Large language models (LLMs) offer impressive performance in various zero-shot and few-shot tasks. However, their success in zero-shot or few-shot settings may be affected by task contamination, a potential limitation that has not been thoroughly examined. This paper investigates how zero-shot and few-shot performance of LLMs has changed chronologically over datasets released over time, and over LLMs released over time. Utilizing GPT-3 series models and several other recent open-sourced LLMs, and controlling for dataset difficulty, we find that datasets released prior to the LLM training data creation date perform surprisingly better than datasets released post the LLM training data creation date. This strongly indicates that, for many LLMs, there exists task contamination on zero-shot and few-shot evaluation for datasets prior to the LLMs' training data creation date. Additionally, we utilize training data inspection, training data extraction, and a membership inference attack, which reveal further evidence of task contamination. Importantly, we find that for tasks with no possibility of task contamination, LLMs rarely demonstrate statistically significant improvements over simple majority baselines, in both zero and few-shot settings.
论文检索
输入标题、作者或关键词，从 2,101 篇学术成果中精准定位
Towards the Disappearing Truth: Fine-Grained Joint Causal Influences Learning with Hidden Variable-Driven Causal Hypergraphs in Time Series
PDF ↗Causal discovery under Granger causality framework has yielded widespread concerns in time series analysis task. Nevertheless, most previous methods are unaware of the underlying causality disappearing problem, that is, certain weak causalities are less focusable and may be lost during the modeling process, thus leading to biased causal conclusions. Therefore, we propose to introduce joint causal influences (i.e., causal influences from the union of multiple variables) as additional causal indication information to help identify weak causalities. Further, to break the limitation of existing methods that implicitly and coarsely model joint causal influences, we propose a novel hidden variable-driven causal hypergraph neural network to meticulously explore the locality and diversity of joint causal influences, and realize its explicit and fine-grained modeling. Specifically, we introduce hidden variables to construct a causal hypergraph for explicitly characterizing various fine-grained joint causal influences. Then, we customize a dual causal information transfer mechanism (encompassing a multi-level causal path and an information aggregation path) to realize the free diffusion and meticulous aggregation of joint causal influences and facilitate its adaptive learning. Finally, we design a multi-view collaborative optimization constraint to guarantee the characterization diversity of causal hypergraph and capture remarkable forecasting relationships (i.e., causalities). Experiments are conducted to demonstrate the superiority of the proposed model.
United We Stand: Accelerating Privacy-Preserving Neural Inference by Conjunctive Optimization with Interleaved Nexus
PDF ↗Privacy-preserving Machine Learning as a Service (MLaaS) enables the powerful cloud server to run its well-trained neural model upon the input from resource-limited client, with both of server's model parameters and client's input data protected. While computation efficiency is critical for the practical implementation of privacy-preserving MLaaS and it is inspiring to witness recent advances towards efficiency improvement, there still exists a significant performance gap to real-world applications. In general, state-of-the-art frameworks perform function-wise efficiency optimization based on specific cryptographic primitives. Although it is logical, such independent optimization for each function makes noticeable amount of expensive operations unremovable and misses the opportunity to further accelerate the performance by jointly considering privacy-preserving computation among adjacent functions. As such, we propose COIN: Conjunctive Optimization with Interleaved Nexus, which remodels mainstream computation for each function to conjunctive counterpart for composite function, with a series of united optimization strategies. Specifically, COIN jointly computes a pair of consecutive nonlinear-linear functions in the neural model by reconstructing the intermediates throughout the whole procedure, which not only eliminates the most expensive crypto operations without invoking extra encryption enabler, but also makes the online crypto complexity independent of filter size. Experimentally, COIN demonstrates 11.2x to 29.6x speedup over various function dimensions from modern networks, and 6.4x to 12x speedup on the total computation time when applied in networks with model input from small-scale CIFAR10 to large-scale ImageNet.
Forecasting irregularly sampled time series with missing values is a crucial task for numerous real-world applications such as healthcare, astronomy, and climate sciences. State-of-the-art approaches to this problem rely on Ordinary Differential Equations (ODEs) which are known to be slow and often require additional features to handle missing values. To address this issue, we propose a novel model using Graphs for Forecasting Irregularly Sampled Time Series with missing values which we call GraFITi. GraFITi first converts the time series to a Sparsity Structure Graph which is a sparse bipartite graph, and then reformulates the forecasting problem as the edge weight prediction task in the graph. It uses the power of Graph Neural Networks to learn the graph and predict the target edge weights. GraFITi has been tested on 3 real-world and 1 synthetic irregularly sampled time series dataset with missing values and compared with various state-of-the-art models. The experimental results demonstrate that GraFITi improves the forecasting accuracy by up to 17% and reduces the run time up to 5 times compared to the state-of-the-art forecasting models.
Continuous-time models such as Neural ODEs and Neural Flows have shown promising results in analyzing irregularly sampled time series frequently encountered in electronic health records. Based on these models, time series are typically processed with a hybrid of an initial value problem (IVP) solver and a recurrent neural network within the variational autoencoder architecture. Sequentially solving IVPs makes such models computationally less efficient. In this paper, we propose to model time series purely with continuous processes whose state evolution can be approximated directly by IVPs. This eliminates the need for recurrent computation and enables multiple states to evolve in parallel. We further fuse the encoder and decoder with one IVP solver utilizing its invertibility, which leads to fewer parameters and faster convergence. Experiments on three real-world datasets show that the proposed method can systematically outperform its predecessors, achieve state-of-the-art results, and have significant advantages in terms of data efficiency.
Financial simulators play an important role in enhancing forecasting accuracy, managing risks, and fostering strategic financial decision-making. Despite the development of financial market simulation methodologies, existing frameworks often struggle with adapting to specialized simulation context. We pinpoint the challenges as i) current financial datasets do not contain context labels; ii) current techniques are not designed to generate financial data with context as control, which demands greater precision compared to other modalities; iii) the inherent difficulties in generating context-aligned, high-fidelity data given the non-stationary, noisy nature of financial data. To address these challenges, our contributions are: i) we proposed the Contextual Market Dataset with market dynamics, stock ticker, and history state as context, leveraging a market dynamics modeling method that combines linear regression and clustering to extract market dynamics; ii) we present Market-GAN, a novel architecture incorporating a Generative Adversarial Networks (GAN) for the controllable generation with context, an autoencoder for learning low-dimension features, and supervisors for knowledge transfer; iii) we introduce a two-stage training scheme to ensure that Market-GAN captures the intrinsic market distribution with multiple objectives. In the pertaining stage, with the use of the autoencoder and supervisors, we prepare the generator with a better initialization for the adversarial training stage. We propose a set of holistic evaluation metrics that consider alignment, fidelity, data usability on downstream tasks, and market facts. We evaluate Market-GAN with the Dow Jones Industrial Average data from 2000 to 2023 and showcase superior performance in comparison to 4 state-of-the-art time-series generative models.
Contrastive learning, as a self-supervised learning paradigm, becomes popular for Multivariate Time-Series (MTS) classification. It ensures the consistency across different views of unlabeled samples and then learns effective representations for these samples. Existing contrastive learning methods mainly focus on achieving temporal consistency with temporal augmentation and contrasting techniques, aiming to preserve temporal patterns against perturbations for MTS data. However, they overlook spatial consistency that requires the stability of individual sensors and their correlations. As MTS data typically originate from multiple sensors, ensuring spatial consistency becomes essential for the overall performance of contrastive learning on MTS data. Thus, we propose Graph-Aware Contrasting for spatial consistency across MTS data. Specifically, we propose graph augmentations including node and edge augmentations to preserve the stability of sensors and their correlations, followed by graph contrasting with both node- and graph-level contrasting to extract robust sensor- and global-level features. We further introduce multi-window temporal contrasting to ensure temporal consistency in the data for each sensor. Extensive experiments demonstrate that our proposed method achieves state-of-the-art performance on various MTS classification tasks. The code is available at https://github.com/Frank-Wang-oss/TS-GAC.
Multivariate Time-Series (MTS) data is crucial in various application fields. With its sequential and multi-source (multiple sensors) properties, MTS data inherently exhibits Spatial-Temporal (ST) dependencies, involving temporal correlations between timestamps and spatial correlations between sensors in each timestamp. To effectively leverage this information, Graph Neural Network-based methods (GNNs) have been widely adopted. However, existing approaches separately capture spatial dependency and temporal dependency and fail to capture the correlations between Different sEnsors at Different Timestamps (DEDT). Overlooking such correlations hinders the comprehensive modelling of ST dependencies within MTS data, thus restricting existing GNNs from learning effective representations. To address this limitation, we propose a novel method called Fully-Connected Spatial-Temporal Graph Neural Network (FC-STGNN), including two key components namely FC graph construction and FC graph convolution. For graph construction, we design a decay graph to connect sensors across all timestamps based on their temporal distances, enabling us to fully model the ST dependencies by considering the correlations between DEDT. Further, we devise FC graph convolution with a moving-pooling GNN layer to effectively capture the ST dependencies for learning effective representations. Extensive experiments show the effectiveness of FC-STGNN on multiple MTS datasets compared to SOTA methods. The code is available at https://github.com/Frank-Wang-oss/FCSTGNN.
Considering Nonstationary within Multivariate Time Series with Variational Hierarchical Transformer for Forecasting
PDF ↗The forecasting of Multivariate Time Series (MTS) has long been an important but challenging task. Due to the non-stationary problem across long-distance time steps, previous studies primarily adopt stationarization method to attenuate the non-stationary problem of original series for better predictability. However, existed methods always adopt the stationarized series, which ignore the inherent non-stationarity, and have difficulty in modeling MTS with complex distributions due to the lack of stochasticity. To tackle these problems, we first develop a powerful hierarchical probabilistic generative module to consider the non-stationarity and stochastity characteristics within MTS, and then combine it with transformer for a well-defined variational generative dynamic model named Hierarchical Time series Variational Transformer (HTV-Trans), which recovers the intrinsic non-stationary information into temporal dependencies. Being an powerful probabilistic model, HTV-Trans is utilized to learn expressive representations of MTS and applied to the forecasting tasks. Extensive experiments on diverse datasets show the efficiency of HTV-Trans on MTS forecasting tasks.
N-gram Unsupervised Compoundation and Feature Injection for Better Symbolic Music Understanding
PDF ↗The first step to apply deep learning techniques for symbolic music understanding is to transform musical pieces (mainly in MIDI format) into sequences of predefined tokens like note pitch, note velocity, and chords. Subsequently, the sequences are fed into a neural sequence model to accomplish specific tasks. Music sequences exhibit strong correlations between adjacent elements, making them prime candidates for N-gram techniques from Natural Language Processing (NLP). Consider classical piano music: specific melodies might recur throughout a piece, with subtle variations each time. In this paper, we propose a novel method, NG-Midiformer, for understanding symbolic music sequences that leverages the N-gram approach. Our method involves first processing music pieces into word-like sequences with our proposed unsupervised compoundation, followed by using our N-gram Transformer encoder, which can effectively incorporate N-gram information to enhance the primary encoder part for better understanding of music sequences. The pre-training process on large-scale music datasets enables the model to thoroughly learn the N-gram information contained within music sequences, and subsequently apply this information for making inferences during the fine-tuning stage. Experiment on various datasets demonstrate the effectiveness of our method and achieved state-of-the-art performance on a series of music understanding downstream tasks. The code and model weights will be released at https://github.com/CinqueOrigin/NG-Midiformer.
Domain incremental object detection (DIOD) aims to gradually learn a unified object detection model from a dataset stream composed of different domains, achieving good performance in all encountered domains. The most critical obstacle to this goal is the catastrophic forgetting problem, where the performance of the model improves rapidly in new domains but deteriorates sharply in old ones after a few sessions. To address this problem, we propose a non-exemplar DIOD method named learning domain bias (LDB), which learns domain bias independently at each new session, avoiding saving examples from old domains. Concretely, a base model is first obtained through training during session 1. Then, LDB freezes the weights of the base model and trains individual domain bias for each new incoming domain, adapting the base model to the distribution of new domains. At test time, since the domain ID is unknown, we propose a domain selector based on nearest mean classifier (NMC), which selects the most appropriate domain bias for a test image. Extensive experimental evaluations on two series of datasets demonstrate the effectiveness of the proposed LDB method in achieving high accuracy on new and old domain datasets. The code is available at https://github.com/SONGX1997/LDB.
Curriculum adversarial training empirically finds that gradually increasing the hardness of adversarial examples can further improve the adversarial robustness of the trained model compared to conventional adversarial training. However, theoretical understanding of this strategy remains limited. In an attempt to bridge this gap, we analyze the adversarial training process from an online perspective. Specifically, we treat adversarial examples in different iterations as samples from different adversarial distributions. We then introduce the time series prediction framework and deduce novel generalization error bounds. Our theoretical results not only demonstrate the effectiveness of the conventional adversarial training algorithm but also explain why curriculum adversarial training methods can further improve adversarial generalization. We conduct comprehensive experiments to support our theory.
Learning the Causal Structure of Networked Dynamical Systems under Latent Nodes and Structured Noise
PDF ↗This paper considers learning the hidden causal network of a linear networked dynamical system (NDS) from the time series data at some of its nodes -- partial observability. The dynamics of the NDS are driven by colored noise that generates spurious associations across pairs of nodes, rendering the problem much harder. To address the challenge of noise correlation and partial observability, we assign to each pair of nodes a feature vector computed from the time series data of observed nodes. The feature embedding is engineered to yield structural consistency: there exists an affine hyperplane that consistently partitions the set of features, separating the feature vectors corresponding to connected pairs of nodes from those corresponding to disconnected pairs. The causal inference problem is thus addressed via clustering the designed features. We demonstrate with simple baseline supervised methods the competitive performance of the proposed causal inference mechanism under broad connectivity regimes and noise correlation levels, including a real world network. Further, we devise novel technical guarantees of structural consistency for linear NDS under the considered regime.
Data augmentation is a crucial component in training neural networks to overcome the limitation imposed by data size, and several techniques have been studied for time series. Although these techniques are effective in certain tasks, they have yet to be generalized to time series benchmarks. We find that current data augmentation techniques ruin the core information contained within the frequency domain. To address this issue, we propose a simple strategy to preserve spectral information (SimPSI) in time series data augmentation. SimPSI preserves the spectral information by mixing the original and augmented input spectrum weighted by a preservation map, which indicates the importance score of each frequency. Specifically, our experimental contributions are to build three distinct preservation maps: magnitude spectrum, saliency map, and spectrum-preservative map. We apply SimPSI to various time series data augmentations and evaluate its effectiveness across a wide range of time series benchmarks. Our experimental results support that SimPSI considerably enhances the performance of time series data augmentations by preserving core spectral information. The source code used in the paper is available at https://github.com/Hyun-Ryu/simpsi.
Efficient Learning of PDEs via Taylor Expansion and Sparse Decomposition into Value and Fourier Domains
PDF ↗Accelerating the learning of Partial Differential Equations (PDEs) from experimental data will speed up the pace of scientific discovery. Previous randomized algorithms exploit sparsity in PDE updates for acceleration. However such methods are applicable to a limited class of decomposable PDEs, which have sparse features in the value domain. We propose Reel, which accelerates the learning of PDEs via random projection and has much broader applicability. Reel exploits the sparsity by decomposing dense updates into sparse ones in both the value and frequency domains. This decomposition enables efficient learning when the source of the updates consists of gradually changing terms across large areas (sparse in the frequency domain) in addition to a few rapid updates concentrated in a small set of “interfacial” regions (sparse in the value domain). Random projection is then applied to compress the sparse signals for learning. To expand the model applicability, Taylor series expansion is used in Reel to approximate the nonlinear PDE updates with polynomials in the decomposable form. Theoretically, we derive a constant factor approximation between the projected loss function and the original one with poly-logarithmic number of projected dimensions. Experimentally, we provide empirical evidence that our proposed Reel can lead to faster learning of PDE models (70-98% reduction in training time when the data is compressed to 1% of its original size) with comparable quality as the non-compressed models.
Time series forecasting is a crucial task in various domains. Caused by factors such as trends, seasonality, or irregular fluctuations, time series often exhibits non-stationary. It obstructs stable feature propagation through deep layers, disrupts feature distributions, and complicates learning data distribution changes. As a result, many existing models struggle to capture the underlying patterns, leading to degraded forecasting performance. In this study, we tackle the challenge of non-stationarity in time series forecasting with our proposed framework called U-Mixer. By combining Unet and Mixer, U-Mixer effectively captures local temporal dependencies between different patches and channels separately to avoid the influence of distribution variations among channels, and merge low- and high-levels features to obtain comprehensive data representations. The key contribution is a novel stationarity correction method, explicitly restoring data distribution by constraining the difference in stationarity between the data before and after model processing to restore the non-stationarity information, while ensuring the temporal dependencies are preserved. Through extensive experiments on various real-world time series datasets, U-Mixer demonstrates its effectiveness and robustness, and achieves 14.5% and 7.7% improvements over state-of-the-art (SOTA) methods.
Artificial intelligence (AI) has immense potential in time series prediction, but most explainable tools have limited capabilities in providing a systematic understanding of important features over time. These tools typically rely on evaluating a single time point, overlook the time ordering of inputs, and neglect the time-sensitive nature of time series applications. These factors make it difficult for users, particularly those without domain knowledge, to comprehend AI model decisions and obtain meaningful explanations. We propose CGS-Mask, a post-hoc and model-agnostic cellular genetic strip mask-based saliency approach to address these challenges. CGS-Mask uses consecutive time steps as a cohesive entity to evaluate the impact of features on the final prediction, providing binary and sustained feature importance scores over time. Our algorithm optimizes the mask population iteratively to obtain the optimal mask in a reasonable time. We evaluated CGS-Mask on synthetic and real-world datasets, and it outperformed state-of-the-art methods in elucidating the importance of features over time. According to our pilot user study via a questionnaire survey, CGS-Mask is the most effective approach in presenting easily understandable time series prediction results, enabling users to comprehend the decision-making process of AI models with ease.
Semi-supervised time-series classification could effectively alleviate the issue of lacking labeled data. However, existing approaches usually ignore model interpretability, making it difficult for humans to understand the principles behind the predictions of a model. Shapelets are a set of discriminative subsequences that show high interpretability in time series classification tasks. Shapelet learning-based methods have demonstrated promising classification performance. Unfortunately, without enough labeled data, the shapelets learned by existing methods are often poorly discriminative, and even dissimilar to any subsequence of the original time series. To address this issue, we propose the Diffusion Language-Shapelets model (DiffShape) for semi-supervised time series classification. In DiffShape, a self-supervised diffusion learning mechanism is designed, which uses real subsequences as a condition. This helps to increase the similarity between the learned shapelets and real subsequences by using a large amount of unlabeled data. Furthermore, we introduce a contrastive language-shapelets learning strategy that improves the discriminability of the learned shapelets by incorporating the natural language descriptions of the time series. Experiments have been conducted on the UCR time series archive, and the results reveal that the proposed DiffShape method achieves state-of-the-art performance and exhibits superior interpretability over baselines.
TimesURL: Self-Supervised Contrastive Learning for Universal Time Series Representation Learning
PDF ↗Learning universal time series representations applicable to various types of downstream tasks is challenging but valuable in real applications. Recently, researchers have attempted to leverage the success of self-supervised contrastive learning (SSCL) in Computer Vision(CV) and Natural Language Processing(NLP) to tackle time series representation. Nevertheless, due to the special temporal characteristics, relying solely on empirical guidance from other domains may be ineffective for time series and difficult to adapt to multiple downstream tasks. To this end, we review three parts involved in SSCL including 1) designing augmentation methods for positive pairs, 2) constructing (hard) negative pairs, and 3) designing SSCL loss. For 1) and 2), we find that unsuitable positive and negative pair construction may introduce inappropriate inductive biases, which neither preserve temporal properties nor provide sufficient discriminative features. For 3), just exploring segment- or instance-level semantics information is not enough for learning universal representation. To remedy the above issues, we propose a novel self-supervised framework named TimesURL. Specifically, we first introduce a frequency-temporal-based augmentation to keep the temporal property unchanged. And then, we construct double Universums as a special kind of hard negative to guide better contrastive learning. Additionally, we introduce time reconstruction as a joint optimization objective with contrastive learning to capture both segment-level and instance-level information. As a result, TimesURL can learn high-quality universal representations and achieve state-of-the-art performance in 6 different downstream tasks, including short- and long-term forecasting, imputation, classification, anomaly detection and transfer learning.
Time-series generation has crucial practical significance for decision-making under uncertainty. Existing methods have various limitations like accumulating errors over time, significantly impacting downstream tasks. We develop a novel generation method, DT-VAE, that incorporates generalizable domain knowledge, is mathematically justified, and significantly outperforms existing methods by mitigating error accumulation through a cumulative difference learning mechanism. We evaluate the performance of DT-VAE on several downstream tasks using both semi-synthetic and real time-series datasets, including benchmark datasets and our newly curated COVID-19 hospitalization datasets. The COVID-19 datasets enrich existing resources for time-series analysis. Additionally, we introduce Diverse Trend Preserving (DTP), a time-series clustering-based evaluation for direct and interpretable assessments of generated samples, serving as a valuable tool for evaluating time-series generative models.