SLOTH: Structured Learning and Task-based Optimization for Time Series Forecasting on Hierarchies

• URL: http://arxiv.org/abs/2302.05650v1
• Date: Sat, 11 Feb 2023 10:50:33 GMT
• Title: SLOTH: Structured Learning and Task-based Optimization for Time Series Forecasting on Hierarchies
• Authors: Fan Zhou, Chen Pan, Lintao Ma, Yu Liu, Shiyu Wang, James Zhang, Xinxin Zhu, Xuanwei Hu, Yunhua Hu, Yangfei Zheng, Lei Lei, Yun Hu
• Abstract summary: The hierarchical time series (HTS) forecasting includes two sub-tasks, i.e., forecasting and reconciliation. In this paper, we propose two novel tree-based feature integration mechanisms, i.e., top-down convolution and bottom-up attention. Unlike most previous reconciliation methods which either rely on strong assumptions or focus on coherent constraints only, we utilize deep neural optimization networks.
• Score: 16.12477042879166
• License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
• Abstract: Multivariate time series forecasting with hierarchical structure is widely used in real-world applications, e.g., sales predictions for the geographical hierarchy formed by cities, states, and countries. The hierarchical time series (HTS) forecasting includes two sub-tasks, i.e., forecasting and reconciliation. In the previous works, hierarchical information is only integrated in the reconciliation step to maintain coherency, but not in forecasting step for accuracy improvement. In this paper, we propose two novel tree-based feature integration mechanisms, i.e., top-down convolution and bottom-up attention to leverage the information of the hierarchical structure to improve the forecasting performance. Moreover, unlike most previous reconciliation methods which either rely on strong assumptions or focus on coherent constraints only,we utilize deep neural optimization networks, which not only achieve coherency without any assumptions, but also allow more flexible and realistic constraints to achieve task-based targets, e.g., lower under-estimation penalty and meaningful decision-making loss to facilitate the subsequent downstream tasks. Experiments on real-world datasets demonstrate that our tree-based feature integration mechanism achieves superior performances on hierarchical forecasting tasks compared to the state-of-the-art methods, and our neural optimization networks can be applied to real-world tasks effectively without any additional effort under coherence and task-based constraints

Related papers

• GMP-AR: Granularity Message Passing and Adaptive Reconciliation for Temporal Hierarchy Forecasting [20.56839345239421]
  Time series forecasts of different temporal granularity are widely used in real-world applications. We propose a novel granularity message-passing mechanism (GMP) that leverages temporal hierarchy information to improve forecasting performance. We also introduce an optimization module to achieve task-based targets while adhering to more real-world constraints.
  arXiv  Detail & Related papers  (2024-06-18T03:33:03Z)
• Hierarchical Decomposition of Prompt-Based Continual Learning: Rethinking Obscured Sub-optimality [55.88910947643436]
  Self-supervised pre-training is essential for handling vast quantities of unlabeled data in practice. HiDe-Prompt is an innovative approach that explicitly optimize the hierarchical components with an ensemble of task-specific prompts and statistics. Our experiments demonstrate the superior performance of HiDe-Prompt and its robustness to pre-training paradigms in continual learning.
  arXiv  Detail & Related papers  (2023-10-11T06:51:46Z)
• Probabilistic Forecasting with Coherent Aggregation [42.215158938066054]
  We augment an MQForecaster neural network architecture with a novel deep Gaussian factor forecasting model that achieves coherence by construction. In a comparison to state-of-the-art coherent forecasting methods, DeepCoFactor achieves significant improvements in scaled CRPS forecast accuracy, with average gains of 15%.
  arXiv  Detail & Related papers  (2023-07-19T07:31:37Z)
• Hierarchical Deep Counterfactual Regret Minimization [53.86223883060367]
  In this paper, we introduce the first hierarchical version of Deep CFR, an innovative method that boosts learning efficiency in tasks involving extensively large state spaces and deep game trees. A notable advantage of HDCFR over previous works is its ability to facilitate learning with predefined (human) expertise and foster the acquisition of skills that can be transferred to similar tasks.
  arXiv  Detail & Related papers  (2023-05-27T02:05:41Z)
• Structural hierarchical learning for energy networks [1.2599533416395767]
  This work investigates custom neural network designs inspired by the topological structures of hierarchies. Results unveil that, in a data-limited setting, structural models with fewer connections perform overall best. Overall, this work expands and improves hierarchical learning methods thanks to a structurally-scaled learning mechanism extension.
  arXiv  Detail & Related papers  (2023-02-08T10:28:32Z)
• Hierarchical learning, forecasting coherent spatio-temporal individual and aggregated building loads [1.3764085113103222]
  We propose a novel multi-dimensional hierarchical forecasting method built upon structurally-informed machine-learning regressors and hierarchical reconciliation taxonomy. The method is evaluated on two different case studies to predict building electrical loads. Overall, the paper expands and unites traditionally hierarchical forecasting methods providing a fertile route toward a novel generation of forecasting regressors.
  arXiv  Detail & Related papers  (2023-01-30T15:11:46Z)
• RANK-NOSH: Efficient Predictor-Based Architecture Search via Non-Uniform Successive Halving [74.61723678821049]
  We propose NOn-uniform Successive Halving (NOSH), a hierarchical scheduling algorithm that terminates the training of underperforming architectures early to avoid wasting budget. We formulate predictor-based architecture search as learning to rank with pairwise comparisons. The resulting method - RANK-NOSH, reduces the search budget by 5x while achieving competitive or even better performance than previous state-of-the-art predictor-based methods on various spaces and datasets.
  arXiv  Detail & Related papers  (2021-08-18T07:45:21Z)
• Bottom-up mechanism and improved contract net protocol for the dynamic task planning of heterogeneous Earth observation resources [61.75759893720484]
  Earth observation resources are becoming increasingly indispensable in disaster relief, damage assessment and related domains. Many unpredicted factors, such as the change of observation task requirements, to the occurring of bad weather and resource failures, may cause the scheduled observation scheme to become infeasible. A bottom-up distributed coordinated framework together with an improved contract net are proposed to facilitate the dynamic task replanning for heterogeneous Earth observation resources.
  arXiv  Detail & Related papers  (2020-07-13T03:51:08Z)
• A machine learning approach for forecasting hierarchical time series [4.157415305926584]
  We propose a machine learning approach for forecasting hierarchical time series. Forecast reconciliation is the process of adjusting forecasts to make them coherent across the hierarchy. We exploit the ability of a deep neural network to extract information capturing the structure of the hierarchy.
  arXiv  Detail & Related papers  (2020-05-31T22:26:16Z)
• Dynamic Hierarchical Mimicking Towards Consistent Optimization Objectives [73.15276998621582]
  We propose a generic feature learning mechanism to advance CNN training with enhanced generalization ability. Partially inspired by DSN, we fork delicately designed side branches from the intermediate layers of a given neural network. Experiments on both category and instance recognition tasks demonstrate the substantial improvements of our proposed method.
  arXiv  Detail & Related papers  (2020-03-24T09:56:13Z)
• Target-Embedding Autoencoders for Supervised Representation Learning [111.07204912245841]
  This paper analyzes a framework for improving generalization in a purely supervised setting, where the target space is high-dimensional. We motivate and formalize the general framework of target-embedding autoencoders (TEA) for supervised prediction, learning intermediate latent representations jointly optimized to be both predictable from features as well as predictive of targets.
  arXiv  Detail & Related papers  (2020-01-23T02:37:10Z)

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.