Explaining deep learning models operating on time series data is crucial in various applications that require transparent and interpretable insights into model behavior. {Existing explanation methods generally fall into two categories: attribution-based explanations, which identify the temporal regions most responsible for a prediction, and counterfactual explanations, which reveal how an input should be modified to alter the model's decision.} {Despite valuable insights, these two fields are largely studied independently. This disconnect leaves attribution methods lacking causal validation, while counterfactual methods suffer from severe instability, producing adversarial-like noise instead of meaningful explanations.} In this work, we revisit time-series explainability from an information-theoretic perspective and show that existing explainers are vulnerable to trivial solutions and distributional shifts. To address these limitations, we propose a unified objective function for explainable time series learning that bridges attribution and counterfactual reasoning within a single framework. Building upon the Information Bottleneck principle, our formulation explicitly prevents trivial explanations and out-of-distribution counterfactuals. {Based on this objective function, we introduce {\modelname}, a novel explanation framework that learns a parametric transformation network to construct explanation-embedded instances, where preserved information yields attribution explanations and controlled information removal produces stable counterfactual explanations.} We evaluate {\modelname} on synthetic and real-world benchmarks against state-of-the-art baselines. Extensive quantitative and qualitative results show that {\modelname} consistently outperforms competing methods, yielding faithful attributions and stable counterfactual explanations.
Xu Zheng, Zichuan Liu, Zhuomin Chen et al.· 0 citations
As forecasts increasingly drive decisions in fields such as energy, transportation, and healthcare, understanding the historical data behind these predictions has become as crucial as the predictions themselves. Although existing interpretable-by-design forecasters reveal their internal structures, they offer no guarantee that these structures faithfully reflect the underlying evidence driving the predictions. In contrast, while faithfulness-oriented methods explicitly verify model behavior, they are almost exclusively designed for post-hoc classification tasks. To bridge this gap, we propose IB-Forecast, an inherently interpretable multivariate time-series forecasting framework. It decomposes forecasting into a learned periodic component and a residual component computed with explainable masks over input tokens. With a budget-constrained information bottleneck, end-to-end optimization enables users to directly control explanation sparsity. With a rigorous faithfulness evaluation protocol, extensive experiments demonstrate that IB-Forecast matches the forecasting error of leading black-box models while providing faithful explanations at no additional inference cost. Furthermore, under a matched sparsity budget, these native explanations consistently surpass gradient-based, occlusion-based, and optimization-based baselines across all evaluated datasets. Ultimately, whereas the native explanations of existing interpretable forecasters exhibit poor faithfulness, IB-Forecast guarantees high explanation fidelity, requiring only 14-20% of the observations to deliver low-error predictions.
: Domain adaptation remains a significant challenge in deploying data-driven models under distribution shifts, particularly when transferring from simulated to real-world environments. Existing approaches often rely on large labeled target datasets, suffer negative transfer, and provide limited interpretability. In this paper, we present NoiseFlow, a data-efficient domain adaptation framework that leverages noise-aware modeling and flow matching to enable robust cross-domain generalization. Our key insight is that feature dimensions exhibit heterogeneous sensitivity to noise, which can be amplified under domain shift. NoiseFlow introduces a feature-aware teacher student architecture that combines knowledge distillation, distribution alignment, and continuous flow matching to learn smooth transformations between source and target domains. Experimentation on wireless network configuration tasks demonstrates that NoiseFlow achieves good performance in low-data regimes, reaching 69.8% accuracy with a single target sample and improving zero-shot transfer performance by up to 40% over existing methods.
Aitian Ma, Dongsheng Luo, M. Sha· Proceedings of the 15th Inte...· 0 citations
Wireless Mesh Networks (WMNs) are essential for many Internet of Things (IoT) applications, such as industrial automation, environmental monitoring, and smart cities. Today, configuring a WMN to meet its stringent performance requirements remains a significant challenge due to dynamic real-world wireless conditions and operating environments. The simulationto-reality gap in network configuration further complicates the generalization of models trained solely with simulation data, leading to suboptimal performance in physical deployments. To address such challenges, we develop WMN-LLM-DS, a novel framework that integrates Large Language Models (LLMs) for synthetic data generation with domain adaptation techniques to better configure WMNs. Leveraging LLMs, WMN-LLM-DS generates high-quality, diverse synthetic datasets conditioned on realworld constraints, effectively bridging the simulation-to-reality gap and enriching the diversity of training data. WMN-LLM-DS employs a teacher-student architecture to transfer network configuration knowledge learned from simulations to physical deployments, enhanced by custom loss functions to align feature representations across different domains. Experiments conducted on datasets collected from a physical testbed and network simulators demonstrate that WMN-LLM-DS outperforms existing solutions, achieving an improvement of up to 10.8% in prediction accuracy while also exhibiting strong domain generalization capabilities.
Aitian Ma, Jean Marco Cruz, Dongsheng Luo et al.· Annual International Compute...· 1 citation
We use cookies to run the site and, with your consent, for analytics and to show ads.
See our Cookie Policy.
