Extracting event time from news articles is a challenging but attractive task. In contrast to the most existing pair-wised temporal link annotation, Reimers et al.(2016) proposed to annotate the time anchor (a.k.a. the exact time) of each event. Their work represents time anchors with discrete representations of Single-Day/Multi-Day and Certain/Uncertain. This increases the complexity of modeling the temporal relations between two time anchors, which cannot be categorized into the relations of Allen's interval algebra (Allen, 1990). In this paper, we propose an effective method to decompose such complex temporal relations into sub-level relations by introducing a unified quadruple representation for both Single-Day/Multi-Day and Certain/Uncertain time anchors. The temporal relation classifiers are trained in a multi-label classification manner. The system structure of our approach is much simpler than the existing decision tree model (Reimers et al., 2018), which is composed by a dozen of node classifiers. Another contribution of this work is to construct a larger event time corpus (256 news documents) with a reasonable Inter-Annotator Agreement (IAA), for the purpose of overcoming the data shortage of the existing event time corpus (36 news documents). The empirical results show our approach outperforms the state-of-the-art decision tree model and the increase of data size obtained a significant improvement of performance.
We propose a new learning algorithm for propagating a learning signal and updating neural network parameters via a forward pass, as an alternative to backpropagation. In forward signal propagation learning (sigprop), there is only the forward path for learning and inference, so there are no additional structural or computational constraints on learning, such as feedback connectivity, weight transport, or a backward pass, which exist under backpropagation. Sigprop enables global supervised learning with only a forward path. This is ideal for parallel training of layers or modules. In biology, this explains how neurons without feedback connections can still receive a global learning signal. In hardware, this provides an approach for global supervised learning without backward connectivity. Sigprop by design has better compatibility with models of learning in the brain and in hardware than backpropagation and alternative approaches to relaxing learning constraints. We also demonstrate that sigprop is more efficient in time and memory than they are. To further explain the behavior of sigprop, we provide evidence that sigprop provides useful learning signals in context to backpropagation. To further support relevance to biological and hardware learning, we use sigprop to train continuous time neural networks with Hebbian updates and train spiking neural networks without surrogate functions.
An electrocardiogram (ECG) monitors the electrical activity generated by the heart and is used to detect fatal cardiovascular diseases (CVDs). Conventionally, to capture the precise electrical activity, clinical experts use multiple-lead ECGs (typically 12 leads). But in recent times, large-size deep learning models have been used to detect these diseases. However, such models require heavy compute resources like huge memory and long inference time. To alleviate these shortcomings, we propose a low-parameter model, named Low Resource Heart-Network (LRH-Net), which uses fewer leads to detect ECG anomalies in a resource-constrained environment. A multi-level knowledge distillation process is used on top of that to get better generalization performance on our proposed model. The multi-level knowledge distillation process distills the knowledge to LRH-Net trained on a reduced number of leads from higher parameter (teacher) models trained on multiple leads to reduce the performance gap. The proposed model is evaluated on the PhysioNet-2020 challenge dataset with constrained input. The parameters of the LRH-Net are 106x less than our teacher model for detecting CVDs. The performance of the LRH-Net was scaled up to 3.2% and the inference time scaled down by 75% compared to the teacher model. In contrast to the compute- and parameter-intensive deep learning techniques, the proposed methodology uses a subset of ECG leads using the low resource LRH-Net, making it eminently suitable for deployment on edge devices.
The rising popularity of online social network services has attracted lots of research on mining social media data, especially on mining social events. Social event detection, due to its wide applications, has now become a trivial task. State-of-the-art approaches exploiting Graph Neural Networks (GNNs) usually follow a two-step strategy: 1) constructing text graphs based on various views (\textit{co-user}, \textit{co-entities} and \textit{co-hashtags}); and 2) learning a unified text representation by a specific GNN model. Generally, the results heavily rely on the quality of the constructed graphs and the specific message passing scheme. However, existing methods have deficiencies in both aspects: 1) They fail to recognize the noisy information induced by unreliable views. 2) Temporal information which works as a vital indicator of events is neglected in most works. To this end, we propose ETGNN, a novel Evidential Temporal-aware Graph Neural Network. Specifically, we construct view-specific graphs whose nodes are the texts and edges are determined by several types of shared elements respectively. To incorporate temporal information into the message passing scheme, we introduce a novel temporal-aware aggregator which assigns weights to neighbours according to an adaptive time exponential decay formula. Considering the view-specific uncertainty, the representations of all views are converted into mass functions through evidential deep learning (EDL) neural networks, and further combined via Dempster-Shafer theory (DST) to make the final detection. Experimental results on three real-world datasets demonstrate the effectiveness of ETGNN in accuracy, reliability and robustness in social event detection.
Frequency-hopping (FH) joint radar-communications (JRC) can offer excellent security for integrated sensing and communication systems. However, existing JRC schemes mainly embed information using only the sub-pulse frequencies and hence the data rate is limited. In this paper, we propose to use both sub-pulse frequencies and durations for information modulation, leading to higher communication data rates. For information demodulation, we propose a novel scheme by using the time-frequency analysis (TFA) technique and a "you only look once" (YOLO)-based detection system. As such, our system does not require channel estimation, simplifying the transmission signal frame design. Simulation results demonstrate the effectiveness of our scheme, and show that it is robust against the Doppler shift and timing offset between the transceiver and the communication receiver.
In a clinical setting it is essential that deployed image processing systems are robust to the full range of inputs they might encounter and, in particular, do not make confidently wrong predictions. The most popular approach to safe processing is to train networks that can provide a measure of their uncertainty, but these tend to fail for inputs that are far outside the training data distribution. Recently, generative modelling approaches have been proposed as an alternative; these can quantify the likelihood of a data sample explicitly, filtering out any out-of-distribution (OOD) samples before further processing is performed. In this work, we focus on image segmentation and evaluate several approaches to network uncertainty in the far-OOD and near-OOD cases for the task of segmenting haemorrhages in head CTs. We find all of these approaches are unsuitable for safe segmentation as they provide confidently wrong predictions when operating OOD. We propose performing full 3D OOD detection using a VQ-GAN to provide a compressed latent representation of the image and a transformer to estimate the data likelihood. Our approach successfully identifies images in both the far- and near-OOD cases. We find a strong relationship between image likelihood and the quality of a model's segmentation, making this approach viable for filtering images unsuitable for segmentation. To our knowledge, this is the first time transformers have been applied to perform OOD detection on 3D image data.
Here, we propose a new reconstruction method of smooth time-series signals. A key concept of this study is not considering the model in signal space, but in delay-embedded space. In other words, we indirectly represent a time-series signal as an output of inverse delay-embedding of a matrix, and the matrix is constrained. Based on the model under inverse delay-embedding, we propose to constrain the matrix to be rank-1 with smooth factor vectors. The proposed model is closely related to the convolutional model, and quadratic variation (QV) regularization. Especially, the proposed method can be characterized as a generalization of QV regularization. In addition, we show that the proposed method provides the softer smoothness than QV regularization. Experiments of audio inpainting and declipping are conducted to show its advantages in comparison with several existing interpolation methods and sparse modeling.
Existing image-to-image translation (I2IT) methods are either constrained to low-resolution images or long inference time due to their heavy computational burden on the convolution of high-resolution feature maps. In this paper, we focus on speeding-up the high-resolution photorealistic I2IT tasks based on closed-form Laplacian pyramid decomposition and reconstruction. Specifically, we reveal that the attribute transformations, such as illumination and color manipulation, relate more to the low-frequency component, while the content details can be adaptively refined on high-frequency components. We consequently propose a Laplacian Pyramid Translation Network (LPTN) to simultaneously perform these two tasks, where we design a lightweight network for translating the low-frequency component with reduced resolution and a progressive masking strategy to efficiently refine the high-frequency ones. Our model avoids most of the heavy computation consumed by processing high-resolution feature maps and faithfully preserves the image details. Extensive experimental results on various tasks demonstrate that the proposed method can translate 4K images in real-time using one normal GPU while achieving comparable transformation performance against existing methods. Datasets and codes are available: https://github.com/csjliang/LPTN.
Emerging technologies can have major economic impacts and affect strategic stability. Yet, early identification of emerging technologies remains challenging. In order to identify emerging technologies in a timely and reliable manner, a comprehensive examination of relevant scientific and technological (S&T) trends and their related references is required. This examination is generally done by domain experts and requires significant amounts of time and effort to gain insights. The use of domain experts to identify emerging technologies from S&T trends may limit the capacity to analyse large volumes of information and introduce subjectivity in the assessments. Decision support systems are required to provide accurate and reliable evidence-based indicators through constant and continuous monitoring of the environment and help identify signals of emerging technologies that could alter security and economic prosperity. For example, the research field of hypersonics has recently witnessed several advancements having profound technological, commercial, and national security implications. In this work, we present a multi-layer quantitative approach able to identify future signs from scientific publications on hypersonics by leveraging deep learning and weak signal analysis. The proposed framework can help strategic planners and domain experts better identify and monitor emerging technology trends.
This paper presents a variational representation of the Bayes' law using optimal transportation theory. The variational representation is in terms of the optimal transportation between the joint distribution of the (state, observation) and their independent coupling. By imposing certain structure on the transport map, the solution to the variational problem is used to construct a Brenier-type map that transports the prior distribution to the posterior distribution for any value of the observation signal. The new formulation is used to derive the optimal transport form of the Ensemble Kalman filter (EnKF) for the discrete-time filtering problem and propose a novel extension of EnKF to the non-Gaussian setting utilizing input convex neural networks. Finally, the proposed methodology is used to derive the optimal transport form of the feedback particle filler (FPF) in the continuous-time limit, which constitutes its first variational construction without explicitly using the nonlinear filtering equation or Bayes' law.