracts the uni-directed relations among variables through a graph learning module. Our proposed model outperforms the state-of-the-art baseline methods on 3 of 4 benchmark datasets.
  arXiv  Detail & Related papers  (2020-05-24T04:02:18Z)

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.