mlsanityData to 7 Oct 2026

CAMul: Calibrated and Accurate Multi-view Time-Series Forecasting

arXiv 2109.07438 ↗First posted 15 Sep 2021cs.LG cs.AI stat.MLcited by 17

Not on the map. Why?

Abstract (arXiv)

Probabilistic time-series forecasting enables reliable decision making across many domains. Most forecasting problems have diverse sources of data containing multiple modalities and structures. Leveraging information as well as uncertainty from these data sources for well-calibrated and accurate forecasts is an important challenging problem. Most previous work on multi-modal learning and forecasting simply aggregate intermediate representations from each data view by simple methods of summation or concatenation and do not explicitly model uncertainty for each data-view. We propose a general probabilistic multi-view forecasting framework CAMul, that can learn representations and uncertainty from diverse data sources. It integrates the knowledge and uncertainty from each data view in a dynamic context-specific manner assigning more importance to useful views to model a well-calibrated forecast distribution. We use CAMul for multiple domains with varied sources and modalities and show that CAMul outperforms other state-of-art probabilistic forecasting models by over 25% in accuracy and calibration.

Key facts. Cited by 17 papers in the map (data through 7 Oct 2026). Builds on 28 of its 62 references that are in the map. First posted on arXiv 15 Sep 2021.

Builds on

28 of 62 references.

References · 28

  1. 2017Attention Is All You Needcited by 59,932
  2. 2018BERT: Pre-training of Deep Bidirectional Transformers for Language Understandingcited by 40,204
  3. 2014Adam: A Method for Stochastic Optimizationcited by 36,960
  4. 2016Semi-Supervised Classification with Graph Convolutional Networkscited by 11,282
  5. 2014Learning Phrase Representations using RNN Encoder-Decoder for Statistical Machine Translationcited by 4,016
  6. 2016Categorical Reparameterization with Gumbel-Softmaxcited by 2,708
  7. 2017DeepAR: Probabilistic Forecasting with Autoregressive Recurrent Networkscited by 1,004
  8. 2020Time Series Forecasting With Deep Learning: A Surveycited by 457
  9. 2018Accurate Uncertainties for Deep Learning Using Calibrated Regressioncited by 417
  10. 2015A Recurrent Latent Variable Model for Sequential Datacited by 362
  11. 2018Neural Processescited by 307
  12. 2016Structured Inference Networks for Nonlinear State Space Modelscited by 182
16 more
  1. 2016Sequential Neural Models with Stochastic Layerscited by 115
  2. 2016A Survey of Multi-View Representation Learningcited by 107
  3. 2017Recent Advances in Recurrent Neural Networkscited by 89
  4. 2019Distribution Calibration for Regressioncited by 88
  5. 2017Deep and Confident Prediction for Time Series at Ubercited by 50
  6. 2019The Functional Neural Processcited by 43
  7. 2020TransModality: An End2End Fusion Method with Transformer for Multimodal Sentiment Analysiscited by 40
  8. 2021Learning Interpretable Deep State Space Model for Probabilistic Time Series Forecastingcited by 29
  9. 2021When in Doubt: Neural Non-Parametric Uncertainty Quantification for Epidemic Forecastingcited by 16
  10. 2019Recurrent Attentive Neural Process for Sequential Datacited by 15
  11. 2020Steering a Historical Disease Forecasting Model Under a Pandemic: Case of Flu and COVID-19cited by 12
  12. 2017State Space LSTM Models with Particle MCMC Inferencecited by 11
  13. 2020DeepCOVIDNet: An Interpretable Deep Learning Model for Predictive Surveillance of COVID-19 Using Heterogeneous Features and their Interactionscited by 10
  14. 2020UNITE: Uncertainty-based Health Risk Prediction Leveraging Multi-sourced Datacited by 9
  15. 2021Back2Future: Leveraging Backfill Dynamics for Improving Real-time Predictions in Futurecited by 7
  16. 2020Understanding Electricity-Theft Behavior via Multi-Source Datacited by 5

Built on by

Cited by year (2026 to 7 Oct)

Citing papers per year: 2022: 4; 2023: 5; 2024: 2; 2025: 1; 2026: 5.

17 papers.

Sort:

By area:

  1. 2023UniTime: A Language-Empowered Unified Model for Cross-Domain Time Series Forecastingcited by 139
  2. 2024Revisiting VAE for Unsupervised Time Series Anomaly Detection: A Frequency Perspectivecited by 22
  3. 2022EINNs: Epidemiologically-informed Neural Networkscited by 21
  4. 2022Differentiable Agent-based Epidemiologycited by 21
  5. 2024Epidemiology-Aware Neural ODE with Continuous Disease Transmission Graphcited by 10
  6. 2022Data-Centric Epidemic Forecasting: A Surveycited by 8
  7. 2023Performative Time-Series Forecastingcited by 8
  8. 2023Fast and Multi-aspect Mining of Complex Time-stamped Event Streamscited by 7
  9. 2022When Rigidity Hurts: Soft Consistency Regularization for Probabilistic Hierarchical Time Series Forecastingcited by 4
  10. 2025Revisiting Backdoor Attacks on Time Series Classification in the Frequency Domaincited by 4
  11. 2023PEMS: Pre-trained Epidemic Time-series Modelscited by 3
  12. 2026Fast Mining and Dynamic Time-to-Event Prediction over Multi-sensor Data Streamscited by 1
5 more
  1. 2026Enhancing Large Language Models for Time-Series Forecasting via Vector-Injected In-Context Learningcited by 1
  2. 2026Are LLMs Ready for Neural-integrated Mechanistic Modeling? A Benchmark and Agentic Frameworkcited by 1
  3. 2023When Rigidity Hurts: Soft Consistency Regularization for Probabilistic Hierarchical Time Series Forecastingcited by 0
  4. 2026Contextual and Seasonal LSTMs for Time Series Anomaly Detectioncited by 0
  5. 2026TERN: A Delta-rule Memory with a Seasonal Reference and Online Adaptation for Epidemic Forecastingcited by 0