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

arXiv: https://arxiv.org/abs/2309.02610 · HTML: https://mlsanity.com/paper/2309.02610/

## Key facts

- Cited by 3 papers in the map (data through 14 Oct 2026).
- Builds on 18 of its 33 references that are in the map.
- First posted on arXiv 5 Sep 2023.

## Builds on (most cited first, 18 of 18)

- [The Lottery Ticket Hypothesis: Finding Sparse, Trainable Neural Networks](https://mlsanity.com/paper/1803.03635/) (2018)
- [Deep Visual Domain Adaptation: A Survey](https://mlsanity.com/paper/1802.03601/) (2018)
- [A Survey of Unsupervised Deep Domain Adaptation](https://mlsanity.com/paper/1812.02849/) (2018)
- [Variational Continual Learning](https://mlsanity.com/paper/1710.10628/) (2017)
- [AdaRNN: Adaptive Learning and Forecasting of Time Series](https://mlsanity.com/paper/2108.04443/) (2021)
- [Continual Learning via Local Module Composition](https://mlsanity.com/paper/2111.07736/) (2021)
- [Continuous Meta-Learning without Tasks](https://mlsanity.com/paper/1912.08866/) (2019)
- [Collapsed Amortized Variational Inference for Switching Nonlinear Dynamical Systems](https://mlsanity.com/paper/1910.09588/) (2019)
- [Deep Explicit Duration Switching Models for Time Series](https://mlsanity.com/paper/2110.13878/) (2021)
- [Towards Faithful and Consistent Explanations for Graph Neural Networks](https://mlsanity.com/paper/2205.13733/) (2022)
- [TopoImb: Toward Topology-level Imbalance in Learning from Graphs](https://mlsanity.com/paper/2212.08689/) (2022)
- [Explanation Guided Contrastive Learning for Sequential Recommendation](https://mlsanity.com/paper/2209.01347/) (2022)
- [Mitigating Popularity Bias in Recommendation with Unbalanced Interactions: A Gradient Perspective](https://mlsanity.com/paper/2211.01154/) (2022)
- [Semi-supervised Drifted Stream Learning with Short Lookback](https://mlsanity.com/paper/2205.13066/) (2022)
- [Synthetic Over-sampling for Imbalanced Node Classification with Graph Neural Networks](https://mlsanity.com/paper/2206.05335/) (2022)
- [Faithful and Consistent Graph Neural Network Explanations with Rationale Alignment](https://mlsanity.com/paper/2301.02791/) (2023)
- [Skill Disentanglement for Imitation Learning from Suboptimal Demonstrations](https://mlsanity.com/paper/2306.07919/) (2023)
- [Graph Relation Aware Continual Learning](https://mlsanity.com/paper/2308.08259/) (2023)

## Built on by (most cited first, 3 of 3)

- [TimeEmb: A Lightweight Static-Dynamic Disentanglement Framework for Time Series Forecasting](https://mlsanity.com/paper/2510.00461/) (2025)
- [Disambiguated Node Classification with Graph Neural Networks](https://mlsanity.com/paper/2402.08824/) (2024)
- [Multi-source Unsupervised Domain Adaptation on Graphs with Transferability Modeling](https://mlsanity.com/paper/2406.10425/) (2024)

## Abstract (arXiv)

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.