AdaRNN

Du, Yuntao; Wang, Jindong; Feng, Wenjie; Pan, Sinno Jialin; Qin, Tao; Xu, Renjun; Wang, Chongjun

doi:10.1145/3459637.3482315

Cited by 100 publications

(42 citation statements)

References 42 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Arik et al [2] proposes Self-Adaptive Forecasting to adapt the forecasting model using test-time training by "backcasting" and using the backcast errors to signal a potential distribution shift to adjust the weights of the model before inference. AdaRNN [7] splits the time series history into dissimilar segments and learns importance weights to combine the RNN hidden states over these segments. Another notion of distribution shift, adversarial attacks, has been recently considered to build more robust forecasting [35,21].…”

Section: A Appendixmentioning

confidence: 99%

Adaptive Sampling for Probabilistic Forecasting under Distribution Shift

Masserano¹,

Rangapuram²,

Kapoor³

et al. 2023

Preprint

View full text Add to dashboard Cite

The world is not static: This causes real-world time series to change over time through external, and potentially disruptive, events such as macroeconomic cycles or the COVID-19 pandemic. We present an adaptive sampling strategy that selects the part of the time series history that is relevant for forecasting. We achieve this by learning a discrete distribution over relevant time steps by Bayesian optimization. We instantiate this idea with a two-step method that is pre-trained with uniform sampling and then training a lightweight adaptive architecture with adaptive sampling. We show with synthetic and real-world experiments that this method adapts to distribution shift and significantly reduces the forecasting error of the base model for three out of five datasets.

show abstract

Section: A Appendixmentioning

confidence: 99%

Adaptive Sampling for Probabilistic Forecasting under Distribution Shift

Masserano¹,

Rangapuram²,

Kapoor³

et al. 2023

Preprint

View full text Add to dashboard Cite

show abstract

“…We use four widely-used evaluation metrics: IC [19], ICIR [4], Rank IC [18], and Rank ICIR [28]. At each date 𝑡, 𝐼𝐶 (𝑡 ) could be measured by…”

Section: Evaluation Metricsmentioning

confidence: 99%

DoubleAdapt: A Meta-learning Approach to Incremental Learning for Stock Trend Forecasting

Zhao

Kong

Shen

2023

Proceedings of the 29th ACM SIGKDD Conference on Knowledge Discovery and Data Mining

View full text Add to dashboard Cite

Stock trend forecasting is a fundamental task of quantitative investment where precise predictions of price trends are indispensable. As an online service, stock data continuously arrive over time. It is practical and efficient to incrementally update the forecast model with the latest data which may reveal some new patterns recurring in the future stock market. However, incremental learning for stock trend forecasting still remains under-explored due to the challenge of distribution shifts (a.k.a. concept drifts). With the stock market dynamically evolving, the distribution of future data can slightly or significantly differ from incremental data, hindering the effectiveness of incremental updates. To address this challenge, we propose DoubleAdapt, an end-to-end framework with two adapters, which can effectively adapt the data and the model to mitigate the effects of distribution shifts. Our key insight is to automatically learn how to adapt stock data into a locally stationary distribution in favor of profitable updates. Complemented by data adaptation, we can confidently adapt the model parameters under mitigated distribution shifts. We cast each incremental learning task as a meta-learning task and automatically optimize the adapters for desirable data adaptation and parameter initialization. Experiments on real-world stock datasets demonstrate that DoubleAdapt achieves state-of-theart predictive performance and shows considerable efficiency. CCS CONCEPTS• Computing methodologies → Online learning settings; • Information systems → Data stream mining.

show abstract

“…(1) JT (joint training): a naive baseline that train on all the available data ever seen 𝐷 1,𝑇 . (2) Adaptive RNN (AdaRNN) [5]: a two-stage method that follow a 'segment-adapt' principle for the evolving shifted data. (3) Meta-learning via online change point analysis (MOCA) [7]: an approach which augments a meta-learning algorithm with a differentiable Bayesian change point detection scheme.…”

Section: Experiments 31 Experimental Setupmentioning

confidence: 99%

T-SaS: Toward Shift-aware Dynamic Adaptation for Streaming Data

Ren,

Zhao,

Qin

et al. 2023

Proceedings of the 32nd ACM International Conference on Information and Knowledge Management

View full text Add to dashboard Cite

In many real-world scenarios, distribution shifts exist in the streaming data across time steps. Many complex sequential data can be effectively divided into distinct regimes that exhibit persistent dynamics. Discovering the shifted behaviors and the evolving patterns underlying the streaming data are important to understand the dynamic system. Existing methods typically train one robust model to work for the evolving data of distinct distributions or sequentially adapt the model utilizing explicitly given regime boundaries. However, there are two challenges: (1) shifts in data streams could happen drastically and abruptly without precursors. Boundaries of distribution shifts are usually unavailable, and ( 2) training a shared model for all domains could fail to capture varying patterns. This paper aims to solve the problem of sequential data modeling in the presence of sudden distribution shifts that occur without any precursors. Specifically, we design a Bayesian framework, dubbed as T-SaS, with a discrete distribution-modeling variable to capture abrupt shifts of data. Then, we design a model that enable adaptation with dynamic network selection conditioned on that discrete variable. The proposed method learns specific model parameters for each distribution by learning which neurons should be activated in the full network. A dynamic masking strategy is adopted here to support inter-distribution transfer through the overlapping of a set of sparse networks. Extensive experiments show that our proposed method is superior in both accurately detecting shift boundaries to get segments of varying distributions and effectively adapting to downstream forecast or classification tasks. CCS CONCEPTS• Computing methodologies → Neural networks; Learning latent representations; Classification and regression trees.

show abstract

AdaRNN

Cited by 100 publications

References 42 publications

Adaptive Sampling for Probabilistic Forecasting under Distribution Shift

Adaptive Sampling for Probabilistic Forecasting under Distribution Shift

DoubleAdapt: A Meta-learning Approach to Incremental Learning for Stock Trend Forecasting

T-SaS: Toward Shift-aware Dynamic Adaptation for Streaming Data

Contact Info

Product

Resources

About