paper-with-me

Papers

Minusformer: Improving Time Series Forecasting by Progressively Learning Residuals

2024-02-04 · Daojun Liang, Haixia Zhang, Dongfeng Yuan, Bingzheng Zhang, Minggao Zhang

In this paper, we find that ubiquitous time series (TS) forecasting models are prone to severe overfitting. To cope with this problem, we embrace a de-redundancy approach to progressively reinstate the intrinsic values of TS for future intervals. Specifically, we introduce a dual-stream and subtraction mechanism, which is a deep Boosting ensemble learning method. And the vanilla Transformer is renovated by reorienting the information aggregation mechanism from addition to subtraction. Then, we incorporate an auxiliary output branch into each block of the original model to construct a highway leading to the ultimate prediction. The output of subsequent modules in this branch will subtract the previously learned results, enabling the model to learn the residuals of the supervision signal, layer by layer. This designing facilitates the learning-driven implicit progressive decomposition of the input and output streams, empowering the model with heightened versatility, interpretability, and resilience against overfitting. Since all aggregations in the model are minus signs, which is called Minusformer. Extensive experiments demonstrate the proposed method outperform existing state-of-the-art methods, yielding an average performance improvement of 11.9% across various datasets.The code has been released at https://github.com/Anoise/Minusformer.

📄 PDF Abstract BibTeX arXiv:2402.02332

Code (1)

anoise/minusformer 공식 구현 pytorch

Tasks

Ensemble LearningTime SeriesTime Series AnalysisTime Series Forecasting

Methods 이 논문이 사용한 방법론

Attention 설명 없음
Absolute Position Encodings Absolute Position Encodings are a type of position embeddings for [Transformer-based models] where positional encodings are…
Linear Layer A Linear Layer is a projection $\mathbf{XW + b}$.
BPE Byte Pair Encoding, or BPE, is a subword segmentation algorithm that encodes rare and unknown words as sequences of subword units. The intuition is that various word…
Multi-Head Attention 설명 없음
Adam 설명 없음
Residual Connection 설명 없음
Layer Normalization Unlike batch normalization, Layer Normalization directly estimates the normalization statistics from the summed inputs…

Similar Papers 제목 키워드 기반

DeepBooTS: Dual-Stream Residual Boosting for Drift-Resilient Time-Series Forecasting

2025-11-10 · Daojun Liang, Jing Chen, Xiao Wang, Yinglong Wang 외 arxiv

Time-Series (TS) exhibits pronounced non-stationarity. Consequently, most forecasting methods display compromised robustness to concept drift, despite the prevalent application of instance normalization. We tackle this c…

Signals, Concepts, and Laws: Toward Universal, Explainable Time-Series Forecasting

2025-08-02 · Hongwei Ma, Junbin Gao, Minh-Ngoc Tran arxiv

Accurate, explainable and physically credible forecasting remains a persistent challenge for multivariate time-series whose statistical properties vary across domains. We propose DORIC, a Domain-Universal, ODE-Regularize…

TEFL: Prediction-Residual-Guided Rolling Forecasting for Multi-Horizon Time Series

2026-02-26 · Xiannan Huang, Shen Fang, Shuhan Qiu, Chengcheng Yu 외 arxiv

Time series forecasting plays a critical role in domains such as transportation, energy, and meteorology. Despite their success, modern deep forecasting models are typically trained to minimize point-wise prediction loss…

Time Series Forecasting

Boosted Ensemble Learning based on Randomized NNs for Time Series Forecasting

2022-03-02 · Grzegorz Dudek

Time series forecasting is a challenging problem particularly when a time series expresses multiple seasonality, nonlinear trend and varying variance. In this work, to forecast complex time series, we propose ensemble le…

Ensemble LearningTime SeriesTime Series AnalysisTime Series Forecasting

Explainable boosted linear regression for time series forecasting

2020-09-18 · Igor Ilic, Berk Gorgulu, Mucahit Cevik, Mustafa Gokce Baydogan

Time series forecasting involves collecting and analyzing past observations to develop a model to extrapolate such observations into the future. Forecasting of future events is important in many fields to support decisio…

Decision MakingPrediction IntervalsregressionTime Series+2