Ensuring the safety of Reinforcement Learning (RL) is crucial for its deployment in real-world applications. Nevertheless, managing the trade-off between reward and safety during exploration presents a significant challenge. Improving reward performance through policy adjustments may adversely affect safety performance. In this study, we aim to address this conflicting relation by leveraging the theory of gradient manipulation. Initially, we analyze the conflict between reward and safety gradients. Subsequently, we tackle the balance between reward and safety optimization by proposing a soft switching policy optimization method, for which we provide convergence analysis. Based on our theoretical examination, we provide a safe RL framework to overcome the aforementioned challenge, and we develop a Safety-MuJoCo Benchmark to assess the performance of safe RL algorithms. Finally, we evaluate the effectiveness of our method on the Safety-MuJoCo Benchmark and a popular safe benchmark, Omnisafe. Experimental results demonstrate that our algorithms outperform several state-of-the-art baselines in terms of balancing reward and safety optimization.
The study of time series data is crucial for understanding trends and anomalies over time, enabling predictive insights across various sectors. Spatio-temporal data, on the other hand, is vital for analyzing phenomena in both space and time, providing a dynamic perspective on complex system interactions. Recently, diffusion models have seen widespread application in time series and spatio-temporal data mining. Not only do they enhance the generative and inferential capabilities for sequential and temporal data, but they also extend to other downstream tasks. In this survey, we comprehensively and thoroughly review the use of diffusion models in time series and spatio-temporal data, categorizing them by model category, task type, data modality, and practical application domain. In detail, we categorize diffusion models into unconditioned and conditioned types and discuss time series data and spatio-temporal data separately. Unconditioned models, which operate unsupervised, are subdivided into probability-based and score-based models, serving predictive and generative tasks such as forecasting, anomaly detection, classification, and imputation. Conditioned models, on the other hand, utilize extra information to enhance performance and are similarly divided for both predictive and generative tasks. Our survey extensively covers their application in various fields, including healthcare, recommendation, climate, energy, audio, and transportation, providing a foundational understanding of how these models analyze and generate data. Through this structured overview, we aim to provide researchers and practitioners with a comprehensive understanding of diffusion models for time series and spatio-temporal data analysis, aiming to direct future innovations and applications by addressing traditional challenges and exploring innovative solutions within the diffusion model framework.
Time series analysis stands as a focal point within the data mining community, serving as a cornerstone for extracting valuable insights crucial to a myriad of real-world applications. Recent advancements in Foundation Models (FMs) have fundamentally reshaped the paradigm of model design for time series analysis, boosting various downstream tasks in practice. These innovative approaches often leverage pre-trained or fine-tuned FMs to harness generalized knowledge tailored specifically for time series analysis. In this survey, we aim to furnish a comprehensive and up-to-date overview of FMs for time series analysis. While prior surveys have predominantly focused on either the application or the pipeline aspects of FMs in time series analysis, they have often lacked an in-depth understanding of the underlying mechanisms that elucidate why and how FMs benefit time series analysis. To address this gap, our survey adopts a model-centric classification, delineating various pivotal elements of time-series FMs, including model architectures, pre-training techniques, adaptation methods, and data modalities. Overall, this survey serves to consolidate the latest advancements in FMs pertinent to time series analysis, accentuating their theoretical underpinnings, recent strides in development, and avenues for future research exploration.
This paper investigates covert data transmission within a multiple-input multiple-output (MIMO) over-the-air computation (AirComp) network, where sensors transmit data to the access point (AP) while guaranteeing covertness to the warden (Willie). Simultaneously, the AP introduces artificial noise (AN) to confuse Willie, meeting the covert requirement. We address the challenge of minimizing mean-square-error (MSE) of the AP, while considering transmit power constraints at both the AP and the sensors, as well as ensuring the covert transmission to Willie with a low detection error probability (DEP). However, obtaining globally optimal solutions for the investigated non-convex problem is challenging due to the interdependence of optimization variables. To tackle this problem, we introduce an exact penalty algorithm and transform the optimization problem into a difference-of-convex (DC) form problem to find a locally optimal solution. Simulation results showcase the superior performance in terms of our proposed scheme in comparison to the benchmark schemes.
The development of Large Language Models (LLMs) often confronts challenges stemming from the heavy reliance on human annotators in the reinforcement learning with human feedback (RLHF) framework, or the frequent and costly external queries tied to the self-instruct paradigm. In this work, we pivot to Reinforcement Learning (RL) -- but with a twist. Diverging from the typical RLHF, which refines LLMs following instruction data training, we use RL to directly generate the foundational instruction dataset that alone suffices for fine-tuning. Our method, TeaMs-RL, uses a suite of textual operations and rules, prioritizing the diversification of training datasets. It facilitates the generation of high-quality data without excessive reliance on external advanced models, paving the way for a single fine-tuning step and negating the need for subsequent RLHF stages. Our findings highlight key advantages of our approach: reduced need for human involvement and fewer model queries (only $5.73\%$ of WizardLM's total), along with enhanced capabilities of LLMs in crafting and comprehending complex instructions compared to strong baselines, and substantially improved model privacy protection.
This paper addresses the fairness issue within fluid antenna system (FAS)-assisted non-orthogonal multiple access (NOMA) and orthogonal multiple access (OMA) systems, where a single fixed-antenna base station (BS) transmits superposition-coded signals to two users, each with a single fluid antenna. We define fairness through the minimization of the maximum outage probability for the two users, under total resource constraints for both FAS-assisted NOMA and OMA systems. Specifically, in the FAS-assisted NOMA systems, we study both a special case and the general case, deriving a closed-form solution for the former and applying a bisection search method to find the optimal solution for the latter. Moreover, for the general case, we derive a locally optimal closed-form solution to achieve fairness. In the FAS-assisted OMA systems, to deal with the non-convex optimization problem with coupling of the variables in the objective function, we employ an approximation strategy to facilitate a successive convex approximation (SCA)-based algorithm, achieving locally optimal solutions for both cases. Empirical analysis validates that our proposed solutions outperform conventional NOMA and OMA benchmarks in terms of fairness.
In long-term time series forecasting (LTSF) tasks, existing deep learning models overlook the crucial characteristic that discrete time series originate from underlying continuous dynamic systems, resulting in a lack of extrapolation and evolution capabilities. Recognizing the chaotic nature of real-world data, our model, \textbf{\textit{Attraos}}, incorporates chaos theory into LTSF, perceiving real-world time series as observations from unknown high-dimensional chaotic dynamic systems. Under the concept of attractor invariance, Attraos utilizes the proposed multi-scale dynamic memory unit to memorize historical dynamics structure and predicts by a frequency-enhanced local evolution strategy. Detailed theoretical analysis and abundant empirical evidence consistently show that Attraos outperforms various LTSF methods on mainstream LTSF datasets and chaotic datasets.
Large-scale black-box models have become ubiquitous across numerous applications. Understanding the influence of individual training data sources on predictions made by these models is crucial for improving their trustworthiness. Current influence estimation techniques involve computing gradients for every training point or repeated training on different subsets. These approaches face obvious computational challenges when scaled up to large datasets and models. In this paper, we introduce and explore the Mirrored Influence Hypothesis, highlighting a reciprocal nature of influence between training and test data. Specifically, it suggests that evaluating the influence of training data on test predictions can be reformulated as an equivalent, yet inverse problem: assessing how the predictions for training samples would be altered if the model were trained on specific test samples. Through both empirical and theoretical validations, we demonstrate the wide applicability of our hypothesis. Inspired by this, we introduce a new method for estimating the influence of training data, which requires calculating gradients for specific test samples, paired with a forward pass for each training point. This approach can capitalize on the common asymmetry in scenarios where the number of test samples under concurrent examination is much smaller than the scale of the training dataset, thus gaining a significant improvement in efficiency compared to existing approaches. We demonstrate the applicability of our method across a range of scenarios, including data attribution in diffusion models, data leakage detection, analysis of memorization, mislabeled data detection, and tracing behavior in language models. Our code will be made available at https://github.com/ruoxi-jia-group/Forward-INF.
Time series analysis is essential for comprehending the complexities inherent in various real-world systems and applications. Although large language models (LLMs) have recently made significant strides, the development of artificial general intelligence (AGI) equipped with time series analysis capabilities remains in its nascent phase. Most existing time series models heavily rely on domain knowledge and extensive model tuning, predominantly focusing on prediction tasks. In this paper, we argue that current LLMs have the potential to revolutionize time series analysis, thereby promoting efficient decision-making and advancing towards a more universal form of time series analytical intelligence. Such advancement could unlock a wide range of possibilities, including modality switching and time series question answering. We encourage researchers and practitioners to recognize the potential of LLMs in advancing time series analysis and emphasize the need for trust in these related efforts. Furthermore, we detail the seamless integration of time series analysis with existing LLM technologies and outline promising avenues for future research.
The detection of anomalies in multivariate time series data is crucial for various practical applications, including smart power grids, traffic flow forecasting, and industrial process control. However, real-world time series data is usually not well-structured, posting significant challenges to existing approaches: (1) The existence of missing values in multivariate time series data along variable and time dimensions hinders the effective modeling of interwoven spatial and temporal dependencies, resulting in important patterns being overlooked during model training; (2) Anomaly scoring with irregularly-sampled observations is less explored, making it difficult to use existing detectors for multivariate series without fully-observed values. In this work, we introduce a novel framework called GST-Pro, which utilizes a graph spatiotemporal process and anomaly scorer to tackle the aforementioned challenges in detecting anomalies on irregularly-sampled multivariate time series. Our approach comprises two main components. First, we propose a graph spatiotemporal process based on neural controlled differential equations. This process enables effective modeling of multivariate time series from both spatial and temporal perspectives, even when the data contains missing values. Second, we present a novel distribution-based anomaly scoring mechanism that alleviates the reliance on complete uniform observations. By analyzing the predictions of the graph spatiotemporal process, our approach allows anomalies to be easily detected. Our experimental results show that the GST-Pro method can effectively detect anomalies in time series data and outperforms state-of-the-art methods, regardless of whether there are missing values present in the data. Our code is available: https://github.com/huankoh/GST-Pro.