Time series classification has ubiquitous applications in the real world. Owing to its importance, many time series classification techniques have been proposed over years. Among them, neural network based methods have attracted significant research attention due to their ability to automatically extract latent and discriminative features from data. In this paper, we explorerelationship features, which provide valuable global information for time series analytics, and propose a general neural network architecture, namelyRel-CNN, to learn both global and local subsequence features for time series classification. Moreover, we provide two detailed model designs,Relationship Feature based Convolution FilteringandLatent Relationship Feature based Convolution Filtering, and address technical issues due to excessive parameters to learn in these models. We evaluate our models and baselines on time series classification, with extensive experiments on the widely-used 85 uni-variate “bake-off” datasets and 8 multi-variate UEA datasets. Experimental results show that our Rel-CNN models are superior to the representative time series classifiers, in terms of average accuracy, average Macro-f1 and ranking metrics. In addition, an ensemble version of Rel-CNN also outperforms the state-of-the-art ensemble classifiers in terms of average rank, average accuracy and average Macro-f1 on the bake-off datasets.

Citations of scientific papers and patents reveal the knowledge flow and usually serve as the metric for evaluating their novelty and impacts in the field. Citation Forecasting thus has various applications in the real world. Existing works on citation forecasting typically exploit the sequential properties of citation events, without exploring the citation network. In this paper, we propose to explore both the citation network and the related citation event sequences which provide valuable information for future citation forecasting. We propose a novel \em Citation Network and Event Sequence (CINES) Model to encode signals in the citation network and related citation event sequences into various types of embeddings for decoding to the arrivals of future citations. Moreover, we propose atemporal network attention and three alternative designs of \em bidirectional feature propagation to aggregate the retrospective and prospective aspects of publications in the citation network, coupled with the citation event sequence embeddings learned by a \em two-level attention mechanism for the citation forecasting. We evaluate our models and baselines on both a U.S. patent dataset and a DBLP dataset. Experimental results show that our models outperform the state-of-the-art methods, i.e., RMTPP, CYAN-RNN, Intensity-RNN, and PC-RNN, reducing the forecasting error by 37.76% - 75.32%.