REVIEW 14 cited by
ETSformer: Exponential Smoothing Transformers for Time-series Forecasting
Not yet reviewed by Pith; the record is open.
This paper has not been read by Pith yet. Machine review is queued; the pith claim, tier, and objections will appear here once it completes.
SPECIMEN: schema-true, not a live event
T0 review · schema-true
One-sentence machine reading of the paper's core claim.
pith:XXXXXXXX · record.json · timestamp
read the original abstract
Transformers have been actively studied for time-series forecasting in recent years. While often showing promising results in various scenarios, traditional Transformers are not designed to fully exploit the characteristics of time-series data and thus suffer some fundamental limitations, e.g., they generally lack of decomposition capability and interpretability, and are neither effective nor efficient for long-term forecasting. In this paper, we propose ETSFormer, a novel time-series Transformer architecture, which exploits the principle of exponential smoothing in improving Transformers for time-series forecasting. In particular, inspired by the classical exponential smoothing methods in time-series forecasting, we propose the novel exponential smoothing attention (ESA) and frequency attention (FA) to replace the self-attention mechanism in vanilla Transformers, thus improving both accuracy and efficiency. Based on these, we redesign the Transformer architecture with modular decomposition blocks such that it can learn to decompose the time-series data into interpretable time-series components such as level, growth and seasonality. Extensive experiments on various time-series benchmarks validate the efficacy and advantages of the proposed method. Code is available at https://github.com/salesforce/ETSformer.
Forward citations
Cited by 14 Pith papers
-
ARIES: Relation Assessment and Model Recommendation for Deep Time Series Forecasting
ARIES shows that deep forecasting models have consistent performance preferences tied to time series properties, and uses those preferences to recommend models for new datasets.
-
Text Reinforcement for Multimodal Time Series Forecasting
Reinforcement learning trains an LLM to generate improved text from time series, improving multimodal forecasting on Time-MMD.
-
The Power of Architecture: Deep Dive into Transformer Architectures for Long-Term Time Series Forecasting
Bidirectional joint-attention, complete forecasting aggregation, and direct mapping form the most effective Transformer design for long-term time series forecasting.
-
Fremer: Lightweight and Effective Frequency Transformer for Workload Forecasting in Cloud Services
Fremer forecasts cloud workloads by aligning frequency spectra via linear padding, filtering noise, and attending over frequency combinations.
-
ST-MTM: Masked Time Series Modeling with Seasonal-Trend Decomposition for Time Series Forecasting
ST-MTM shows that masking seasonal and trend components separately, with a contrastive alignment loss, improves self-supervised time series forecasting.
-
LiQSS: Post-Transformer Linear Quantum-Inspired State-Space Tensor Networks for Real-Time 6G
LiQSS, a linear-time state-space tensor-network forecaster, matches or beats Transformer-based KPI predictors on an O-RAN dataset with up to 155x fewer parameters and faster inference.
-
MSTN: A Lightweight and Fast Model for General TimeSeries Analysis
MSTN is a lightweight hybrid model that reports new state-of-the-art results on 33 of 40 time series benchmarks for imputation, forecasting, and classification while using under one million parameters and sub-second i...
-
CaReTS: A Multi-Task Framework Unifying Classification and Regression for Time Series Forecasting
CaReTS forecasts multi-step time series by combining a trend classifier with a deviation regressor in a residual, uncertainty-weighted multi-task framework.
-
Rivaling Transformers: Multi-Scale Structured State-Space Mixtures for Agentic 6G O-RAN
A 0.70M-parameter multi-scale state-space mixture predicts next-step RSRP on an O-RAN testbed with RMSE 0.29 dB and R2=0.993, running 3-10x faster than the tested Transformers.
-
Teaching Time Series to See and Speak: Forecasting with Aligned Visual and Textual Perspectives
TimesCLIP aligns image-based and text-based views of the same time series via contrastive learning to improve forecasting accuracy on several benchmarks, but the full multimodal model is not used on two of the six lon...
-
MetaEformer: Unveiling and Leveraging Meta-patterns for Complex and Dynamic Systems Load Forecasting
A transformer that pools and reuses learned waveform prototypes reports state-of-the-art load forecasting accuracy across cloud, power, and traffic benchmarks.
-
A Quantum-Classical Hybrid Framework for Multivariate Time-Series Forecasting Complexity-Fidelity Trade-offs and Limitations
A trainable 6-qubit-per-channel variational circuit plus linear readout roughly matches transformer forecasters at short horizons on ETT/Weather/Electricity benchmarks, but the reported setup does not match the paper'...
-
Frequency-Constrained Learning for Long-Term Forecasting
Initializing sinusoidal time embeddings with FFT-extracted dominant frequencies and constraining their learning rate yields mixed improvements on traffic forecasting benchmarks, contradicting the paper's claim of cons...
-
Scaling Transformers for Time Series Forecasting: Do Pretrained Large Models Outperform Small-Scale Alternatives?
LLM4TS_FS achieves the best MSE on four of seven long-term datasets, but the claimed broad advantage of pre-trained large models over small transformers is not consistent across all benchmarks.
Discussion (0). Sign in to comment.