Search

Large language models have demonstrated exceptional capability in natural language understanding and generation. However, their generation speed is limited by the inherently sequential nature of their decoding process, posing challenges for real-time applications. This paper introduces Lexical Unit Decoding (LUD), a novel decoding methodology implemented in a data-driven manner, accelerating the decoding process without sacrificing output quality. The core of our approach is the observation that a pre-trained language model can confidently predict multiple contiguous tokens, forming the basis for a \textit{lexical unit}, in which these contiguous tokens could be decoded in parallel. Extensive experiments validate that our method substantially reduces decoding time while maintaining generation quality, i.e., 33\% speed up on natural language generation with no quality loss, and 30\% speed up on code generation with a negligible quality loss of 3\%. Distinctively, LUD requires no auxiliary models and does not require changes to existing architectures. It can also be integrated with other decoding acceleration methods, thus achieving an even more pronounced inference efficiency boost. We posit that the foundational principles of LUD could define a new decoding paradigm for future language models, enhancing their applicability for a broader spectrum of applications. All codes are be publicly available at https://github.com/tjunlp-lab/Lexical-Unit-Decoding-LUD-. Keywords: Parallel Decoding, Lexical Unit Decoding, Large Language Model, Comment: Accepted for publication at LREC-COLING 2024

Data is essential to performing time series analysis utilizing machine learning approaches, whether for classic models or today's large language models. A good time-series dataset is advantageous for the model's accuracy, robustness, and convergence, as well as task outcomes and costs. The emergence of data-centric AI represents a shift in the landscape from model refinement to prioritizing data quality. Even though time-series data processing methods frequently come up in a wide range of research fields, it hasn't been well investigated as a specific topic. To fill the gap, in this paper, we systematically review different data-centric methods in time series analysis, covering a wide range of research topics. Based on the time-series data characteristics at sample, feature, and period, we propose a taxonomy for the reviewed data selection methods. In addition to discussing and summarizing their characteristics, benefits, and drawbacks targeting time-series data, we also introduce the challenges and opportunities by proposing recommendations, open problems, and possible research topics., Comment: 9 pages, 1 figure

We have developed an individual identification system based on magnetocardiography (MCG) signals captured using optically pumped magnetometers (OPMs). Our system utilizes pattern recognition to analyze the signals obtained at different positions on the body, by scanning the matrices composed of MCG signals with a 2*2 window. In order to make use of the spatial information of MCG signals, we transform the signals from adjacent small areas into four channels of a dataset. We further transform the data into time-frequency matrices using wavelet transforms and employ a convolutional neural network (CNN) for classification. As a result, our system achieves an accuracy rate of 97.04% in identifying individuals. This finding indicates that the MCG signal holds potential for use in individual identification systems, offering a valuable tool for personalized healthcare management., Comment: 7 pages, 5 figures. Author manuscript accepted for AAAI 2024 Spring Symposium on Clinical Foundation Models

Spiking Neural Networks (SNNs) have a greater potential for modeling time series data than Artificial Neural Networks (ANNs), due to their inherent neuron dynamics and low energy consumption. However, it is difficult to demonstrate their superiority in classification accuracy, because current efforts mainly focus on designing better network structures. In this work, enlighten by brain-inspired science, we find that, not only the structure but also the learning process should be human-like. To achieve this, we investigate the power of Curriculum Learning (CL) on SNNs by designing a novel method named CSNN with two theoretically guaranteed mechanisms: The active-to-dormant training order makes the curriculum similar to that of human learning and suitable for spiking neurons; The value-based regional encoding makes the neuron activity to mimic the brain memory when learning sequential data. Experiments on multiple time series sources including simulated, sensor, motion, and healthcare demonstrate that CL has a more positive effect on SNNs than ANNs with about twice the accuracy change, and CSNN can increase about 3% SNNs' accuracy by improving network sparsity, neuron firing status, anti-noise ability, and convergence speed., Comment: 11 pages, 3 figures

Time series widely exists in real-world applications and many deep learning models have performed well on it. Current research has shown the importance of learning strategy for models, suggesting that the benefit is the order and size of learning samples. However, no effective strategy has been proposed for time series due to its abstract and dynamic construction. Meanwhile, the existing one-shot tasks and continuous tasks for time series necessitate distinct learning processes and mechanisms. No all-purpose approach has been suggested. In this work, we propose a novel Curricular and CyclicaL loss (CRUCIAL) to learn time series for the first time. It is model- and task-agnostic and can be plugged on top of the original loss with no extra procedure. CRUCIAL has two characteristics: It can arrange an easy-to-hard learning order by dynamically determining the sample contribution and modulating the loss amplitude; It can manage a cyclically changed dataset and achieve an adaptive cycle by correlating the loss distribution and the selection probability. We prove that compared with monotonous size, cyclical size can reduce expected error. Experiments on 3 kinds of tasks and 5 real-world datasets show the benefits of CRUCIAL for most deep learning models when learning time series., Comment: 23 pages, 5 figures

We tackle the challenge of learning to charge Electric Vehicles (EVs) with Out-of-Distribution (OOD) data. Traditional scheduling algorithms typically fail to balance near-optimal average performance with worst-case guarantees, particularly with OOD data. Model Predictive Control (MPC) is often too conservative and data-independent, whereas Reinforcement Learning (RL) tends to be overly aggressive and fully trusts the data, hindering their ability to consistently achieve the best-of-both-worlds. To bridge this gap, we introduce a novel OOD-aware scheduling algorithm, denoted OOD-Charging. This algorithm employs a dynamic "awareness radius", which updates in real-time based on the Temporal Difference (TD)-error that reflects the severity of OOD. The OOD-Charging algorithm allows for a more effective balance between consistency and robustness in EV charging schedules, thereby significantly enhancing adaptability and efficiency in real-world charging environments. Our results demonstrate that this approach improves the scheduling reward reliably under real OOD scenarios with remarkable shifts of EV charging behaviors caused by COVID-19 in the Caltech ACN-Data., Comment: 12 pages, 7 figures

Federated Learning (FL) has demonstrated a significant potential to improve the quality of service (QoS) of EV charging stations. While existing studies have primarily focused on developing FL algorithms, the effect of FL on the charging stations' operation in terms of price competition has yet to be fully understood. This paper aims to fill this gap by modeling the strategic interactions between two charging stations and EV owners as a multi-stage game. Each station first decides its FL participation strategy and charging price, and then individual EV owners decide their charging strategies. The game analysis involves solving a non-concave problem and by decomposing it into a piece-wise concave program we manage to fully characterize the equilibrium. Based on real-world datasets, our numerical results reveal an interesting insight: even if FL improves QoS, it can lead to smaller profits for both stations. The key reason is that FL intensifies the price competition between charging stations by improving stations' QoS to a similar level. We further show that the stations will participate in FL when their data distributions are mildly dissimilar., Comment: Accepted to IEEE ISGT EUROPE 2023

This work summarizes two ways to accomplish Time-Series (TS) tasks in today's Large Language Model (LLM) context: LLM-for-TS (model-centric) designs and trains a fundamental large model, or fine-tunes a pre-trained LLM for TS data; TS-for-LLM (data-centric) converts TS into a model-friendly representation to enable the pre-trained LLM to handle TS data. Given the lack of data, limited resources, semantic context requirements, and so on, this work focuses on TS-for-LLM, where we aim to activate LLM's ability for TS data by designing a TS embedding method suitable for LLM. The proposed method is named TEST. It first tokenizes TS, builds an encoder to embed TS via instance-wise, feature-wise, and text-prototype-aligned contrast, where the TS embedding space is aligned to LLM embedding layer space, then creates soft prompts to make LLM more open to that embeddings, and finally implements TS tasks using the frozen LLM. We also demonstrate the feasibility of TS-for-LLM through theory and experiments. Experiments are carried out on TS classification, forecasting, and representation tasks using eight frozen LLMs with various structures and sizes. The results show that the pre-trained LLM with TEST strategy can achieve better or comparable performance than today's SOTA TS models and offer benefits for few-shot and generalization. By treating LLM as the pattern machine, TEST can endow LLM's ability to process TS data without compromising language ability. We hope that this study will serve as a foundation for future work to support TS+LLM progress.

While Current TTS systems perform well in synthesizing high-quality speech, producing highly expressive speech remains a challenge. Emphasis, as a critical factor in determining the expressiveness of speech, has attracted more attention nowadays. Previous works usually enhance the emphasis by adding intermediate features, but they can not guarantee the overall expressiveness of the speech. To resolve this matter, we propose Emphatic Expressive TTS (EE-TTS), which leverages multi-level linguistic information from syntax and semantics. EE-TTS contains an emphasis predictor that can identify appropriate emphasis positions from text and a conditioned acoustic model to synthesize expressive speech with emphasis and linguistic information. Experimental results indicate that EE-TTS outperforms baseline with MOS improvements of 0.49 and 0.67 in expressiveness and naturalness. EE-TTS also shows strong generalization across different datasets according to AB test results., Comment: Accepted by Interspeech 2023, fix some typos

Continuous diagnosis and prognosis are essential for intensive care patients. It can provide more opportunities for timely treatment and rational resource allocation, especially for sepsis, a main cause of death in ICU, and COVID-19, a new worldwide epidemic. Although deep learning methods have shown their great superiority in many medical tasks, they tend to catastrophically forget, over fit, and get results too late when performing diagnosis and prognosis in the continuous mode. In this work, we summarized the three requirements of this task, proposed a new concept, continuous classification of time series (CCTS), and designed a novel model training method, restricted update strategy of neural networks (RU). In the context of continuous prognosis, our method outperformed all baselines and achieved the average accuracy of 90%, 97%, and 85% on sepsis prognosis, COVID-19 mortality prediction, and eight diseases classification. Superiorly, our method can also endow deep learning with interpretability, having the potential to explore disease mechanisms and provide a new horizon for medical research. We have achieved disease staging for sepsis and COVID-19, discovering four stages and three stages with their typical biomarkers respectively. Further, our method is a data-agnostic and model-agnostic plug-in, it can be used to continuously prognose other diseases with staging and even implement CCTS in other fields., Comment: 41 pages, 15 figures

In the real world, the class of a time series is usually labeled at the final time, but many applications require to classify time series at every time point. e.g. the outcome of a critical patient is only determined at the end, but he should be diagnosed at all times for timely treatment. Thus, we propose a new concept: Continuous Classification of Time Series (CCTS). It requires the model to learn data in different time stages. But the time series evolves dynamically, leading to different data distributions. When a model learns multi-distribution, it always forgets or overfits. We suggest that meaningful learning scheduling is potential due to an interesting observation: Measured by confidence, the process of model learning multiple distributions is similar to the process of human learning multiple knowledge. Thus, we propose a novel Confidence-guided method for CCTS (C3TS). It can imitate the alternating human confidence described by the Dunning-Kruger Effect. We define the objective- confidence to arrange data, and the self-confidence to control the learning duration. Experiments on four real-world datasets show that C3TS is more accurate than all baselines for CCTS., Comment: 20 pages, 12 figures

The rapid growth of electric vehicles (EVs) has promised a next-generation transportation system with reduced carbon emission. The fast development of EVs and charging facilities is driving the evolution of Internet of Vehicles (IoV) to Internet of Electric Vehicles (IoEV). IoEV benefits from both smart grid and Internet of Things (IoT) technologies which provide advanced bi-directional charging services and real-time data processing capability, respectively. The major design challenges of the IoEV charging control lie in the randomness of charging events and the mobility of EVs. In this article, we present a holistic review on advanced bi-directional EV charging control algorithms. For Grid-to-Vehicle (G2V), we introduce the charging control problem in two scenarios: 1) Operation of a single charging station and 2) Operation of multiple charging stations in coupled transportation and power networks. For Vehicle-to-Grid (V2G), we discuss how EVs can perform energy trading in the electricity market and provide ancillary services to the power grid. Besides, a case study is provided to illustrate the economic benefit of the joint optimization of routing and charging scheduling of multiple EVs in the IoEV. Last but not the least, we will highlight some open problems and future research directions of charging scheduling problems for IoEVs.

Since data is presented long-tailed in reality, it is challenging for Federated Learning (FL) to train across decentralized clients as practical applications. We present Global-Regularized Personalization (GRP-FED) to tackle the data imbalanced issue by considering a single global model and multiple local models for each client. With adaptive aggregation, the global model treats multiple clients fairly and mitigates the global long-tailed issue. Each local model is learned from the local data and aligns with its distribution for customization. To prevent the local model from just overfitting, GRP-FED applies an adversarial discriminator to regularize between the learned global-local features. Extensive results show that our GRP-FED improves under both global and local scenarios on real-world MIT-BIH and synthesis CIFAR-10 datasets, achieving comparable performance and addressing client imbalance., Comment: (FL-ICML'21) International Workshop on Federated Learning for User Privacy and Data Confidentiality in Conjunction with ICML 2021

Prediction based on Irregularly Sampled Time Series (ISTS) is of wide concern in the real-world applications. For more accurate prediction, the methods had better grasp more data characteristics. Different from ordinary time series, ISTS is characterised with irregular time intervals of intra-series and different sampling rates of inter-series. However, existing methods have suboptimal predictions due to artificially introducing new dependencies in a time series and biasedly learning relations among time series when modeling these two characteristics. In this work, we propose a novel Time Encoding (TE) mechanism. TE can embed the time information as time vectors in the complex domain. It has the the properties of absolute distance and relative distance under different sampling rates, which helps to represent both two irregularities of ISTS. Meanwhile, we create a new model structure named Time Encoding Echo State Network (TE-ESN). It is the first ESNs-based model that can process ISTS data. Besides, TE-ESN can incorporate long short-term memories and series fusion to grasp horizontal and vertical relations. Experiments on one chaos system and three real-world datasets show that TE-ESN performs better than all baselines and has better reservoir property., Comment: 7 pages, 4 figures, accepted by IJCAI 2021

Recurrent Neural Networks (RNNs) have demonstrated their outstanding ability in sequence tasks and have achieved state-of-the-art in wide range of applications, such as industrial, medical, economic and linguistic. Echo State Network (ESN) is simple type of RNNs and has emerged in the last decade as an alternative to gradient descent training based RNNs. ESN, with a strong theoretical ground, is practical, conceptually simple, easy to implement. It avoids non-converging and computationally expensive in the gradient descent methods. Since ESN was put forward in 2002, abundant existing works have promoted the progress of ESN, and the recently introduced Deep ESN model opened the way to uniting the merits of deep learning and ESNs. Besides, the combinations of ESNs with other machine learning models have also overperformed baselines in some applications. However, the apparent simplicity of ESNs can sometimes be deceptive and successfully applying ESNs needs some experience. Thus, in this paper, we categorize the ESN-based methods to basic ESNs, DeepESNs and combinations, then analyze them from the perspective of theoretical studies, network designs and specific applications. Finally, we discuss the challenges and opportunities of ESNs by summarizing the open questions and proposing possible future works., Comment: 37 pages, 5 figures, 2 tables

Irregularly sampled time series (ISTS) data has irregular temporal intervals between observations and different sampling rates between sequences. ISTS commonly appears in healthcare, economics, and geoscience. Especially in the medical environment, the widely used Electronic Health Records (EHRs) have abundant typical irregularly sampled medical time series (ISMTS) data. Developing deep learning methods on EHRs data is critical for personalized treatment, precise diagnosis and medical management. However, it is challenging to directly use deep learning models for ISMTS data. On the one hand, ISMTS data has the intra-series and inter-series relations. Both the local and global structures should be considered. On the other hand, methods should consider the trade-off between task accuracy and model complexity and remain generality and interpretability. So far, many existing works have tried to solve the above problems and have achieved good results. In this paper, we review these deep learning methods from the perspectives of technology and task. Under the technology-driven perspective, we summarize them into two categories - missing data-based methods and raw data-based methods. Under the task-driven perspective, we also summarize them into two categories - data imputation-oriented and downstream task-oriented. For each of them, we point out their advantages and disadvantages. Moreover, we implement some representative methods and compare them on four medical datasets with two tasks. Finally, we discuss the challenges and opportunities in this area., Comment: 19 pages, 7 figures