Clustering user devices (UDs) with similar traffic flows enables more effective transmission scheduling and resource allocation in wireless networks, especially for Internet of Things (IoT) with dominant demands for machine-to-machine (M2M) data communications. In this paper, we propose an experience-driven spatial-temporal graph attention network (Exp-STGAN) for UDs’ clustering, by exploiting the spatial-temporal correlations from UDs’ historical traffic flows. Considering the UDs’ heterogeneity, we first characterize each UD’s out-going traffic flows by a dynamic radiation pattern, which reflects the UD’s spatial distribution of traffic demands and its targeted receivers in different directions. We aim to explore UDs’ clustering based on traffic flows’ radiation patterns and propose a spatial-temporal graph attention to aggregate information from different UDs correlated in space and time domains. Without true labels for the UDs’ clustering, we formulate a flow similarity metric based on Kullback-Leibler (KL) divergence to quantify the clustering performance. Moreover, to improve the learning efficiency, we integrate salient human experience into the graph attention module and also continuously update the experience during the training process. Experiments demonstrate that the Exp-STGAN framework can effectively cluster similar UDs by their dynamic traffic flows, highlighting the potential for flow-aware network performance maximization in large-scale IoT systems.

Recent advances in prompt engineering enable large language models (LLMs) to solve multihop logical reasoning problems with impressive accuracy.However, there is little existing work investigating the robustness of LLMs with few-shot prompting techniques.Therefore, we introduce a systematic approach to test the robustness of LLMs in multi-hop reasoning tasks via domain-agnostic perturbations.We include perturbations at multiple levels of abstractions (e.g.lexical perturbations such as typos, and semantic perturbations such as the inclusion of intermediate reasoning steps in the questions) to conduct behavioral analysis on the LLMs.Throughout our experiments, we find that models are more sensitive to certain perturbations such as replacing words with their synonyms.We also demonstrate that increasing the proportion of perturbed exemplars in the prompts improves the robustness of few-shot prompting methods.

Inspired by the great success of deep neural networks (DNNs), many unfolding methods have been proposed to integrate traditional image modeling techniques, such as dictionary learning (DicL) and sparse coding, into DNNs for image restoration. However, the performance of such methods remains limited for several reasons. First, the unfolded architectures do not strictly follow the image representation model of DicL and lose the desired physical meaning. Second, handcrafted priors are still used in most unfolding methods without effectively utilizing the learning capability of DNNs. Third, a universal dictionary is learned to represent all images, reducing the model representation flexibility. We propose a novel framework of deep convolutional dictionary learning (DCDicL), which follows the representation model of DicL strictly, learns the priors for both representation coefficients and the dictionaries, and can adaptively adjust the dictionary for each input image based on its content. The effectiveness of our DCDicL method is validated on the image denoising problem. DCDicL demonstrates leading denoising performance in terms of both quantitative metrics (e.g., PSNR, SSIM) and visual quality. In particular, it can reproduce the subtle image structures and textures, which are hard to recover by many existing denoising DNNs. The code is available at: https://github.com/natezhenghy/DCDicL_denoising.

The mobile-cloud based visual recognition (MCVR) system, in which the low-end mobile sensors are deployed to persistently collect and transmit visual data to the cloud for analysis and recognition, is important for visual monitoring applications such as wildfire detection, wildlife monitoring, etc. However, the current MCVR systems are mostly human-perception-oriented, which consume many computational resources and much energy for data sensing as well as much bandwidth for data transmission, limiting their large-scale deployment. In this work, we present a machine-perception-oriented MCVR system, called BS-MCVR, where the mobile end is designed to efficiently sense highly compact and discriminative features directly from the scene, and the sensed features are analyzed on the cloud for recognition. Particularly, the mobile end is designed to operate with completely binary operations and generate fixed-point feature maps. Experiments on benchmark datasets show that our system only needs to transmit 1/200 the amount of original image data without degrading much the recognition accuracy, while it consumes minimal computational cost in the data sensing process. BS-MCVR provides a highly cost-effective solution for deploying MCVR systems at a large-scale.