论文检索

Deep Learning/Sequential Models, Time series

Aaditya Singh, Stephanie Chan, Ted Moskovitz, Erin Grant, Andrew Saxe, Felix Hill

Transformer neural networks can exhibit a surprising capacity for in-context learning (ICL) despite not being explicitly trained for it. Prior work has provided a deeper understanding of how ICL emerges in transformers, e.g. through the lens of mechanistic interpretability, Bayesian inference, or by examining the distributional properties of training data. However, in each of these cases, ICL is treated largely as a persistent phenomenon; namely, once ICL emerges, it is assumed to persist asymptotically. Here, we show that the emergence of ICL during transformer training is, in fact, often transient. We train transformers on synthetic data designed so that both ICL and in-weights learning (IWL) strategies can lead to correct predictions. We find that ICL first emerges, then disappears and gives way to IWL, all while the training loss decreases, indicating an asymptotic preference for IWL. The transient nature of ICL is observed in transformers across a range of model sizes and datasets, raising the question of how much to ``overtrain'' transformers when seeking compact, cheaper-to-run models. We find that L2 regularization may offer a path to more persistent ICL that removes the need for early stopping based on ICL-style validation tasks. Finally, we present initial evidence that ICL transience may be caused by competition between ICL and IWL circuits.

Deep Learning/Sequential Models, Time series

Yihe Wang, Yu Han, Haishuai Wang, Xiang Zhang

Contrastive representation learning is crucial in medical time series analysis as it alleviates dependency on labor-intensive, domain-specific, and scarce expert annotations. However, existing contrastive learning methods primarily focus on one single data level, which fails to fully exploit the intricate nature of medical time series. To address this issue, we present COMET, an innovative hierarchical framework that leverages data consistencies at all inherent levels in medical time series. Our meticulously designed model systematically captures data consistency from four potential levels: observation, sample, trial, and patient levels. By developing contrastive loss at multiple levels, we can learn effective representations that preserve comprehensive data consistency, maximizing information utilization in a self-supervised manner. We conduct experiments in the challenging patient-independent setting. We compare COMET against six baselines using three diverse datasets, which include ECG signals for myocardial infarction and EEG signals for Alzheimer’s and Parkinson’s diseases. The results demonstrate that COMET consistently outperforms all baselines, particularly in setup with 10% and 1% labeled data fractions across all datasets. These results underscore the significant impact of our framework in advancing contrastive representation learning techniques for medical time series. The source code is available at https://github.com/DL4mHealth/COMET.

Deep Learning/Sequential Models, Time series

Chih-Yu (Andrew) Lai, Fan-Keng Sun, Zhengqi Gao, Jeffrey H Lang, Duane Boning

Time series anomaly detection is challenging due to the complexity and variety of patterns that can occur. One major difficulty arises from modeling time-dependent relationships to find contextual anomalies while maintaining detection accuracy for point anomalies. In this paper, we propose a framework for unsupervised time series anomaly detection that utilizes point-based and sequence-based reconstruction models. The point-based model attempts to quantify point anomalies, and the sequence-based model attempts to quantify both point and contextual anomalies. Under the formulation that the observed time point is a two-stage deviated value from a nominal time point, we introduce a nominality score calculated from the ratio of a combined value of the reconstruction errors. We derive an induced anomaly score by further integrating the nominality score and anomaly score, then theoretically prove the superiority of the induced anomaly score over the original anomaly score under certain conditions. Extensive studies conducted on several public datasets show that the proposed framework outperforms most state-of-the-art baselines for time series anomaly detection.

Deep Learning/Sequential Models, Time series

Dror Freirich, Tomer Michaeli, Ron Meir

Many practical settings call for the reconstruction of temporal signals from corrupted or missing data. Classic examples include decoding, tracking, signal enhancement and denoising. Since the reconstructed signals are ultimately viewed by humans, it is desirable to achieve reconstructions that are pleasing to human perception.Mathematically, perfect perceptual-quality is achieved when the distribution of restored signals is the same as that of natural signals, a requirement which has been heavily researched in static estimation settings (i.e. when a whole signal is processed at once). Here, we study the problem of optimal causal filtering under a perfect perceptual-quality constraint, which is a task of fundamentally different nature. Specifically, we analyze a Gaussian Markov signal observed through a linear noisy transformation. In the absence of perceptual constraints, the Kalman filter is known to be optimal in the MSE sense for this setting. Here, we show that adding the perfect perceptual quality constraint (i.e. the requirement of temporal consistency), introduces a fundamental dilemma whereby the filter may have to ``knowingly'' ignore new information revealed by the observations in order to conform to its past decisions. This often comes at the cost of a significant increase in the MSE (beyond that encountered in static settings). Our analysis goes beyond the classic innovation process of the Kalman filter, and introduces the novel concept of an unutilized information process. Using this tool, we present a recursive formula for perceptual filters, and demonstrate the qualitative effects of perfect perceptual-quality estimation on a video reconstruction problem.

Applications/Language, Speech and Dialog

Tong Wu, Zhihao Fan, Xiao Liu, Hai-Tao Zheng, Yeyun Gong, yelong shen, Jian Jiao, Juntao Li, zhongyu wei, Jian Guo 等

Diffusion models have gained significant attention in the realm of image generation due to their exceptional performance. Their success has been recently expanded to text generation via generating all tokens within a sequence concurrently. However, natural language exhibits a far more pronounced sequential dependency in comparison to images, and the majority of existing language models are trained with a left-to-right auto-regressive approach.To account for the inherent sequential characteristic of natural language, we introduce Auto-Regressive Diffusion (AR-Diffusion). AR-Diffusion ensures that the generation of tokens on the right depends on the generated ones on the left, a mechanism achieved through employing a dynamic number of denoising steps that vary based on token position. This results in tokens on the left undergoing fewer denoising steps than those on the right, thereby enabling them to generate earlier and subsequently influence the generation of tokens on the right.In a series of experiments on various text generation tasks, including text summarization, machine translation, and common sense generation, AR-Diffusion clearly demonstrated its superiority over existing diffusion language models and that it can be $100\times\sim600\times$ faster when achieving comparable results. Our code is available at https://github.com/microsoft/ProphetNet/tree/master/AR-diffusion.

Deep Learning/Sequential Models, Time series

Joon-Hyuk Ko, Hankyul Koh, Nojun Park, Wonho Jhe

Neural Ordinary Differential Equations (NeuralODEs) present an attractive way to extract dynamical laws from time series data, as they bridge neural networks with the differential equation-based modeling paradigm of the physical sciences. However, these models often display long training times and suboptimal results, especially for longer duration data. While a common strategy in the literature imposes strong constraints to the NeuralODE architecture to inherently promote stable model dynamics, such methods are ill-suited for dynamics discovery as the unknown governing equation is not guaranteed to satisfy the assumed constraints. In this paper, we develop a new training method for NeuralODEs, based on synchronization and homotopy optimization, that does not require changes to the model architecture. We show that synchronizing the model dynamics and the training data tames the originally irregular loss landscape, which homotopy optimization can then leverage to enhance training. Through benchmark experiments, we demonstrate our method achieves competitive or better training loss while often requiring less than half the number of training epochs compared to other model-agnostic techniques. Furthermore, models trained with our method display better extrapolation capabilities, highlighting the effectiveness of our method.

Deep Learning/Sequential Models, Time series

Alistair White, Niki Kilbertus, Maximilian Gelbrecht, Niklas Boers

Many successful methods to learn dynamical systems from data have recently been introduced. However, ensuring that the inferred dynamics preserve known constraints, such as conservation laws or restrictions on the allowed system states, remains challenging. We propose stabilized neural differential equations (SNDEs), a method to enforce arbitrary manifold constraints for neural differential equations. Our approach is based on a stabilization term that, when added to the original dynamics, renders the constraint manifold provably asymptotically stable. Due to its simplicity, our method is compatible with all common neural differential equation (NDE) models and broadly applicable. In extensive empirical evaluations, we demonstrate that SNDEs outperform existing methods while broadening the types of constraints that can be incorporated into NDE training.

Deep Learning/Sequential Models, Time series

Andrea Cini, Ivan Marisca, Daniele Zambon, Cesare Alippi

Spatiotemporal graph neural networks have shown to be effective in time series forecasting applications, achieving better performance than standard univariate predictors in several settings. These architectures take advantage of a graph structure and relational inductive biases to learn a single (global) inductive model to predict any number of the input time series, each associated with a graph node. Despite the gain achieved in computational and data efficiency w.r.t. fitting a set of local models, relying on a single global model can be a limitation whenever some of the time series are generated by a different spatiotemporal stochastic process. The main objective of this paper is to understand the interplay between globality and locality in graph-based spatiotemporal forecasting, while contextually proposing a methodological framework to rationalize the practice of including trainable node embeddings in such architectures. We ascribe to trainable node embeddings the role of amortizing the learning of specialized components. Moreover, embeddings allow for 1) effectively combining the advantages of shared message-passing layers with node-specific parameters and 2) efficiently transferring the learned model to new node sets. Supported by strong empirical evidence, we provide insights and guidelines for specializing graph-based models to the dynamics of each time series and show how this aspect plays a crucial role in obtaining accurate predictions.

Deep Learning/Sequential Models, Time series

Yuqi Chen, Kan Ren, Yansen Wang, Yuchen Fang, Weiwei Sun, Dongsheng Li

Modeling continuous-time dynamics on irregular time series is critical to account for data evolution and correlations that occur continuously. Traditional methods including recurrent neural networks or Transformer models leverage inductive bias via powerful neural architectures to capture complex patterns. However, due to their discrete characteristic, they have limitations in generalizing to continuous-time data paradigms. Though neural ordinary differential equations (Neural ODEs) and their variants have shown promising results in dealing with irregular time series, they often fail to capture the intricate correlations within these sequences. It is challenging yet demanding to concurrently model the relationship between input data points and capture the dynamic changes of the continuous-time system. To tackle this problem, we propose ContiFormer that extends the relation modeling of vanilla Transformer to the continuous-time domain, which explicitly incorporates the modeling abilities of continuous dynamics of Neural ODEs with the attention mechanism of Transformers. We mathematically characterize the expressive power of ContiFormer and illustrate that, by curated designs of function hypothesis, many Transformer variants specialized in irregular time series modeling can be covered as a special case of ContiFormer. A wide range of experiments on both synthetic and real-world datasets have illustrated the superior modeling capacities and prediction performance of ContiFormer on irregular time series data. The project link is https://seqml.github.io/contiformer/.

Deep Learning/Sequential Models, Time series

Kun Yi, Qi Zhang, Wei Fan, Hui He, Liang Hu, Pengyang Wang, Ning An, Longbing Cao, Zhendong Niu

Multivariate time series (MTS) forecasting has shown great importance in numerous industries. Current state-of-the-art graph neural network (GNN)-based forecasting methods usually require both graph networks (e.g., GCN) and temporal networks (e.g., LSTM) to capture inter-series (spatial) dynamics and intra-series (temporal) dependencies, respectively. However, the uncertain compatibility of the two networks puts an extra burden on handcrafted model designs. Moreover, the separate spatial and temporal modeling naturally violates the unified spatiotemporal inter-dependencies in real world, which largely hinders the forecasting performance. To overcome these problems, we explore an interesting direction of directly applying graph networks and rethink MTS forecasting from a pure graph perspective. We first define a novel data structure, hypervariate graph, which regards each series value (regardless of variates or timestamps) as a graph node, and represents sliding windows as space-time fully-connected graphs. This perspective considers spatiotemporal dynamics unitedly and reformulates classic MTS forecasting into the predictions on hypervariate graphs. Then, we propose a novel architecture Fourier Graph Neural Network (FourierGNN) by stacking our proposed Fourier Graph Operator (FGO) to perform matrix multiplications in Fourier space. FourierGNN accommodates adequate expressiveness and achieves much lower complexity, which can effectively and efficiently accomplish {the forecasting}. Besides, our theoretical analysis reveals FGO's equivalence to graph convolutions in the time domain, which further verifies the validity of FourierGNN. Extensive experiments on seven datasets have demonstrated our superior performance with higher efficiency and fewer parameters compared with state-of-the-art methods. Code is available at this repository: https://github.com/aikunyi/FourierGNN.

Deep Learning/Sequential Models, Time series

Ilze Amanda Auzina, Çağatay Yıldız, Sara Magliacane, Matthias Bethge, Efstratios Gavves

Neural ordinary differential equations (NODEs) have been proven useful for learning non-linear dynamics of arbitrary trajectories. However, current NODE methods capture variations across trajectories only via the initial state value or by auto-regressive encoder updates. In this work, we introduce Modulated Neural ODEs (MoNODEs), a novel framework that sets apart dynamics states from underlying static factors of variation and improves the existing NODE methods. In particular, we introduce *time-invariant modulator variables* that are learned from the data. We incorporate our proposed framework into four existing NODE variants. We test MoNODE on oscillating systems, videos and human walking trajectories, where each trajectory has trajectory-specific modulation. Our framework consistently improves the existing model ability to generalize to new dynamic parameterizations and to perform far-horizon forecasting. In addition, we verify that the proposed modulator variables are informative of the true unknown factors of variation as measured by $R^2$ scores.

Deep Learning/Sequential Models, Time series

Shangshang Yang, Xiaoshan Yu, Ye Tian, Xueming Yan, Haiping Ma, Xingyi Zhang

Knowledge tracing (KT) aims to trace students' knowledge states by predicting whether students answer correctly on exercises. Despite the excellent performance of existing Transformer-based KT approaches, they are criticized for the manually selected input features for fusion and the defect of single global context modelling to directly capture students' forgetting behavior in KT, when the related records are distant from the current record in terms of time. To address the issues, this paper first considers adding convolution operations to the Transformer to enhance its local context modelling ability used for students' forgetting behavior, then proposes an evolutionary neural architecture search approach to automate the input feature selection and automatically determine where to apply which operation for achieving the balancing of the local/global context modelling. In the search space, the original global path containing the attention module in Transformer is replaced with the sum of a global path and a local path that could contain different convolutions, and the selection of input features is also considered. To search the best architecture, we employ an effective evolutionary algorithm to explore the search space and also suggest a search space reduction strategy to accelerate the convergence of the algorithm. Experimental results on the two largest and most challenging education datasets demonstrate the effectiveness of the architecture found by the proposed approach.

Deep Learning/Sequential Models, Time series

Vaisakh Shaj Kumar, SALEH GHOLAM ZADEH, Ozan Demir, Luiz Douat, Gerhard Neumann

Intelligent agents use internal world models to reason and make predictions about different courses of their actions at many scales. Devising learning paradigms and architectures that allow machines to learn world models that operate at multiple levels of temporal abstractions while dealing with complex uncertainty predictions is a major technical hurdle. In this work, we propose a probabilistic formalism to learn multi-time scale world models which we call the Multi Time Scale State Space (MTS3) model. Our model uses a computationally efficient inference scheme on multiple time scales for highly accurate long-horizon predictions and uncertainty estimates over several seconds into the future. Our experiments, which focus on action conditional long horizon future predictions, show that MTS3 outperforms recent methods on several system identification benchmarks including complex simulated and real-world dynamical systems. Code is available at this repository:https://github.com/ALRhub/MTS3.

Deep Learning/Sequential Models, Time series

Allan Raventós, Mansheej Paul, Feng Chen, Surya Ganguli

Pretrained transformers exhibit the remarkable ability of in-context learning (ICL): they can learn tasks from just a few examples provided in the prompt without updating any weights. This raises a foundational question: can ICL solve fundamentally _new_ tasks that are very different from those seen during pretraining? To probe this question, we examine ICL’s performance on linear regression while varying the diversity of tasks in the pretraining dataset. We empirically demonstrate a _task diversity threshold_ for the emergence of ICL. Below this threshold, the pretrained transformer cannot solve unseen regression tasks, instead behaving like a Bayesian estimator with the _non-diverse pretraining task distribution_ as the prior. Beyond this threshold, the transformer significantly outperforms this estimator; its behavior aligns with that of ridge regression, corresponding to a Gaussian prior over _all tasks_, including those not seen during pretraining. Thus, when pretrained on data with task diversity greater than the threshold, transformers _can_ optimally solve fundamentally new tasks in-context. Importantly, this capability hinges on it deviating from the Bayes optimal estimator with the pretraining distribution as the prior. This study also explores the effect of regularization, model capacity and task structure and underscores, in a concrete example, the critical role of task diversity, alongside data and model scale, in the emergence of ICL.

Deep Learning/Sequential Models, Time series

Zihao Zhou, Rose Yu

Learning continuous-time point processes is essential to many discrete event forecasting tasks. However, integration poses a major challenge, particularly for spatiotemporal point processes (STPPs), as it involves calculating the likelihood through triple integrals over space and time. Existing methods for integrating STPP either assume a parametric form of the intensity function, which lacks flexibility; or approximating the intensity with Monte Carlo sampling, which introduces numerical errors. Recent work by Omi et al. proposes a dual network approach for efficient integration of flexible intensity function. However, their method only focuses on the 1D temporal point process. In this paper, we introduce a novel paradigm: `Auto-STPP` (Automatic Integration for Spatiotemporal Neural Point Processes) that extends the dual network approach to 3D STPP. While previous work provides a foundation, its direct extension overly restricts the intensity function and leads to computational challenges. In response, we introduce a decomposable parametrization for the integral network using ProdNet. This approach, leveraging the product of simplified univariate graphs, effectively sidesteps the computational complexities inherent in multivariate computational graphs. We prove the consistency of `Auto-STPP` and validate it on synthetic data and benchmark real-world datasets. `Auto-STPP` shows a significant advantage in recovering complex intensity functions from irregular spatiotemporal events, particularly when the intensity is sharply localized. Our code is open-source at https://github.com/Rose-STL-Lab/AutoSTPP.

Deep Learning/Sequential Models, Time series

Berken Utku Demirel, Christian Holz

The success of contrastive learning is well known to be dependent on data augmentation.Although the degree of data augmentations has been well controlled by utilizing pre-defined techniques in some domains like vision, time-series data augmentation is less explored and remains a challenging problem due to the complexity of the data generation mechanism, such as the intricate mechanism involved in the cardiovascular system.Moreover, there is no widely recognized and general time-series augmentation method that can be applied across different tasks.In this paper, we propose a novel data augmentation method for time-series tasks that aims to connect intra-class samples together, and thereby find order in the latent space.Our method builds upon the well-known data augmentation technique of mixup by incorporating a novel approach that accounts for the non-stationary nature of time-series data.Also, by controlling the degree of chaos created by data augmentation, our method leads to improved feature representations and performance on downstream tasks.We evaluate our proposed method on three time-series tasks, including heart rate estimation, human activity recognition, and cardiovascular disease detection. Extensive experiments against the state-of-the-art methods show that the proposed method outperforms prior works on optimal data generation and known data augmentation techniques in three tasks, reflecting the effectiveness of the presented method. The source code is available at double-blind policy.

Long Zhuo, Guangcong Wang, Shikai Li, Wayne Wu, Ziwei Liu

Video-to-Video synthesis (Vid2Vid) has achieved remarkable results on generating a photo-realistic video from a sequence of semantic maps. However, this pipeline suffers from high computational cost and long inference latency, which largely depends on two essential factors: 1) network architecture parameters, 2) sequential data stream. Recently, the parameters of image-based generative models have been significantly compressed via more efficient network architectures. Nevertheless, existing methods mainly focus on slimming network architectures and ignore the size of sequential data stream. Moreover, due to the lack of temporal coherence, image-based compression is not sufficient for the compression of video synthesis with a dynamic time series. In this paper, we present a spatial-temporal compression framework, Fast-Vid2Vid, which focuses on data aspects of generative models. It makes the first attempt at time dimension to reduce computational resources and accelerate inference. Specifically, we compress the input data stream spatially and reduce the temporal redundancy. After the proposed spatial-knowledge distillation, our model can synthesize key-frames using low-resolution data stream. Finally, Fast-Vid2Vid interpolates inter frames by motion compensation with negligible latency. On standard benchmarks, Fast-Vid2Vid achieves around real-time performance as 20 FPS and saves around 8× computational cost on a single V100 GPU.

Jianping Wu, Liang Zhang, Ye Liu, Ke Chen

We propose a novel approach that integrates under-parameterized RANSAC (UPRANSAC) with Hough Transform to detect vanishing points (VPs) from un-calibrated monocular images. In our algorithm, the UPRANSAC chooses one hypothetical inlier in a sample set to find a portion of the VP's degrees of freedom, which is followed by a highly reliable brute-force voting scheme (1-D Hough Transform) to find the VP's remaining degrees of freedom along the extension line of the hypothetical inlier. Our approach is able to sequentially find a series of VPs by repeatedly removing inliers of any detected VPs from minimal sample sets until the stop criterion is reached. Compared to traditional RANSAC that selects 2 edges as a hypothetical inlier pair to fit a model of VP hypothesis and requires hitting a pair of inliners, the UPRANSAC has a higher likelihood to hit one inliner and is more reliable in VP detection. Meanwhile, the tremendously scaled-down voting space with the requirement of only 1 parameter for processing significantly increased the performance efficiency of Hough Transform in our scheme. Testing results with well-known benchmark datasets show that the detection accuracies of our approach were higher or on par with the SOTA while running in deeply real-time zone.

Hang Xu, Ning Kang, Gengwei Zhang, Chuanlong Xie, Xiaodan Liang, Zhenguo Li

Fine-tuning from pre-trained ImageNet models has been a simple, effective, and popular approach for various computer vision tasks. The common practice of fine-tuning is to adopt a default hyperparameter setting with a fixed pre-trained model, while both of them are not optimized for specific tasks and time constraints. Moreover, in cloud computing or GPU clusters where the tasks arrive sequentially in a stream, faster online fine-tuning is a more desired and realistic strategy for saving money, energy consumption, and CO2 emission. In this paper, we propose a joint Neural Architecture Search and Online Adaption framework named NASOA towards a faster task-oriented fine-tuning upon the request of users. Specifically, NASOA first adopts an offline NAS to identify a group of training-efficient networks to form a pretrained model zoo. We propose a novel joint block and macro level search space to enable a flexible and efficient search. Then, by estimating fine-tuning performance via an adaptive model by accumulating experience from the past tasks, an online schedule generator is proposed to pick up the most suitable model and generate a personalized training regime with respect to each desired task in a one-shot fashion. The resulting model zoo is more training efficient than SOTA NAS models, e.g. 6x faster than RegNetY-16GF, and 1.7x faster than EfficientNetB3. Experiments on multiple datasets also show that NASOA achieves much better fine-tuning results, i.e. improving around 2.1% accuracy than the best performance in RegNet series under various time constraints and tasks; 40x faster compared to the BOHB method.

Wei Han, Zhengdong Zhang, Benjamin Caine, Brandon Yang, Christoph Sprunk, Ouais Alsharif, Jiquan Ngiam, Vijay Vasudevan, Jonathon Shlens, Zhifeng Chen

Autonomous vehicles operate in a dynamic environment, where the speed with which a vehicle can perceive and react impacts the safety and efficacy of the system. LiDAR provides a central and prominent sensory modality that informs many existing perceptual systems including object detection, segmentation, motion estimation and action recognition. The latency for perceptual system based on point cloud data can be dominated by the amount of time for a complete rotational scan (e.g. 100 ms). This built-in data capture latency is artificial, and based on treating the point cloud as a camera image in order to leverage camera-inspired architectures. However, unlike CCD camera sensors, most LiDAR point cloud data is natively a {\it streaming} data source in which laser reflections are sequentially recorded based on the rotational angle of the laser beam. In this work, we explore how to build an object detector that removes this artificial latency constraint, and instead operates on native streaming data in order to significantly reduce latency. This approach has the added benefit of reducing the peak computational burden on inference hardware by spreading the computation over the complete scan sequence. We demonstrate a family of streaming detection systems based on sequential modeling through a series of modifications to the traditional object detection meta-architecture. We highlight how this model may achieve competitive if not superior predictive performance with state-of-the-art, traditional non-streaming detection systems while achieving significant latency gains (e.g. 1/15'th - 1/3'rd of peak latency). Our results show that operating on LiDAR data in its native streaming formulation offers several advantages for self driving object detection -- advantages that we hope will be useful for any LiDAR perception system where minimizing latency is critical for safe and efficient operation.