Defect recognition is an important task in intelligent manufacturing. Due to the subjectivity of human annotation, the collected defect data usually contains a lot of noise and unpredictable uncertainties, which have a great negative influence on defect recognition. It is a significant challenge to discover an effective defect recognition model with satisfactory uncertainty processing ability. A natural way is to automatically search for an efficient deep model, which can be realized by neural architecture search (NAS). To achieve this, we propose an efficient fuzzy NAS framework for defect recognition, where the searched architecture can effectively handle uncertain information from the given datasets. Specifically, we first design a fuzzy search space and the related encoding strategy for fuzzy NAS. Then, we propose a comparator-based evolutionary search approach, where an online end-to-end comparator is learned to directly determine the selection of candidate architectures from the evolutionary population. The comparator works in an end-to-end way and it transforms the complex ranking problem of evaluating architectures into a simple classification task, which overcomes the rank disorder issue suffered from traditional performance predictors. A series of experimental results demonstrate that the architecture with fewer #Params (1.22 M) search by fuzzy neural architecture search framework for defect recognition method achieves higher accuracy (92.26%) compared to the state-of-the-art results (i.e., DARTS-PV) on the ELPV dataset, as well as competitive results (accuracy = 76.4%, #Params = 1.04 M) on the CODEBRIM dataset. Experimental results show the effectiveness and efficiency of our proposed method in handling uncertain problems.
24 February 2022 in IEEE Transactions on Network Science and Engineering
With the development of modern technology, numerous economic losses are incurred by various spreading phenomena. Thus, it is of great significance to identify the initial sources triggering such phenomena. The investigation of source localization in social networks has gained substantial attention and become a popular topic of study. For practical spreading phenomena on social networks, the infection rates are relatively low. Hence, a high uncertainty of spreading trace might be incurred, which further incurs the reduction of localization accuracy obtained through existed source localization methods, especially the observer-based ones. Aiming to solve the source localization problem with a low infection rate, we propose a novel localization algorithm, i.e., path-based source identification (PBSI). First, a small number of nodes are selected and designated as observers. After the propagation process triggered by sources, we can obtain a snapshot. Later, a label is assigned to represent whether a node is infected or not, and observers are supposed to record the paths through which nodes are successfully infected. Based on source centrality theory, observers make the labels flow in the direction recorded during the label iteration process, which ensures the labels of nodes in the direction of the source increase gradually. Extensive experiments indicate that the proposed PBSI can handle source localization problems for both single and multi-source scenarios with better performance than that of state-of-the-art algorithms under different propagation models.
24 March 2024 in Proceedings of the AAAI Conference on Artificial Intelligence
With the rise of social media, the spread of fake news has become a significant concern, potentially misleading public perceptions and impacting social stability. Although deep learning methods like CNNs, RNNs, and Transformer-based models like BERT have enhanced fake news detection. However, they primarily focus on content and do not consider social context during news propagation. Graph-based techniques have incorporated the social context but are limited by the need for large labeled datasets. To address these challenges, this paper introduces GAMC, an unsupervised fake news detection technique using the Graph Autoencoder with Masking and Contrastive learning. By leveraging both the context and content of news propagation as self-supervised signals, our method reduces the dependency on labeled datasets. Specifically, GAMC begins by applying data augmentation to the original news propagation graphs. Subsequently, these augmented graphs are encoded using a graph encoder and subsequently reconstructed via a graph decoder. Finally, a composite loss function that encompasses both reconstruction error and contrastive loss is designed. Firstly, it ensures the model can effectively capture the latent features, based on minimizing the discrepancy between reconstructed and original graph representations. Secondly, it aligns the representations of augmented graphs that originate from the same source. Experiments on the real-world dataset validate the effectiveness of our method.
15 November 2022 in IEEE Internet of Things Journal
Adversarial attacks have been successfully extended to the field of point clouds. Besides applying the common perturbation guided by the gradient, adversarial attacks on point clouds can be conducted by applying directional perturbations, e.g., along normal and along the tangent plane. In this paper, we first investigate whether adversarial attacks with these two orthogonal directional perturbations are more imperceptible than that with the gradient-aware perturbation. Second, we investigate the deeper difference between adversarial attacks with these two directional perturbations, and whether they are applicable to the same scenarios. Third, based on the verification results that the above two directional perturbations have different sensitiveness to curvature, we devise a novel normal-tangent attack (NTA) framework with a hybrid directional perturbation scheme that adaptively chooses the direction according to the curvature of the local shape around the point. Extensive experiments on two publicly available datasets, e.g., ModelNet40 and ShapeNet Part, with classifiers in three representative networks, e.g., PointNet++, DGCNN, PointConv, validate the effectiveness of NTA, and the superiority to the state-of-the-art methods.
23 October 2018 in IEEE Transactions on Circuits and Systems II: Express Briefs
In realistic world, vast majority of networks exhibit layered properties, i.e., the same nodes share different links in each layer (referred as multi-layer networks). Here, the epidemic spreading process on multi-layer networks is investigated, where an infectious yet indistinguishable (as symptoms are not presented) state is considered (i.e., an exposed state). Motived by the fact that subjects are inclined to take preventive measure: cutting potential connection with infection sources during undesirable infections, we consider the epidemic spreading process with such an adaptive framework: a susceptible/exposed individual will disconnect with infected neighbors probabilistically. Once a connection is removed, one new connection will be constructed with uninfected one. The epidemic spreading process will be greatly affected with the adoption of adaptive strategy. Furthermore, we also study the effect of varying community number via incorporating new individuals, and find the consideration of community movement plays an important role in the epidemic re-occurrence. Various benchmarks are analyzed via using the proposed model as well to investigating corresponding spreading behaviors.