Temporal Regularized Matrix Factorization for High-dimensional Time Series Prediction

By Hsiang-Fu Yu, Nikhil S. Rao, Inderjit S. Dhillon. 2016

544 citations recorded by the source corpus.

How researchers see this paper

The researchers whose trusted networks rank it highest, strongest advocate first. Every researcher gets a different order.

In Time-Series & Forecasting

Citations in the corpus

N-BEATS: Neural basis expansion analysis for interpretable time series forecasting (2019, methodology): “In this experiment we are comparing the performances of MatFact (Yu et al., 2016), DeepAR (Flunkert et al.”
Temporal Fusion Transformers for Interpretable Multi-horizon Time Series Forecasting (2019, methodology): “• Traffic: The UCI PEM-SF Traffic Dataset describes the occupancy rate (with yt ∈ [0, 1]) of 440 SF Bay Area freeways – as in [32].”
Enhancing the Locality and Breaking the Memory Bottleneck of Transformer on Time Series Forecasting (2019, methodology): “arima, ets implemented in R’s forecast package and the recent matrix factorization method TRMF [17], a RNN-based autoregressive model DeepAR and a RNN-based state space model DeepState [6].”
Deep Factors for Forecasting (2019, methodology): “Closely related are the matrix factorization (MF) techniques (Yu et al., 2016; Xie et al., 2017; Hooi et al., 2019) and tensor factorization (Araujo et al., 2019), which have been applied to the time series matrix with temporal regularization to ensure the regularity of the latent time series.”
Think Globally, Act Locally: A Deep Neural Network Approach to High-Dimensional Time Series Forecasting (2019, methodology): “There has been a concurrent work [25], where an RNN has been used to evolve a global state common to all time-series.”
Approximate Bayesian Inference in Linear State Space Models for Intermittent Demand Forecasting at Scale (2017, methodology): “For this, we selected one of the time series from the electricity dataset [19] which contains hourly time series of the electricity use (kW) of 370 customers.”
Probabilistic Forecasting with Temporal Convolutional Neural Network (2019, methodology): “Therefore, methods that can provide forecasting on multiple series jointly have received increasing attention in the last few years (e.g., Yu et al., 2016).”
Multi-step Deep Autoregressive Forecasting with Latent States (2019, methodology): “We compare our method with shallow methods ARIMA, exponential smoothing (ETS) and TRMF (Yu et al., 2016), as well as recent deep models DeepAR (Flunkert et al.”
Unified Training of Universal Time Series Forecasting Transformers (2024, background): “…experiments with additional point forecasting metrics, including the symmetric mean absolute percentage error (sMAPE) (Hyndman, 2014), mean absolute scaled error (MASE) (Hyndman & Koehler, 2006), normalized deviation (ND), and normalized root mean squared error (NRMSE) (Yu et al., 2016).”
Deep Learning on Traffic Prediction: Methods, Analysis, and Future Directions (2021, methodology): “…[25] Traditional machine learning methods Feature-based models Flow [30] Demand [28], [29] Gaussian process models Flow [31] Speed [33] Demand [32] Occupancy [32] State space models Flow [34], [35], [38]–[40], [45]–[48] Speed [36], [42], [43] Demand [37] Travel time [44] Occupancy [41], [44] Fig.”
Bayesian Temporal Factorization for Multidimensional Time Series Prediction (2019, methodology): “Inspired by the recent studies on temporal regularization [19] and Bayesian factorization [12], this framework applies low-rank matrix/tensor factorization to model multivariate and multidimensional spatiotemporal data and imposes a vector autoregressive (VAR) process to model the temporal factor…”
Probabilistic Forecasting with Spline Quantile Function RNNs (2019, background): “• hourly occupancy rate, between 0 and 1, of 963 car lanes of San Fransisco bay area freeways (Yu et al., 2016).”
Modeling Long- and Short-Term Temporal Patterns with Deep Neural Networks (2017, methodology): “• TRMF is the autoregressive model using temporal regularized matrix factorization by [33].”
Deep State Space Models for Time Series Forecasting (2018, methodology): “Since MatFact only produces point forecasts, we report normalized deviation as in [28], which in our case is equal to p50-loss.”
Diffusion Convolutional Recurrent Neural Network: Data-Driven Traffic Forecasting (2017, background): “However, existing machine learning models either impose strong stationary assumptions on the data (e.g., auto-regressive model) or fail to account for highly non-linear temporal dependency (e.g., latent space model Yu et al. (2016); Deng et al. (2016)).”
GAIN: Missing Data Imputation using Generative Adversarial Nets (2018, methodology): “…& Oudshoorn, 2000; Buuren & Groothuis-Oudshoorn, 2011), MissForest (Stekhoven & B ¨ uhlmann, 2011), and matrix completion (Mazumder et al., 2010a; Yu et al., 2016; Schnabel et al., 2016; Mazumder et al., 2010b); generative methods include algorithms based on Expectation Maximization…”
SAITS: Self-Attention-based Imputation for Time Series (2022, background): “Amounts of prior work are proposed to solve this problem with statistics and machine learning methods [2, 15, 16, 17, 18, 19, 20].”
A Unified Framework for Long Range and Cold Start Forecasting of Seasonal Profiles in Time Series (2017, methodology): “In Figure 4a, it is clear that our model more appropriately captures the bumps around days 100 and 160, and TRMF falsely predicts a weekly oscillation structure.”