We study the problem of estimating at a central server the mean of a set of vectors distributed across several nodes (one vector per node). When the vectors are high-dimensional, the communication cost of sending entire vectors may be prohibitive, and it may be imperative for them to use sparsification techniques. While most existing work on sparsified mean estimation is agnostic to the characteristics of the data vectors, in many practical applications such as federated learning, there may be spatial correlations (similarities in the vectors sent by different nodes) or temporal correlations (similarities in the data sent by a single node over different iterations of the algorithm) in the data vectors. We leverage these correlations by simply modifying the decoding method used by the server to estimate the mean. We provide an analysis of the resulting estimation error as well as experiments for PCA, K-Means and Logistic Regression, which show that our estimators consistently outperform more sophisticated and expensive sparsification methods.
Temporal data are naturally everywhere, especially in the digital era that sees the advent of big data and internet of things. One major challenge that arises during temporal data analysis and mining is the comparison of time series or sequences, which requires to determine a proper distance or (dis)similarity measure. In this context, the Dynamic Time Warping (DTW) has enjoyed success in many domains, due to its 'temporal elasticity', a property particularly useful when matching temporal data. Unfortunately this dissimilarity measure suffers from a quadratic computational cost, which prohibit…
The facility location problem is widely used for summarizing large datasets and has additional applications in sensor placement, image retrieval, and clustering. One difficulty of this problem is that submodular optimization algorithms require the calculation of pairwise benefits for all items in the dataset. This is infeasible for large problems, so recent work proposed to only calculate nearest neighbor benefits. One limitation is that several strong assumptions were invoked to obtain provable approximation guarantees. In this paper we establish that these extra assumptions are not necessary…
IRSTEA（法国国家环境与农业科学研究院）；University of Montpellier（蒙彼利埃大学）；LIRMM（蒙彼利埃计算机信息与机器人实验室）；CIRAD（法国农业发展研究中心）；CSE（塞内加尔高级研究中心）；University Cheikh Anta Diop（谢赫·安达·迪奥普大学）
European satellite missions Sentinel-1 (S1) and Sentinel-2 (S2) provide at highspatial resolution and high revisit time, respectively, radar and optical imagesthat support a wide range of Earth surface monitoring tasks such as LandUse/Land Cover mapping. A long-standing challenge in the remote sensingcommunity is about how to efficiently exploit multiple sources of information and leverage their complementary. In this particular case, get the most out ofradar and optical satellite image time series (SITS). Here, we propose to dealwith land cover mapping through a deep learning framework especi…
The inclusion of temporal scopes of facts in knowledge graph embedding (KGE) presents significant opportunities for improving the resulting embeddings, and consequently for increased performance in downstream applications. Yet, little research effort has focussed on this area and much of the carried out research reports only marginally improved results compared to models trained without temporal scopes (static models). Furthermore, rather than leveraging existing work on static models, they introduce new models specific to temporal knowledge graphs. We propose a novel perspective that takes ad…
Technion, Israel Institute of Technology（以色列理工学院）；eBay Research（eBay研究院）；Ben-Gurion University of the Negev（内盖夫本-古里安大学）
Temporal graph neural networks (temporal GNNs) have been widely researched, reaching state-of-the-art results on multiple prediction tasks. A common approach employed by most previous works is to apply a layer that aggregates information from the historical neighbors of a node. Taking a different research direction, in this work, we propose tBDFS -- a novel temporal GNN architecture. tBDFS applies a layer that efficiently aggregates information from temporal paths to a given (target) node in the graph. For each given node, the aggregation is applied in two stages: (1) A single representation i…
Santa Clara University（圣克拉拉大学）；University of Utah（犹他大学）；University of Utah Health Plans（犹他大学健康计划）；Cairo University（开罗大学）
Objective: To design and assess a method to leverage individuals' temporal data for predicting their healthcare cost. To achieve this goal, we first used patients' temporal data in their fine-grain form as opposed to coarse-grain form. Second, we devised novel spike detection features to extract temporal patterns that improve the performance of cost prediction. Third, we evaluated the effectiveness of different types of temporal features based on cost information, visit information and medical information for the prediction task. Materials and methods: We used three years of medical and pharma…
Robust video scene classification models should capture the spatial (pixel-wise) and temporal (frame-wise) characteristics of a video effectively. Transformer models with self-attention which are designed to get contextualized representations for individual tokens given a sequence of tokens, are becoming increasingly popular in many computer vision tasks. However, the use of Transformer based models for video understanding is still relatively unexplored. Moreover, these models fail to exploit the strong temporal relationships between the neighboring video frames to get potent frame-level repre…
Tampere University（坦佩雷大学）；Aristotle University of Thessaloniki（塞萨洛尼基亚里士多德大学）；Aarhus University（奥胡斯大学）
Time series forecasting is a crucial component of many important applications, ranging from forecasting the stock markets to energy load prediction. The high-dimensionality, velocity and variety of the data collected in these applications pose significant and unique challenges that must be carefully addressed for each of them. In this work, a novel Temporal Logistic Neural Bag-of-Features approach, that can be used to tackle these challenges, is proposed. The proposed method can be effectively combined with deep neural networks, leading to powerful deep learning models for time series analysis…
Improving the forecast accuracy of wind power by leveraging multiple hierarchical structure
Lucas English School of Mathematics and Physics The University of Queensland St Lucia, QLD 4072, Australia（Lucas English 数学与物理学院 昆士兰大学 斯塔 Lucia 分校）；Mahdi Abolghasemi School of Mathematics and Physics The University of Queensland St Lucia, QLD 4072, Australia（Mahdi Abolghasemi 数学与物理学院 昆士兰大学 斯塔 Lucia 分校）
Temporal Decisions: Leveraging Temporal Correlation for Efficient Decisions in Early Exit Neural Networks
Infineon Technologies Dresden GmbH & Co. KG（英飞凌德累斯顿有限两合公司）；Technical University of Munich（慕尼黑工业大学）；Infineon Technologies AG（英飞凌股份公司）；Technical University of Dresden（德累斯顿工业大学）
Symantec Research Labs（赛门铁克研究实验室）；Boston University（波士顿大学）
Despite the fact that cyberattacks are constantly growing in complexity, the research community still lacks effective tools to easily monitor and understand them. In particular, there is a need for techniques that are able to not only track how prominently certain malicious actions, such as the exploitation of specific vulnerabilities, are exploited in the wild, but also (and more importantly) how these malicious actions factor in as attack steps in more complex cyberattacks. In this paper we present ATTACK2VEC, a system that uses temporal word embeddings to model how attack steps are exploite…
The objective of this study is to develop and test a novel structured deep-learning modeling framework for urban flood nowcasting by integrating physics-based and human-sensed features. We present a new computational modeling framework including an attention-based spatial-temporal graph convolution network (ASTGCN) model and different streams of data that are collected in real-time, preprocessed, and fed into the model to consider spatial and temporal information and dependencies that improve flood nowcasting. The novelty of the computational modeling framework is threefold; first, the model i…
Leveraging Duration Pseudo-Embeddings in Multilevel LSTM and GCN Hypermodels for Outcome-Oriented PPM
College of Computing and Mathematical Sciences（计算与数学学院）；Center for Cyber-Physical Systems（网络物理系统中心）；Khalifa University（卡利法大学）；Computer Science Department（计算机科学系）；University of Milan（米兰大学）
From Division to Decision: Leveraging Temporal Cell-Stage Segmentation for Embryo Transferability Prediction
Inria center at Rennes University, Paris-Saclay University, UVSQ, INRAE, BREED（里昂大学Inria研究中心、巴黎萨克雷大学、UVSQ、INRAE、BREED）；University of Rennes, IRISA（雷恩大学、IRISA）；The National Veterinary School of Alfort（阿尔福兽医学校）
该研究提出TransFACT框架，利用时间 lapse 视频中的早期发育阶段信息，通过结合帧级时间特征和阶段级表示，预测胚胎可转移性，优于现有方法。
Institute of Acoustics, Chinese Academy of Sciences（中国科学院声学研究所）；University of Chinese Academy of Sciences（中国科学院大学）
Previous research has looked into ways to improve speech emotion recognition (SER) by utilizing both acoustic and linguistic cues of speech. However, the potential association between state-of-the-art ASR models and the SER task has yet to be investigated. In this paper, we propose a novel channel and temporal-wise attention RNN (CTA-RNN) architecture based on the intermediate representations of pre-trained ASR models. Specifically, the embeddings of a large-scale pre-trained end-to-end ASR encoder contain both acoustic and linguistic information, as well as the ability to generalize to differ…
Leveraging Vulnerabilities in Temporal Graph Neural Networks via Strategic High-Impact Assaults
Bowling Green State University（博伊尔格林州立大学）；University of Houston-Clear Lake（休斯顿-克莱湖大学）；Grand Valley State University（格兰德山谷州立大学）；University of Maryland at Baltimore County（马里兰大学巴尔的摩县分校）
Temporal Sparse Autoencoders: Leveraging the Sequential Nature of Language for Interpretability
Harvard School of Engineering and Applied Science（哈佛工程与应用科学学院）；Kempner Institute for the Study of Natural & Artificial Intelligence（自然与人工智能研究学院）；Harvard Business School（哈佛商学院）
Patient time series classification faces challenges in high degrees of dimensionality and missingness. In light of patient similarity theory, this study explores effective temporal feature engineering and reduction, missing value imputation, and change point detection methods that can afford similarity-based classification models with desirable accuracy enhancement. We select a piecewise aggregation approximation method to extract fine-grain temporal features and propose a minimalist method to impute missing values in temporal features. For dimensionality reduction, we adopt a gradient descent…
Improving day-ahead Solar Irradiance Time Series Forecasting by Leveraging Spatio-Temporal Context
Mila - Québec AI Institute（米拉-魁北克人工智能研究所）；Université de Montréal（蒙特利尔大学）；Université du Québec à Rimouski（魁北克大学里穆斯基分校）；NASA Goddard Space Flight Center（美国国家航空航天局戈达德太空飞行中心）
University of New South Wales（新南威尔士大学）；University of Wollongong（伍伦贡大学）
In this paper, we propose a novel pipeline that leverages language foundation models for temporal sequential pattern mining, such as for human mobility forecasting tasks. For example, in the task of predicting Place-of-Interest (POI) customer flows, typically the number of visits is extracted from historical logs, and only the numerical data are used to predict visitor flows. In this research, we perform the forecasting task directly on the natural language input that includes all kinds of information such as numerical values and contextual semantic information. Specific prompts are introduced…
Multi-Window Temporal Analysis for Enhanced Arrhythmia Classification: Leveraging Long-Range Dependencies in Electrocardiogram Signals
AI4Health Department, Oldenburg University（奥尔登堡大学AI4Health部门）；Department of Cardiology, Angiology and Intensive Care Medicine, Charité Campus Mitte, German Heart Center of the Charité-University Medicine Berlin（查理医院梅特校区心内科、血管科和重症医学科，查理-柏林大学医学中心心脏中心）
Leveraging graph neural networks and mobility data for COVID-19 forecasting
Postgraduate Program in Computer Science, Federal University of Ouro Preto（奥鲁普托联邦大学计算机科学研究生院）；Department of Computing, Federal University of Ouro Preto（奥鲁普托联邦大学计算机系）；National Center for Monitoring and Early Warning of Natural Disasters（国家自然灾害监测与预警中心）
