Search

Scaling law that rewards large datasets, complex models and enhanced data granularity has been observed in various fields of deep learning. Yet, studies on time series forecasting have cast doubt on scaling behaviors of deep learning methods for time series forecasting: while more training data improves performance, more capable models do not always outperform less capable models, and longer input horizons may hurt performance for some models. We propose a theory for scaling law for time series forecasting that can explain these seemingly abnormal behaviors. We take into account the impact of dataset size and model complexity, as well as time series data granularity, particularly focusing on the look-back horizon, an aspect that has been unexplored in previous theories. Furthermore, we empirically evaluate various models using a diverse set of time series forecasting datasets, which (1) verifies the validity of scaling law on dataset size and model complexity within the realm of time series forecasting, and (2) validates our theoretical framework, particularly regarding the influence of look back horizon. We hope our findings may inspire new models targeting time series forecasting datasets of limited size, as well as large foundational datasets and models for time series forecasting in future work. Code for our experiments has been made public at https://github.com/JingzheShi/ScalingLawForTimeSeriesForecasting., Comment: Accepted by NeurIPS 2024

Businesses and software platforms are increasingly turning to Large Language Models (LLMs) such as GPT-3.5, GPT-4, GLM-3, and LLaMa-2 for chat assistance with file access or as reasoning agents for customer service. However, current LLM-based customer service models have limited integration with customer profiles and lack the operational capabilities necessary for effective service. Moreover, existing API integrations emphasize diversity over the precision and error avoidance essential in real-world customer service scenarios. To address these issues, we propose an LLM agent named CHOPS (CHat with custOmer Profile in existing System), designed to: (1) efficiently utilize existing databases or systems for accessing user information or interacting with these systems following existing guidelines; (2) provide accurate and reasonable responses or carry out required operations in the system while avoiding harmful operations; and (3) leverage a combination of small and large LLMs to achieve satisfying performance at a reasonable inference cost. We introduce a practical dataset, the CPHOS-dataset, which includes a database, guiding files, and QA pairs collected from CPHOS, an online platform that facilitates the organization of simulated Physics Olympiads for high school teachers and students. We have conducted extensive experiments to validate the performance of our proposed CHOPS architecture using the CPHOS-dataset, with the aim of demonstrating how LLMs can enhance or serve as alternatives to human customer service. Code for our proposed architecture and dataset can be found at {https://github.com/JingzheShi/CHOPS}., Comment: Accepted by COLM 2024

Vision-language foundation models have exhibited remarkable success across a multitude of downstream tasks due to their scalability on extensive image-text paired data. However, these models also display significant limitations when applied to downstream tasks, such as fine-grained image classification, as a result of ``decision shortcuts'' that hinder their generalization capabilities. In this work, we find that the CLIP model possesses a rich set of features, encompassing both \textit{desired invariant causal features} and \textit{undesired decision shortcuts}. Moreover, the underperformance of CLIP on downstream tasks originates from its inability to effectively utilize pre-trained features in accordance with specific task requirements. To address this challenge, we propose a simple yet effective method, Spurious Feature Eraser (SEraser), to alleviate the decision shortcuts by erasing the spurious features. Specifically, we introduce a test-time prompt tuning paradigm that optimizes a learnable prompt, thereby compelling the model to exploit invariant features while disregarding decision shortcuts during the inference phase. The proposed method effectively alleviates excessive dependence on potentially misleading spurious information. We conduct comparative analysis of the proposed method against various approaches which validates the significant superiority.

Self-supervised learning has been actively studied in time series domain recently, especially for masked reconstruction. Most of these methods follow the "Pre-training + Fine-tuning" paradigm in which a new decoder replaces the pre-trained decoder to fit for a specific downstream task, leading to inconsistency of upstream and downstream tasks. In this paper, we first point out that the unification of task objectives and adaptation for task difficulty are critical for bridging the gap between time series masked reconstruction and forecasting. By reserving the pre-trained mask token during fine-tuning stage, the forecasting task can be taken as a special case of masked reconstruction, where the future values are masked and reconstructed based on history values. It guarantees the consistency of task objectives but there is still a gap in task difficulty. Because masked reconstruction can utilize contextual information while forecasting can only use historical information to reconstruct. To further mitigate the existed gap, we propose a simple yet effective prompt token tuning (PT-Tuning) paradigm, in which all pre-trained parameters are frozen and only a few trainable prompt tokens are added to extended mask tokens in element-wise manner. Extensive experiments on real-world datasets demonstrate the superiority of our proposed paradigm with state-of-the-art performance compared to representation learning and end-to-end supervised forecasting methods.

Nowadays, billions of people engage in communication and express their opinions on the internet daily. Unfortunately, not all of these expressions are friendly or compliant, making content moderation an indispensable task. A common approach is to use a discriminative model to classify the content, but this method often requires strict data engineering, otherwise it will face unacceptable overfitting. With the successful development of Large Language Models (LLMs) in recent years, LLM-based methods have become a feasible solution for handling tasks in various domains. Thanks to the knowledge of the foundation models, we can develop more robust privately deployed models with limited data via fine-tuning these foundation models. Moreover, as a generative model, it can provide detailed analysis of the review process, enhancing interpretability. In this paper, we introduce how to fine-tune a LLM model that can be privately deployed for content moderation. Specifically, we discuss the differences between discriminative and generative models using content moderation as an example. Additionally, we reveal that incorporating reasoning processes during the fine-tuning of LLMs can effectively alleviate overfitting, even if the model is not allowed to directly output reasoning processes during deployment. We present a complete process, from data collection and construction to model training and overfitting elimination, for fine-tuning LLMs in vertical domain deployments. We report the entire research process and the key findings in this paper, hoping to provide valuable experience for researchers who are fine-tuning privately deployed models in their domain-specific research.

To improve the data rate in differential chaos shift keying (DCSK) based ambient backscatter communication (AmBC) system, we propose a new AmBC system based on code index modulation (CIM), referred to as CIM-DCSK-AmBC system. In the proposed system, the CIM-DCSK signal transmitted in the direct link is used as the radio frequency source of the backscatter link. The signal format in the backscatter link is designed to increase the data rate as well as eliminate the interference of the direct link signal. As such, the direct link signal and the backscatter link signal can be received and demodulated simultaneously. Moreover, we derive and validate the theoretical bit error rate (BER) expressions of the CIM-DCSK-AmBC system over multipath Rayleigh fading channels. Regarding the short reference DCSK-based AmBC (SR-DCSK-AmBC) system as a benchmark system, numerical results reveal that the CIM-DCSK-AmBC system can achieve better BER performance in the direct link and higher throughput in the backscatter link than the benchmark system.

The rapid development of digital economy has led to the emergence of various black and shadow internet industries, which pose potential risks that can be identified and managed through digital risk management (DRM) that uses different techniques such as machine learning and deep learning. The evolution of DRM architecture has been driven by changes in data forms. However, the development of AI-generated content (AIGC) technology, such as ChatGPT and Stable Diffusion, has given black and shadow industries powerful tools to personalize data and generate realistic images and conversations for fraudulent activities. This poses a challenge for DRM systems to control risks from the source of data generation and to respond quickly to the fast-changing risk environment. This paper aims to provide a technical analysis of the challenges and opportunities of AIGC from upstream, midstream, and downstream paths of black/shadow industries and suggest future directions for improving existing risk control systems. The paper will explore the new black and shadow techniques triggered by generative AI technology and provide insights for building the next-generation DRM system.

Large language models have demonstrated surprising ability to perform in-context learning, i.e., these models can be directly applied to solve numerous downstream tasks by conditioning on a prompt constructed by a few input-output examples. However, prior research has shown that in-context learning can suffer from high instability due to variations in training examples, example order, and prompt formats. Therefore, the construction of an appropriate prompt is essential for improving the performance of in-context learning. In this paper, we revisit this problem from the view of predictive bias. Specifically, we introduce a metric to evaluate the predictive bias of a fixed prompt against labels or a given attributes. Then we empirically show that prompts with higher bias always lead to unsatisfactory predictive quality. Based on this observation, we propose a novel search strategy based on the greedy search to identify the near-optimal prompt for improving the performance of in-context learning. We perform comprehensive experiments with state-of-the-art mainstream models such as GPT-3 on various downstream tasks. Our results indicate that our method can enhance the model's in-context learning performance in an effective and interpretable manner.

Reservoir computing (RC), a particular form of recurrent neural network, is under explosive development due to its exceptional efficacy and high performance in reconstruction or/and prediction of complex physical systems. However, the mechanism triggering such effective applications of RC is still unclear, awaiting deep and systematic exploration. Here, combining the delayed embedding theory with the generalized embedding theory, we rigorously prove that RC is essentially a high dimensional embedding of the original input nonlinear dynamical system. Thus, using this embedding property, we unify into a universal framework the standard RC and the time-delayed RC where we novelly introduce time delays only into the network's output layer, and we further find a trade-off relation between the time delays and the number of neurons in RC. Based on this finding, we significantly reduce the network size of RC for reconstructing and predicting some representative physical systems, and, more surprisingly, only using a single neuron reservoir with time delays is sometimes sufficient for achieving those tasks.

Exploring the potential application of quantum computers in material design and drug discovery has attracted a lot of interest in the age of quantum computing. However, the quantum resource requirement for solving practical electronic structure problems are far beyond the capacity of near-term quantum devices. In this work, we integrate the divide-and-conquer (DC) approaches into the variational quantum eigensolver (VQE) for large-scale quantum computational chemistry simulations. Two popular divide-and-conquer schemes, including many-body expansion~(MBE) fragmentation theory and density matrix embedding theory~(DMET), are employed to divide complicated problems into many small parts that are easy to implement on near-term quantum computers. Pilot applications of these methods to systems consisting of tens of atoms are performed with adaptive VQE algorithms. This work should encourage further studies of using the philosophy of DC to solve electronic structure problems on quantum computers., Comment: 9 pages, 6 figures

Quantum computational chemistry (QCC) is the use of quantum computers to solve problems in computational quantum chemistry. We develop a high performance variational quantum eigensolver (VQE) simulator for simulating quantum computational chemistry problems on a new Sunway supercomputer. The major innovations include: (1) a Matrix Product State (MPS) based VQE simulator to reduce the amount of memory needed and increase the simulation efficiency; (2) a combination of the Density Matrix Embedding Theory with the MPS-based VQE simulator to further extend the simulation range; (3) A three-level parallelization scheme to scale up to 20 million cores; (4) Usage of the Julia script language as the main programming language, which both makes the programming easier and enables cutting edge performance as native C or Fortran; (5) Study of real chemistry systems based on the VQE simulator, achieving nearly linearly strong and weak scaling. Our simulation demonstrates the power of VQE for large quantum chemistry systems, thus paves the way for large-scale VQE experiments on near-term quantum computers., Comment: 13 pages, accepted by SC conference

In this paper, we propose two reconfigurable intelligent surface-aided $M$-ary frequency-modulated differential chaos shift keying (RIS-$M$-FM-DCSK) schemes. In scheme I, the RIS is regarded as a transmitter at the source to incorporate the $M$-ary phase-shift-keying ($M$-PSK) symbols into the FM chaotic signal and to reflect the resultant $M$-ary FM chaotic signal toward the destination. The information bits of the source are carried by both the positive/negative state of the FM chaotic signal and the $M$-PSK symbols. In scheme II, the RIS is treated as a relay so that both the source and relay can simultaneously transmit their information bits to the destination. The information bits of the source and relay are carried by the positive/negative state of the FM chaotic signal and $M$-PSK symbols generated by the RIS, respectively. The proposed RIS-$M$-FM-DCSK system has an attractive advantage that it does not require channel state information for detection, thus avoiding complex channel estimation. Moreover, we derive the theoretical expressions for bit error rates (BERs) of the proposed RIS-$M$-FM-DCSK system with both scheme I and scheme II over multipath Rayleigh fading channels. Simulations results not only verify the accuracy of the theoretical derivations, but also demonstrate the superiority of the proposed system. The proposed RIS-$M$-FM-DCSK system is a promising low-cost, low-power, and high-reliability alternative for wireless communication networks.

In this paper, we propose a reconfigurable intelligent surface (RIS)-assisted frequency-modulated (FM) differential chaos shift keying (DCSK) scheme with simultaneous wireless information and power transfer (SWIPT), called RIS-FM-DCSK-SWIPT scheme, for low-power, low-cost, and high-reliability wireless communication networks. In particular, the proposed scheme is developed under a non-linear energy-harvesting (EH) model which can accurately characterize the practical situation. The proposed RIS-FM-DCSK-SWIPT scheme has an appealing feature that it does not require channel state information, thus avoiding the complex channel estimation. We further derive the closed-form theoretical expressions for the energy shortage probability and bit error rate (BER) of the proposed scheme over the multipath Rayleigh fading channel. In addition, we investigate the influence of key parameters on the performance of the proposed transmission scheme in two different scenarios, i.e., RIS-assisted access point (RIS-AP) and dual-hop communication (RIS-DH). Finally, we carry out various Monte-Carlo experiments to verify the accuracy of the theoretical derivation, illustrate the performance advantage of the proposed scheme, and give some design insights for future study., Comment: accepted by IEEE Transactions on Communications

Data based detection and quantification of causation in complex, nonlinear dynamical systems is of paramount importance to science, engineering and beyond. Inspired by the widely used methodology in recent years, the cross-map-based techniques, we develop a general framework to advance towards a comprehensive understanding of dynamical causal mechanisms, which is consistent with the natural interpretation of causality. In particular, instead of measuring the smoothness of the cross map as conventionally implemented, we define causation through measuring the {\it scaling law} for the continuity of the investigated dynamical system directly. The uncovered scaling law enables accurate, reliable, and efficient detection of causation and assessment of its strength in general complex dynamical systems, outperforming those existing representative methods. The continuity scaling based framework is rigorously established and demonstrated using datasets from model complex systems and the real world., Comment: 7 figures; The article has been peer reviewed and accepted by RESEARCH