Training for the Future: A Simple Gradient Interpolation Loss to Generalize Along Time

• URL: http://arxiv.org/abs/2108.06721v1
• Date: Sun, 15 Aug 2021 11:20:10 GMT
• Title: Training for the Future: A Simple Gradient Interpolation Loss to Generalize Along Time
• Authors: Anshul Nasery, Soumyadeep Thakur, Vihari Piratla, Abir De, Sunita Sarawagi
• Abstract summary: In several real world applications, machine learning models are deployed to make predictions on data whose distribution changes gradually along time. We propose a simple method that starts with a model with time-sensitive parameters but regularizes its temporal complexity using a Gradient Interpolation (GI) loss.
• Score: 26.261277497201565
• License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
• Abstract: In several real world applications, machine learning models are deployed to make predictions on data whose distribution changes gradually along time, leading to a drift between the train and test distributions. Such models are often re-trained on new data periodically, and they hence need to generalize to data not too far into the future. In this context, there is much prior work on enhancing temporal generalization, e.g. continuous transportation of past data, kernel smoothed time-sensitive parameters and more recently, adversarial learning of time-invariant features. However, these methods share several limitations, e.g, poor scalability, training instability, and dependence on unlabeled data from the future. Responding to the above limitations, we propose a simple method that starts with a model with time-sensitive parameters but regularizes its temporal complexity using a Gradient Interpolation (GI) loss. GI allows the decision boundary to change along time and can still prevent overfitting to the limited training time snapshots by allowing task-specific control over changes along time. We compare our method to existing baselines on multiple real-world datasets, which show that GI outperforms more complicated generative and adversarial approaches on the one hand, and simpler gradient regularization methods on the other.

Related papers

• PeFAD: A Parameter-Efficient Federated Framework for Time Series Anomaly Detection [51.20479454379662]
  We propose a. Federated Anomaly Detection framework named PeFAD with the increasing privacy concerns. We conduct extensive evaluations on four real datasets, where PeFAD outperforms existing state-of-the-art baselines by up to 28.74%.
  arXiv  Detail & Related papers  (2024-06-04T13:51:08Z)
• GinAR: An End-To-End Multivariate Time Series Forecasting Model Suitable for Variable Missing [21.980379175333443]
  We propose a novel Graph Interpolation Attention Recursive Network (named GinAR) to model the spatial-temporal dependencies over the limited collected data for forecasting. In GinAR, it consists of two key components, that is, attention and adaptive graph convolution. Experiments conducted on five real-world datasets demonstrate that GinAR outperforms 11 SOTA baselines, and even when 90% of variables are missing, it can still accurately predict the future values of all variables.
  arXiv  Detail & Related papers  (2024-05-18T16:42:44Z)
• Graph Spatiotemporal Process for Multivariate Time Series Anomaly Detection with Missing Values [67.76168547245237]
  We introduce a novel framework called GST-Pro, which utilizes a graphtemporal process and anomaly scorer to detect anomalies. Our experimental results show that the GST-Pro method can effectively detect anomalies in time series data and outperforms state-of-the-art methods.
  arXiv  Detail & Related papers  (2024-01-11T10:10:16Z)
• Spatiotemporal-Linear: Towards Universal Multivariate Time Series Forecasting [10.404951989266191]
  We introduce the Spatio-Temporal- Linear (STL) framework. STL seamlessly integrates time-embedded and spatially-informed bypasses to augment the Linear-based architecture. Empirical evidence highlights STL's prowess, outpacing both Linear and Transformer benchmarks across varied observation and prediction durations and datasets.
  arXiv  Detail & Related papers  (2023-12-22T17:46:34Z)
• Towards Robust Continual Learning with Bayesian Adaptive Moment Regularization [51.34904967046097]
  Continual learning seeks to overcome the challenge of catastrophic forgetting, where a model forgets previously learnt information. We introduce a novel prior-based method that better constrains parameter growth, reducing catastrophic forgetting. Results show that BAdam achieves state-of-the-art performance for prior-based methods on challenging single-headed class-incremental experiments.
  arXiv  Detail & Related papers  (2023-09-15T17:10:51Z)
• Correlation-aware Spatial-Temporal Graph Learning for Multivariate Time-series Anomaly Detection [67.60791405198063]
  We propose a correlation-aware spatial-temporal graph learning (termed CST-GL) for time series anomaly detection. CST-GL explicitly captures the pairwise correlations via a multivariate time series correlation learning module. A novel anomaly scoring component is further integrated into CST-GL to estimate the degree of an anomaly in a purely unsupervised manner.
  arXiv  Detail & Related papers  (2023-07-17T11:04:27Z)
• 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)
• A Deep Learning Framework for Traffic Data Imputation Considering Spatiotemporal Dependencies [7.835274806604221]
  Imputation of S.temporal data is quite difficult due to complexity of dependencies in the traffic network. Existing approaches mostly only capture the temporal dependencies in time series or static spatial dependencies. They fail directly to model the S.temporal dependencies representation ability of the models.
  arXiv  Detail & Related papers  (2023-04-18T07:13:52Z)
• Multivariate Time Series Imputation by Graph Neural Networks [13.308026049048717]
  We introduce a graph neural network architecture, named GRIL, which aims at reconstructing missing data in different channels of a multivariate time series. Preliminary results show that our model outperforms state-of-the-art methods in the imputation task on relevant benchmarks.
  arXiv  Detail & Related papers  (2021-07-31T17:47:10Z)
• Low-Rank Autoregressive Tensor Completion for Spatiotemporal Traffic Data Imputation [4.9831085918734805]
  Missing data imputation has been a long-standing research topic and critical application for real-world intelligent transportation systems. We propose a low-rank autoregressive tensor completion (LATC) framework by introducing textittemporal variation as a new regularization term. We conduct extensive numerical experiments on several real-world traffic data sets, and our results demonstrate the effectiveness of LATC in diverse missing scenarios.
  arXiv  Detail & Related papers  (2021-04-30T12:00:57Z)
• 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.