Learning the graph topology of a complex network is challenging due to limited data availability and imprecise data models. A common remedy in existing works is to incorporate priors such as sparsity or modularity which highlight on the structural property of graph topology. We depart from these approaches to develop priors that are directly inspired by complex network dynamics. Focusing on social networks with actions modeled by equilibriums of linear quadratic games, we postulate that the social network topologies are optimized with respect to a social welfare function. Utilizing this prior knowledge, we propose a network games induced regularizer to assist graph learning. We then formulate the graph topology learning problem as a bilevel program. We develop a two-timescale gradient algorithm to tackle the latter. We draw theoretical insights on the optimal graph structure of the bilevel program and show that they agree with the topology in several manmade networks. Empirically, we demonstrate the proposed formulation gives rise to reliable estimate of graph topology.

Previous Multimodal Information based Speech Processing (MISP) challenges mainly focused on audio-visual speech recognition (AVSR) with commendable success. However, the most advanced back-end recognition systems often hit performance limits due to the complex acoustic environments. This has prompted a shift in focus towards the Audio-Visual Target Speaker Extraction (AVTSE) task for the MISP 2023 challenge in ICASSP 2024 Signal Processing Grand Challenges. Unlike existing audio-visual speech enhancement challenges primarily focused on simulation data, the MISP 2023 challenge uniquely explores how front-end speech processing, combined with visual clues, impacts back-end tasks in real-world scenarios. This pioneering effort aims to set the first benchmark for the AVTSE task, offering fresh insights into enhancing the accuracy of back-end speech recognition systems through AVTSE in challenging and real acoustic environments. This paper delivers a thorough overview of the task setting, dataset, and baseline system of the MISP 2023 challenge. It also includes an in-depth analysis of the challenges participants may encounter. The experimental results highlight the demanding nature of this task, and we look forward to the innovative solutions participants will bring forward.

In many real-life systems, the interactions among entities are complex and varied. This necessitates the use of a multiplex graph model with heterogeneous layers of graphs to effectively describe these interactions. The current paper focuses on incorporating high-order relations, specifically inter-layer couplings or connections, in multiplex graph learning. Through developing a high-order smoothness criterion, we propose an algorithm that integrates inter-layer connections to perform inference from multi-attribute graph signals. We show that it is essential to consider high-order interactions in the inference process. We validate our claims through numerical experiments, demonstrating their efficacy in capturing the intricate relationships within multiplex networks.

Video information has been widely introduced to speech enhancement as its contribution at low signal-to-noise ratios (SNRs). Conventional audio-visual speech enhancement networks take noisy speech and video as input and learn features of clean speech directly. To reduce the large SNR gap between the learning target and input noisy speech, we propose a novel mask-based audio-visual progressive learning speech enhancement (AVPL) framework with visual information reconstruction (VIR) to increase SNRs gradually. Each stage of AVPL takes a concatenation of pre-trained visual embedding and the previous representation as input and predicts a mask with the intermediate representation of the current stage. To extract more visual information and deal with the performance distortion, the AVPL-VIR model reconstructs the visual embedding as it is fed in for each stage. Experiment on the TCD-TIMIT dataset shows that the progressive learning method significantly outperforms direct learning for both audio-only and audio-visual models. Moreover, by reconstructing video information, the VIR module provides a more accurate and comprehensive representation of the data, which in turn improves the performance of both AVDL and AVPL.

This paper considers learning a product graph from multi-attribute graph signals. Our work is motivated by the widespread presence of multilayer networks that feature interactions within and across graph layers. Focusing on a product graph setting with homogeneous layers, we propose a bivariate polynomial graph filter model. We then consider the topology inference problems thru adapting existing spectral methods. We propose two solutions for the required spectral estimation step: a simplified solution via unfolding the multiattribute data into matrices, and an exact solution via nearest Kro-necker product decomposition (NKD). Interestingly, we show that strong inter-layer coupling can degrade the performance of the unfolding solution while the NKD solution is robust to inter-layer coupling effects. Numerical experiments show efficacy of our methods.

Weakly Supervised Semantic Segmentation (WSSS) based on image-level labels has been greatly advanced by exploiting the outputs of Class Activation Map (CAM) to generate the pseudo labels for semantic segmentation. However, CAM merely discovers seeds from a small number of regions, which may be insufficient to serve as pseudo masks for semantic segmentation. In this paper, we formulate the expansion of object regions in CAM as an increase in information. From the perspective of information theory, we propose a novel Complementary Patch (CP) Representation and prove that the information of the sum of the CAMs by a pair of input images with complementary hidden (patched) parts, namely CP Pair, is greater than or equal to the information of the baseline CAM. Therefore, a CAM with more information related to object seeds can be obtained by narrowing down the gap between the sum of CAMs generated by the CP Pair and the original CAM. We propose a CP Network (CPN) implemented by a triplet network and three regularization functions. To further improve the quality of the CAMs, we propose a Pixel-Region Correlation Module (PRCM) to augment the contextual in-formation by using object-region relations between the feature maps and the CAMs. Experimental results on the PAS-CAL VOC 2012 datasets show that our proposed method achieves a new state-of-the-art in WSSS, validating the effectiveness of our CP Representation and CPN.

Currently, connected vehicles have gradually stepped into our daily lives, and they generally rely on vehicular networks to generate and exchange traffic-related messages to improve the overall travel safety and efficiency. However, due to the open nature of vehicular networks, these traffic-related messages could be erroneous, which may be caused by various reasons, ranging from an onboard device (OBD) sensor malfunctioning and reporting incorrect reading to the message being tampered by a malicious vehicle. To address these rapidly increasing security challenges, we have proposed an AI-enabled trust management system (AIT) in this article, which is an AI-enabled trust management system for vehicular networks using the blockchain technique. In the AIT system, each vehicle first senses, generates, and exchanges messages with other vehicles. These messages then get validated by the neighboring vehicles. As vehicles receive and validate messages from other nearby vehicles, they will establish and manage the trust of those nearby vehicles, which is enabled by utilizing the deep learning algorithm. Once a vehicle identifies untrustworthy vehicles, it reports them to the nearby roadside unit (RSU), and the RSU will validate the authenticity of the report as well as the identity of the vehicle by using the emerging blockchain technique. The security credentials of untrustworthy vehicles will then be revoked by the RSU. We have conducted an extensive experimental study to evaluate the AIT system. Simulation results clearly indicate that AIT performs better than existing approaches and can manage the trust of vehicles and detect malicious ones in an accurate and efficient manner.