CoChat

Multi-Variate Time Series Forecasting on Variable Subsets

Open access
Chauhan, Jatin, Raghuveer, Aravindan, Saket, Rishi, Nandy, Jay, Ravindran, Balaraman · 2022 · Proceedings of the 28th ACM SIGKDD Conference on Knowledge Discovery and Data Mining

The DOI matches its Crossref record; 35 of the 35 references it cites were found in a registry or an index.

Abstract

We formulate a new inference task in the domain of multivariate time series forecasting (MTSF), called Variable Subset Forecast (VSF), where only a small subset of the variables is available during inference. Variables are absent during inference because of long-term data loss (eg. sensor failures) or high -> low-resource domain shift between train / test. To the best of our knowledge, robustness of MTSF models in presence of such failures, has not been studied in the literature. Through extensive evaluation, we first show that the performance of state of the art methods degrade significantly in the VSF setting. We propose a non-parametric, wrapper technique that can be applied on top any existing forecast models. Through systematic experiments across 4 datasets and 5 forecast models, we show that our technique is able to recover close to 95% performance of the models even when only 15% of the original variables are present.

Overview

The claims and statistics of this paper haven’t been checked yet.

Free: it reads the open-access text and checks the first 5 claims that cite a source we can check. Create a free account to check every claim.

A few free checks a day · papers already verified open instantly · results are public

Integrity signals

Registry

Crossref · 10.1145/3534678.3539394

Cites

35 of 35 references verified0 citation errors · 0 not checkable

Statistics

Figures

Figure 1 Variable Subset Forecast Problem: The two subfigures show a (i) training and (ii) test instance, respectively. The light gray part on top of each sub-figure represents the input timesteps. The dark shaded part is the forecast. During training, Variables V1 through V7 are present while during Testing, only V1, V2, V4, V7 are present.
Figure 1 Variable Subset Forecast Problem: The two subfigures show a (i) training and (ii) test instance, respectively. The light gray part on top of each sub-figure represents the input timesteps. The dark shaded part is the forecast. During training, Variables V1 through V7 are present while during Testing, only V1, V2, V4, V7 are present.CC-BY · From the PDF
Figure 2 Variation of Error metrics with relative size of S for the Traffic dataset. The Gap closes with increasing size of S . Solid lineplot is the Partial setting, whereas the dashed correspond to Oracle (nearly constant), for a given model.
Figure 2 Variation of Error metrics with relative size of S for the Traffic dataset. The Gap closes with increasing size of S . Solid lineplot is the Partial setting, whereas the dashed correspond to Oracle (nearly constant), for a given model.CC-BY · From the PDF
Figure 3 Reciprocal Rank of Optimal Nearest Neighbor
Figure 3 Reciprocal Rank of Optimal Nearest NeighborCC-BY · From the PDF
Image 4
CC-BY · From the PDF
Image 5
CC-BY · From the PDF
Figure 5 Variation of gap (difference) between Oracle and Partial across horizon length for the error metrics.
Figure 5 Variation of gap (difference) between Oracle and Partial across horizon length for the error metrics.CC-BY · From the PDF
Image 7
CC-BY · From the PDF
Image 8
CC-BY · From the PDF
Figure 7 Variation of the average number of rounds taken against the desired number of neighbors to fetch. Experimented for MTGNN on ECG5000.
Figure 7 Variation of the average number of rounds taken against the desired number of neighbors to fetch. Experimented for MTGNN on ECG5000.CC-BY · From the PDF

Verification

Claims the paper makes

The claims and statistics of this paper haven’t been checked yet.

Free: it reads the open-access text and checks the first 5 claims that cite a source we can check. Create a free account to check every claim.

A few free checks a day · papers already verified open instantly · results are public

Self-check

Percentages, sums and reported differences re-computed from the paper’s own numbers.

The self-check needs the paper’s full text.

Citations

Cites

Show all 35 references

Research works printed but not linked: 3

  1. Defu Cao Yujing Wang Juanyong Duan Ce Zhang Xia Zhu Congrui Huang Yunhai Tong Bixiong Xu Jing Bai Jie Tong and Qi Zhang. 2020. Spectral Temporal Graph Neural Network for Multivariate Time-series Forecasting. In Advances in Neural Information Processing Systems .
  2. 10.5555/3104482.3104599 · doi:10.5555/3104482.3104599
  3. Yaguang Li, Rose Yu, Cyrus Shahabi, and Yan Liu. 2018. Diffusion Convolutional Recurrent Neural Network: Data-Driven Traffic Forecasting. In International Conference on Learning Representations .

Cited by

See all 21

Metadata

Authors
Chauhan, J., Raghuveer, A., Saket, R., Nandy, J., & Ravindran, B.
Affiliations
  • Google (United States) (US)
  • Indian Institute of Technology Madras (IN)
Venue
Proceedings of the 28th ACM SIGKDD Conference on Knowledge Discovery and Data Mining
Publisher
ACM
Published
2022-08-14
Pages
76-86
OpenAlex
W4283706581
Cited by
21
References
35
Citations by year
2026: 3 · 2025: 11 · 2024: 4 · 2023: 3
FWCI
3.20
Type
conference paper
Language
en
Open access
Locations
  • ACM SIGKDD Conference on Knowledge Discovery and Data Mining (KDD) (publishedVersion, cc-by)
  • arXiv (Cornell University) (submittedVersion)
  • arXiv (Cornell University)
Topics
  • Physical Sciences › Computer Science › Signal Processing › Time Series Analysis and Forecasting
  • Social Sciences › Decision Sciences › Management Science and Operations Research › Forecasting Techniques and Applications
  • Social Sciences › Transportation › Traffic Prediction and Management Techniques
Keywords
multivariate time series forecasting, missing variables, sensor faults, domain shift, model robustness, data loss

About these checks

Registry, retraction, Cites and statistics results are computed, not judged, with one exception: a printed reference that no index lists is read once by a model before it counts as a citation error. Claims are extracted by a model and kept only when their quote appears verbatim in the text; each cited source is then checked, with a model’s help, for whether it says what the claim relies on. Those verdicts can be wrong — read the claim’s quote and the cited source before relying on one.

Statistics and arithmetic are recomputed, not judged.

Confidence bands are shown only for fields calibrated on our annotated test set. None is calibrated yet, so no band is shown.

What counts as a claim ›How we measure confidence ›How we check this ›

Are you an author, or do you see a problem with this page? Request a review

How to cite

Cite CoChat for the checks on this page, and the paper for its own findings.

This page
CoChat. (2026). Citation check: Multi-Variate Time Series Forecasting on Variable Subsets. https://app.cochat.ai/papers/10.1145/3534678.3539394
The paper
Chauhan, J., Raghuveer, A., Saket, R., Nandy, J., & Ravindran, B. (2022). Multi-Variate Time Series Forecasting on Variable Subsets. Proceedings of the 28th ACM SIGKDD Conference on Knowledge Discovery and Data Mining. https://doi.org/10.1145/3534678.3539394

Data sources

Bibliographic data: Semantic Scholar, OpenAlex, Crossref.

Contains information from the Semantic Scholar Academic Graph Datasets, made available under the ODC Attribution License (ODC-BY 1.0).

Semantic Scholar’s data is described in: Kinney, R., et al. (2023). The Semantic Scholar Open Data Platform. arXiv:2301.10140.