合集下载地址:点我跳转下载合集。
包含时间序列预测、建模、对齐、分析、异常检测、对比学习、度量学习、分类、聚类等14个细分方向。
以下是详细目录。
1、时间序列预测
[1]FEDformer: Frequency Enhanced Decomposed Transformer for Long-term Series Forecasting
[代码]https://github.com/MAZiqing/FEDformer
[发表]ICML 2022
[领域]长时间序列预测
[2]TACTiS: Transformer-Attentional Copulas for Time Series
[代码]https://github.com/ServiceNow/tactis
[发表]ICML 2022
[领域]时间序列预测
[3]Domain Adaptation for Time Series Forecasting via Attention Sharing
[代码]https://github.com/leejoonhun/daf
[发表]ICML 2022
[领域]基于DA的时间序列预测
[4]Adaptive Conformal Predictions for Time Series
[代码]https://github.com/mzaffran/adaptiveconformalpredictionstimeseries
[发表]ICML 2022
[领域]电价时间序列预测
[5]OFA: Unifying Architectures, Tasks, and Modalities Through a Simple Sequence-to-Sequence Learning Framework
[代码]https://github.com/OFA-Sys/OFA
[发表]ICML 2022
[领域]基于Sequence-to-Sequence多模态预训练
[6]Reinforcement Learning based Dynamic Model Combination for Time Series Forecasting
[代码]hNone
[发表]AAAI 2022
[领域]基于强化学习的时间序列预测
[7]Reversible Instance Normalization for Accurate Time-Series Forecasting against Distribution Shift
[代码]https://github.com/ts-kim/RevIN
[发表]ICLR 2022
[领域]时间序列预测
[8]Filling the G_ap_s: Multivariate Time Series Imputation by Graph Neural Networks
[代码]https://github.com/Graph-Machine-Learning-Group/grin
[发表]ICLR 2022
[领域]时间序列预测
[9]Pyraformer: Low-Complexity Pyramidal Attention for Long-Range Time Series Modeling and Forecasting
[代码]https://github.com/alipay/Pyraformer
[发表]ICLR 2022
[领域]时间序列预测
[10]TAMP-S2GCNets: Coupling Time-Aware Multipersistence Knowledge Representation with Spatio-Supra Graph Convolutional Networks for Time-Series Forecasting
[代码]None
[发表]ICLR 2022
[领域]时间序列预测
[11]DEPTS: Deep Expansion Learning for Periodic Time Series Forecasting
[代码]https://github.com/weifantt/depts
[发表]ICLR 2022
[领域]时间序列预测
[12]PSA-GAN: Progressive Self Attention GANs for Synthetic Time Series
[代码]https://github.com/awslabs/gluon-ts
[发表]ICLR 2022
[领域]时间序列预测
[13]Back2Future: Leveraging Backfill Dynamics for Improving Real-time Predictions in Future
[代码]https://github.com/AdityaLab/Back2Future
[发表]ICLR 2022
[领域]时间序列预测/流行病预测
[14]CAMul: Calibrated and Accurate Multi-view Time-Series Forecasting
[代码]https://github.com/adityalab/camul
[发表]WWW 2022
[领域]时间序列预测
[15]PopNet: Real-Time Population-Level Disease Prediction with Data Latency
[代码]https://github.com/v1xerunt/popnet
[发表]WWW 2022
[领域]时间序列预测
[16]Multi-Granularity Residual Learning with Confidence Estimation for Time Series Prediction
[代码]h
[发表]WWW 2022
[领域]时间序列预测
[17]Allocating Stimulus Checks in Times of Crisis
[代码]https://github.com/papachristoumarios/financial-contagion
[发表]WWW 2022
[领域]时间序列预测
[18]Regularized Graph Structure Learning with Semantic Knowledge for Multi-variates Time-Series Forecasting
[代码]https://github.com/ant-research/RGSL
[发表]IJCAI 2022
[领域]时间序列预测
[1]Triformer: Triangular, Variable-Specific Attentions for Long Sequence Multivariate Time Series Forecasting
[代码]None
[发表]IJCAI 2022
[领域]多变量时间序列预测
[20]DeepExtrema: A Deep Learning Approach for Forecasting Block Maxima in Time Series Data
[代码]https://github.com/galib19/deepextrema-ijcai22-
[发表]IJCAI 2022
[领域]时间序列预测
2、时间序列建模
[1]Modeling Irregular Time Series with Continuous Recurrent Units
[代码]https://github.com/boschresearch/continuous-recurrent-units
[发表]ICML 2022
[领域]不规则采样的时间序列建模
[2]Transformer Neural Processes: Uncertainty-Aware Meta Learning Via Sequence Modeling
[代码]https://github.com/tung-nd/tnp-pytorch
[发表]ICML 2022
[领域]序列建模、神经过程、不确定性
[3]Accelerating Bayesian Optimization for Biological Sequence Design with Denoising Autoencoders
[代码]https://github.com/samuelstanton/lambo
[发表]ICML 2022
[领域]生物序列数据建模、贝叶斯优化
[4]Unsupervised Flow-Aligned Sequence-to-Sequence Learning for Video Restoration
[代码]https://github.com/linjing7/VR-Baseline
[发表]ICML 2022
[领域]Sequence-to-Sequence计算机视觉模型
[5]Learning Temporal Point Processes for Efficient Retrieval of Continuous Time Event Sequences
[代码]https://github.com/data-iitd/neuroseqret
[发表]AAAI 2022
[领域]点过程结合时间事件序列
3、时间序列对齐
[1]Closed-Form Diffeomorphic Transformations for Time Series Alignment
[代码]https://github.com/imartinezl/difw
[发表]ICML 2022
[领域]时间序列对齐
4、时间序列分析
[1]Reconstructing Nonlinear Dynamical Systems from Multi-Modal Time Series
[代码]https://github.com/durstewitzlab/mmplrnn
[发表]ICML 2022
[领域]多模态时间序列分析
[2]Learning of Cluster-based Feature Importance for Electronic Health Record Time-series
[代码]None
[发表]ICML 2022
[领域]电子健康记录(EHR)数据分析
[3]Proximal Exploration for Model-guided Protein Sequence Design
[代码]None
[发表]ICML 2022
[领域]蛋白质序列分析
[4]Biological Sequence Design with GFlowNets
[代码]https://github.com/mj10/bioseq-gfn-al
[发表]ICML 2022
[领域]生物序列分析
[5]SkexGen: Autoregressive Generation of CAD Construction Sequences with Disentangled Codebooks
[代码]https://github.com/samxuxiang/SkexGen
[发表]ICML 2022
[领域]计算机辅助设计(CAD)结构序列分析
[6]Graph-Guided Network for Irregularly Sampled Multivariate Time Series
[代码]https://github.com/mims-harvard/raindrop
[发表]ICLR 2022
[领域]不规则采用的多元时间序列分析方法
[7]Huber Additive Models for Non-stationary Time Series Analysis
[代码]https://github.com/xianruizhong/SpHAM
[发表]ICLR 2022
[领域]非平稳时间序列分析
[8]Coherence-based Label Propagation over Time Series for Accelerated Active Learning
[代码]None
[发表]ICLR 2022
[领域]缺乏标注的时间序列分析
[9]Heteroscedastic Temporal Variational Autoencoder For Irregularly Sampled Time Series
[代码]https://github.com/reml-lab/hetvae
[发表]ICLR 2022
[领域]不规则采样的时间序列分析方法
5、无监督/自监督时间序列
[1]Unsupervised Time-Series Representation Learning with Iterative Bilinear Temporal-Spectral Fusion
[代码]None
[发表]ICML 2022
[领域]无监督/自监督时间序列
[1]Style Equalization: Unsupervised Learning of Controllable Generative Sequence Models
[代码]https://apple.github.io/ml-style-equalization/
[发表]ICML 2022
[领域]可控序列生成、无监督
6、时间序列异常检测
[1]Deep Variational Graph Convolutional Recurrent Network for Multivariate Time Series Anomaly Detection
[代码]None
[发表]ICML 2022
[领域]多变量时间序列异常检测
[2]Towards a Rigorous Evaluation of Time-series Anomaly Detection
[代码]https://github.com/tuslkkk/tadpak
[发表]AAAI 2022
[领域]时间序列异常检测综述
[3]Graph-Augmented Normalizing Flows for Anomaly Detection of Multiple Time Series
[代码]https://github.com/enyandai/ganf
[发表]ICLR 2022
[领域]时间序列异常检测
[4]Anomaly Transformer: Time Series Anomaly Detection with Association Discrepancy
[代码]https://github.com/thuml/Anomaly-Transformer
[发表]ICLR 2022
[领域]时间序列异常检测
[5]A Semi-Supervised VAE Based Active Anomaly Detection Framework in Multivariate Time Series for Online Systems
[代码]None
[发表]WWW 2022
[领域]时间序列异常检测
[6]GRELEN: Multivariate Time Series Anomaly Detection from the Perspective of Graph Relational Learning
[代码]None
[发表]IJCAI 2022
[领域]时间序列异常检测
[7]Neural Contextual Anomaly Detection for Time Series
[代码]https://github.com/Francois-Aubet/gluon-ts
[发表]IJCAI 2022
[领域]时间序列异常检测
7、时间序列对比学习
[1]Utilizing Expert Features for Contrastive Learning of Time-Series Representations
[代码]https://github.com/boschresearch/expclr
[发表]ICML 2022
[领域]时间序列对比学习
8、时间序列因果分析
[1]CITRIS: Causal Identifiability from Temporal Intervened Sequences
[代码]https://github.com/phlippe/citris
[发表]ICML 2022
[领域]时间序列因果分析
[2]Causal Conceptions of Fairness and their Consequences
[代码]None
[发表]ICML 2022
[领域]因果关系、公平决策算法
9、时间序列度量学习
[1]I-SEA: Importance Sampling and Expected Alignment-based Deep Distance Metric Learning for Time Series Analysis and Embedding
[代码]https://github.com/srambhatla/ISEA
[发表]AAAI 2022
[领域]时间序列度量学习
10、时间序列生成
[1]Conditional Loss and Deep Euler Scheme for Time Series Generation
[代码]None
[发表]AAAI 2022
[领域]时间序列生成
11、时间序列聚类
[1]Clustering Interval-Censored Time-Series for Disease Phenotyping
[代码]None
[发表]AAAI 2022
[领域]时间序列聚类
12、时间序列分类
[1]Training Robust Deep Models for Time-Series Domain: Novel Algorithms and Theoretical Analysis
[代码]https://github.com/tahabelkhouja/robust-training-for-time-series
[发表]AAAI 2022
[领域]时间序列训练
[2]T-WaveNet: A Tree-Structured Wavelet Neural Network for Time Series Signal Analysis
[代码]None
[发表]ICLR 2022
[领域]时间序列分类
[3]Omni-Scale CNNs: a simple and effective kernel size configuration for time series classification
[代码]https://github.com/Wensi-Tang/OS-CNN
[发表]ICLR 2022
[领域]时间序列分类
[4]EXIT: Extrapolation and Interpolation-based Neural Controlled Differential Equations for Time-series Classification and Forecasting
[代码]None
[发表]WWW 2022
[领域]时间序列分类
[5]A Reinforcement Learning-Informed Pattern Mining Framework for Multivariate Time Series Classification
[代码]None
[发表]IJCAI 2022
[领域]时间序列分类
13、时间序列表示学习
[1]TS2Vec: Towards Universal Representation of Time Series
[代码]https://github.com/yuezhihan/ts2vec
[发表]AAAI 2022
[领域]时间序列表示学习
[2]CoST: Contrastive Learning of Disentangled Seasonal-Trend Representations for Time Series Forecasting
[代码]https://github.com/salesforce/CoST
[发表]ICLR 2022
[领域]时间序列表示学习
14、序列与推荐
[1]Towards Automatic Discovering of Deep Hybrid Network Architecture for Sequential Recommendation
[代码]https://github.com/Mingyue-Cheng/NASR
[发表]WWW 2022
[领域]序列与推荐
[2]Sequential Recommendation with Decomposed Item Feature Routing
[代码]None
[发表]WWW 2022
[领域]序列与推荐
[3]Sequential Recommendation via Stochastic Self-Attention
[代码]https://github.com/zfan20/stosa
[发表]WWW 2022
[领域]序列与推荐
[4]Learn over Past, Evolve for Future: Search-based Time-aware Recommendation with Sequential Behavior Data
[代码]https://github.com/zfan20/STOSA
[发表]WWW 2022
[领域]序列与推荐
[5]Intent Contrastive Learning for Sequential Recommendation
[代码]https://github.com/salesforce/iclrec
[发表]WWW 2022
[领域]序列与推荐
[6]Filter-enhanced MLP is All You Need for Sequential Recommendation
[代码]https://github.com/RUCAIBox/FMLP-Rec
[发表]WWW 2022
[领域]序列与推荐
[7]Efficient Online Learning to Rank for Sequential Music Recommendation
[代码]None
[发表]WWW 2022
[领域]序列与推荐