Spectral Propagation Graph Network for Few-shot Time Series Classification
Institute of Medical Technology, Health Science Center of Peking University（北京大学医学部医学技术研究院）；National Institute of Health Data Science, Peking University（北京大学国家健康医疗大数据研究院）
Few-shot Time Series Classification (few-shot TSC) is a challenging problem in time series analysis. It is more difficult to classify when time series of the same class are not completely consistent in spectral domain or time series of different classes are partly consistent in spectral domain. To address this problem, we propose a novel method named Spectral Propagation Graph Network (SPGN) to explicitly model and propagate the spectrum-wise relations between different time series with graph network. To the best of our knowledge, SPGN is the first to utilize spectral comparisons in different intervals and involve spectral propagation across all time series with graph networks for few-shot TSC. SPGN first uses bandpass filter to expand time series in spectral domain for calculating spectrum-wise relations between time series. Equipped with graph networks, SPGN then integrates spectral relations with label information to make spectral propagation. The further study conveys the bi-directional effect between spectral relations acquisition and spectral propagation. We conduct extensive experiments on few-shot TSC benchmarks. SPGN outperforms state-of-the-art results by a large margin in $4\% \sim 13\%$. Moreover, SPGN surpasses them by around $12\%$ and $9\%$ under cross-domain and cross-way settings respectively.
University at Buffalo（布法罗大学）；Microsoft Research（微软研究院）
Few-shot learning features the capability of generalizing from a few examples. In this paper, we first identify that a discriminative feature space, namely a rectified metric space, that is learned to maintain the metric consistency from training to testing, is an essential component to the success of metric-based few-shot learning. Numerous analyses indicate that a simple modification of the objective can yield substantial performance gains. The resulting approach, called rectified metric propagation (ReMP), further optimizes an attentive prototype propagation network, and applies a repulsive…
Element AI；University of British Columbia（不列颠哥伦比亚大学）
Few-shot classification is challenging because the data distribution of the training set can be widely different to the test set as their classes are disjoint. This distribution shift often results in poor generalization. Manifold smoothing has been shown to address the distribution shift problem by extending the decision boundaries and reducing the noise of the class representations. Moreover, manifold smoothness is a key factor for semi-supervised learning and transductive learning algorithms. In this work, we propose to use embedding propagation as an unsupervised non-parametric regularizer…
Rethinking Zero-Shot Time Series Classification: From Task-specific Classifiers to In-Context Inference
Guangdong University of Technology, Guangzhou, China（广东工业大学）；Paris Descartes University, Paris, France（巴黎笛卡尔大学）；Mohamed bin Zayed University of Artificial Intelligence, Abu Dhabi, United Arab Emirates（马尔代夫 bin Zayed 人工智能大学）；Huawei Noah’s Ark Lab, Paris, France（华为诺亚实验室）；Huawei Noah’s Ark Lab, Shenzhen, China（华为诺亚实验室）
Univariate to Multivariate: LLMs as Zero-Shot Predictors for Time-Series Forecasting
School of Computing Technologies RMIT University, Australia（计算机技术学院皇家墨尔本理工大学，澳大利亚）；School of Information Technologies Deakin University, Australia（信息科技学院德肯大学，澳大利亚）
École Centrale de Nantes（南特中央理工学院）；Université de Nantes（南特大学）
We present an accurate, fast and efficient method for segmentation and muscle mask propagation in 3D freehand ultrasound data, towards accurate volume quantification. A deep Siamese 3D Encoder-Decoder network that captures the evolution of the muscle appearance and shape for contiguous slices is deployed. We uses it to propagate a reference mask annotated by a clinical expert. To handle longer changes of the muscle shape over the entire volume and to provide an accurate propagation, we devise a Bidirectional Long Short Term Memory module. Also, to train our model with a minimal amount of train…
University of Oxford（牛津大学）；Mind Foundry Ltd.（思维铸造有限公司）
Recurrent neural networks (RNNs) are state-of-the-art in several sequential learning tasks, but they often require considerable amounts of data to generalise well. For many time series forecasting (TSF) tasks, only a few dozens of observations may be available at training time, which restricts use of this class of models. We propose a novel RNN-based model that directly addresses this problem by learning a shared feature embedding over the space of many quantised time series. We show how this enables our RNN framework to accurately and reliably forecast unseen time series, even when there is l…
MetaCaster: Meta-Harness-Optimized Agent for End-to-End Few-Shot Learning of Lightweight Time Series Forecasters
University of Houston（休斯顿大学）；NEC Labs（NEC实验室）；University of Waterloo（滑铁卢大学）；University of Connecticut（康涅狄格大学）；University of Illinois at Urbana-Champaign（伊利诺伊大学厄巴纳-香槟分校）；Singapore Management University（新加坡管理大学）
FAF: A Feature-Adaptive Framework for Few-Shot Time Series Forecasting
The School of Computer and Artificial Intelligence of Zhengzhou University（郑州大学计算机与人工智能学院）；Engineering Research Center of Intelligent Swarm Systems, Ministry of Education（智能群体系统工程研究中心）；National Supercomputing Center In Zhengzhou（郑州国家超级计算中心）；New quality Software Engineering Research Center（高质量软件工程研究中心）
Learning complex time series forecasting models usually requires a large amount of data, as each model is trained from scratch for each task/data set. Leveraging learning experience with similar datasets is a well-established technique for classification problems called few-shot classification. However, existing approaches cannot be applied to time-series forecasting because i) multivariate time-series datasets have different channels and ii) forecasting is principally different from classification. In this paper we formalize the problem of few-shot forecasting of time-series with heterogeneou…
Arizona State University（亚利桑那州立大学）；Texas A&M University（得克萨斯农工大学）
Inspired by the extensive success of deep learning, graph neural networks (GNNs) have been proposed to learn expressive node representations and demonstrated promising performance in various graph learning tasks. However, existing endeavors predominately focus on the conventional semi-supervised setting where relatively abundant gold-labeled nodes are provided. While it is often impractical due to the fact that data labeling is unbearably laborious and requires intensive domain knowledge, especially when considering the heterogeneity of graph-structured data. Under the few-shot semi-supervised…
TS-RAG: Retrieval-Augmented Generation based Time Series Foundation Models are Stronger Zero-Shot Forecaster
School of Computing, University of Connecticut（康奈尔大学计算机学院）；Department of Machine Learning Research, Morgan Stanley（摩根士丹利机器学习研究部）；Ant Group（蚂蚁集团）；TWG Global（TWG全球）
ROAR: Retrieval Opportunity-Aware Refinement for Zero-Shot Time Series Forecasting
College of Computer Science and Technology, Jilin University（吉林大学计算机科学与技术学院）；College of Computing and Data Science, Nanyang Technological University（南洋理工大学计算机与数据科学学院）；City St George’s, University of London（伦敦大学城圣乔治学院）；Systems Research Institute, Polish Academy of Sciences（波兰科学院系统研究所）
University of Technology Sydney（悉尼科技大学）；University of Washington（华盛顿大学）
The goal of zero-shot learning (ZSL) is to train a model to classify samples of classes that were not seen during training. To address this challenging task, most ZSL methods relate unseen test classes to seen(training) classes via a pre-defined set of attributes that can describe all classes in the same semantic space, so the knowledge learned on the training classes can be adapted to unseen classes. In this paper, we aim to optimize the attribute space for ZSL by training a propagation mechanism to refine the semantic attributes of each class based on its neighbors and related classes on a g…
Towards Foundation Models for Zero-Shot Time Series Anomaly Detection: Leveraging Synthetic Data and Relative Context Discrepancy
Department of Industrial Engineering, Tsinghua University, Beijing, China（清华大学工业工程系）；Datadog AI Research, Paris, France. This work was completed prior to joining Datadog（Datadog AI 研究院）；Lab, Huawei Technologies, ShenZhen, China（华为技术2012实验室）
Various things propagate through the medium of individuals. Some individuals follow the others and take the states similar to their states a small number of time steps later. In this paper, we study the problem of estimating the state propagation order of individuals from the real-valued state sequences of all the individuals. We propose a method to estimate the propagation direction between individuals by the sum of the time delay of one individual's state positions from the other individual's matched state position averaged over the minimum cost alignments and show how to calculate it effici…
Recent few-shot learning works focus on training a model with prior meta-knowledge to fast adapt to new tasks with unseen classes and samples. However, conventional time-series classification algorithms fail to tackle the few-shot scenario. Existing few-shot learning methods are proposed to tackle image or text data, and most of them are neural-based models that lack interpretability. This paper proposes an interpretable neural-based framework, namely \textit{Dual Prototypical Shapelet Networks (DPSN)} for few-shot time-series classification, which not only trains a neural network-based model …
NTT Communication Science Laboratories（NTT通信科学实验室）；NTT Software Innovation Center（NTT软件创新中心）
Time-series forecasting is important for many applications. Forecasting models are usually trained using time-series data in a specific target task. However, sufficient data in the target task might be unavailable, which leads to performance degradation. In this paper, we propose a few-shot learning method that forecasts a future value of a time-series in a target task given a few time-series in the target task. Our model is trained using time-series data in multiple training tasks that are different from target tasks. Our model uses a few time-series to build a forecasting function based on a…
Instance Relation Learning Network with Label Knowledge Propagation for Few-shot Multi-label Intent Detection
Key Lab of High Confidence Software Technologies (MOE), School of Computer Science, Peking University, Beijing, China（高可信软件技术重点实验室（教育部）、计算机科学学院、北京大学，北京，中国）；Research Center for Computational Social Science, Peking University, Beijing, China（计算社会科学研究中心、北京大学，北京，中国）；Institute of Computational Social Science, Peking University, Qingdao, China（计算社会科学研究院、北京大学，青岛，中国）；Department of Systems Engineering and Engineering Management, The Chinese University of Hong Kong, Hong Kong, China（系统工程与工程管理系、香港中文大学，香港，中国）
Humans are good at compositional zero-shot reasoning; someone who has never seen a zebra before could nevertheless recognize one when we tell them it looks like a horse with black and white stripes. Machine learning systems, on the other hand, usually leverage spurious correlations in the training data, and while such correlations can help recognize objects in context, they hurt generalization. To be able to deal with underspecified datasets while still leveraging contextual clues during classification, we propose ProtoProp, a novel prototype propagation graph method. First we learn prototypic…
Learning-based methods for visual segmentation have made progress on particular types of segmentation tasks, but are limited by the necessary supervision, the narrow definitions of fixed tasks, and the lack of control during inference for correcting errors. To remedy the rigidity and annotation burden of standard approaches, we address the problem of few-shot segmentation: given few image and few pixel supervision, segment any images accordingly. We propose guided networks, which extract a latent task representation from any amount of supervision, and optimize our architecture end-to-end for f…
Prediction and Causality of functional MRI and synthetic signal using a Zero-Shot Time-Series Foundation Model
AGH University of Krakow, Poland（克拉科夫AGH大学）；Institut de Neurosciences de la Timone UMR 7289, Aix Marseille Université, CNRS, 13005, Marseille, France（里莫内神经科学研究所）
Structured information extraction from document images usually consists of three steps: text detection, text recognition, and text field labeling. While text detection and text recognition have been heavily studied and improved a lot in literature, text field labeling is less explored and still faces many challenges. Existing learning based methods for text labeling task usually require a large amount of labeled examples to train a specific model for each type of document. However, collecting large amounts of document images and labeling them is difficult and sometimes impossible due to privac…
CAI, University of Technology Sydney（悉尼科技大学CAI）；University of Oxford（牛津大学）；AITRICS；KAIST（韩国科学技术院）；Baidu Research（百度研究院）
The goal of few-shot learning is to learn a classifier that generalizes well even when trained with a limited number of training instances per class. The recently introduced meta-learning approaches tackle this problem by learning a generic classifier across a large number of multiclass classification tasks and generalizing the model to a new task. Yet, even with such meta-learning, the low-data problem in the novel classification task still remains. In this paper, we propose Transductive Propagation Network (TPN), a novel meta-learning framework for transductive inference that classifies the …
