This article introduces a novel approach for building a robust Automatic Gesture Recognition system based on Surface Electromyographic (sEMG) signals, acquired at the forearm level. Our main contribution is to propose new constrained learning strategies that ensure robustness against adversarial perturbations by controlling the Lipschitz constant of the classifier. We focus on nonnegative neural networks for which accurate Lipschitz bounds can be derived, and we propose different spectral norm constraints offering robustness guarantees from a theoretical viewpoint. Experimental results on four publicly available datasets highlight that a good tradeoff in terms of accuracy and performance is achieved. We then demonstrate the robustness of our models, compared with standard trained classifiers in four scenarios, considering both white-box and black-box attacks.

Large language models (LLMs) have demonstrated impressive capabilities in natural language processing. However, their internal mechanisms are still unclear and this lack of transparency poses unwanted risks for downstream applications. Therefore, understanding and explaining these models is crucial for elucidating their behaviors, limitations, and social impacts. In this article, we introduce a taxonomy of explainability techniques and provide a structured overview of methods for explaining Transformer-based language models. We categorize techniques based on the training paradigms of LLMs: traditional fine-tuning-based paradigm and prompting-based paradigm. For each paradigm, we summarize the goals and dominant approaches for generating local explanations of individual predictions and global explanations of overall model knowledge. We also discuss metrics for evaluating generated explanations and discuss how explanations can be leveraged to debug models and improve performance. Lastly, we examine key challenges and emerging opportunities for explanation techniques in the era of LLMs in comparison to conventional deep learning models.

We apply reinforcement learning to video compressive sensing to adapt the compression ratio. Specifically, video snapshot compressive imaging (SCI), which captures high-speed video using a low-speed camera is considered in this work, in which multiple ( B ) video frames can be reconstructed from a snapshot measurement. One research gap in previous studies is how to adapt B in the video SCI system for different scenes. In this article, we fill this gap utilizing reinforcement learning (RL). An RL model, as well as various convolutional neural networks for reconstruction, are learned to achieve adaptive sensing of video SCI systems. Furthermore, the performance of an object detection network using directly the video SCI measurements without reconstruction is also used to perform RL-based adaptive video compressive sensing. Our proposed adaptive SCI method can thus be implemented in low cost and real time. Our work takes the technology one step further towards real applications of video SCI.

The generic object detection (GOD) task has been successfully tackled by recent deep neural networks, trained by an avalanche of annotated training samples from some common classes. However, it is still non-trivial to generalize these object detectors to the novel long-tailed object classes, which have only few labeled training samples. To this end, the Few-Shot Object Detection (FSOD) has been topical recently, as it mimics the humans’ ability of learning to learn and intelligently transfers the learned generic object knowledge from the common heavy-tailed to the novel long-tailed object classes. Especially, the research in this emerging field has been flourishing in recent years with various benchmarks, backbones, and methodologies proposed. To review these FSOD works, there are several insightful FSOD survey articles [ 58 , 59 , 74 , 78 ] that systematically study and compare them as the groups of fine-tuning/transfer learning and meta-learning methods. In contrast, we review the existing FSOD algorithms from a new perspective under a new taxonomy based on their contributions, i.e., data-oriented, model-oriented, and algorithm-oriented. Thus, a comprehensive survey with performance comparison is conducted on recent achievements of FSOD. Furthermore, we also analyze the technical challenges, the merits and demerits of these methods, and envision the future directions of FSOD. Specifically, we give an overview of FSOD, including the problem definition, common datasets, and evaluation protocols. The taxonomy is then proposed that groups FSOD methods into three types. Following this taxonomy, we provide a systematic review of the advances in FSOD. Finally, further discussions on performance, challenges, and future directions are presented.

In recent years, automatic skin lesion diagnosis methods based on artificial intelligence have achieved great success. However, the lack of labeled data, visual similarity between skin diseases, and restriction on private data sharing remain the major challenges in skin lesion diagnosis. In this article, first, we propose a federated contrastive learning framework to break down data silos and enhance the generalizability of diagnostic model to unseen data. Subsequently, by combining data features from different participated nodes, the proposed framework can improve the performance of contrastive training. To extract discriminative features during on-device training, we propose a contrastive learning based intelligent skin lesion diagnosis scheme in edge computing networks. Specifically, a contrastive learning based dual encoder network is designed to overcome training sample scarcity by fully leveraging unlabeled samples for performance improvement. Meanwhile, we devise a maximum mean discrepancy based supervised contrastive loss function, which can efficiently explore complex intra-class and inter-class variances of samples. Finally, the diagnosis simulations demonstrate that compared with existing methods, our proposed scheme can achieve superior accuracy in both on-device training and distributed training scenarios.

Satellite imagery depicts the Earth’s surface remotely and provides comprehensive information for many applications, such as land use monitoring and urban planning. Existing studies on unsupervised representation learning for satellite images only take into account the images’ geographic information, ignoring human activity factors. To bridge this gap, we propose using the Point-of-Interest (POI) data to capture human factors and designing a contrastive learning-based framework to consolidate the representation of satellite imagery with POI information. Besides, we introduce a season-invariant representation learning model on satellite imagery, considering that human factors are mostly unchanging with respect to seasons. An attention model is designed at last to merge the representations from the geographic, seasonal, and POI perspectives adaptively. On the basis of real-world datasets collected from Beijing, 1 we evaluate our method for predicting socioeconomic indicators. The results show that the representation containing POI information outperforms the geographic representation in estimating commercial activity-related indicators. Our proposed attentional framework can estimate the socioeconomic indicators with R 2 of 0.874 and outperforms the baseline methods. Furthermore, we explore the differences in the representations of satellite images with varying socioeconomic statuses. Finally, we investigate the impact of geographic and POI perspective information in the representation learning process, as well as the effect of satellite imagery on various spatial resolutions.

Multi-view clustering aims to capture the multiple views inherent information by identifying the data clustering that reflects distinct features of datasets. Since there is a consensus in literature that different views of a dataset share a common latent structure, most existing multi-view subspace learning methods rely on the nuclear norm to seek the low-rank representation of the underlying subspace. However, the nuclear norm often fails to distinguish the variance of features for each cluster due to its convex nature and data tends to fall in multiple non-linear subspaces for multi-dimensional datasets. To address these problems, we propose a new and novel multi-view clustering method (HL-L21-TLD-MSC) that unifies the Hyper-Laplacian (HL) and exclusive ℓ 2,1 (L21) regularization with the Tensor Log-Determinant Rank Minimization (TLD) setting. Specifically, the hyper-Laplacian regularization maintains the local geometrical structure that makes the estimation prune to nonlinearities, and the mixed ℓ 2,1 and ℓ 1,2 regularization provides the joint sparsity within-cluster as well as the exclusive sparsity between-cluster. Furthermore, a log-determinant function is used as a tighter tensor rank approximation to discriminate the dimension of features. An efficient alternating algorithm is then derived to optimize the proposed model, and the construction of a convergent sequence to the Karush-Kuhn-Tucker (KKT) critical point solution is mathematically validated in detail. Extensive experiments are conducted on ten well-known datasets to demonstrate that the proposed approach outperforms the existing state-of-the-art approaches with various scenarios, in which, six of them achieve perfect results under our framework developed in this article, demonstrating highl effectiveness for the proposed approach.

In this article, we study knowledge concept recommendation in Massive Open Online Courses (MOOCs) in an explainable manner. Knowledge concepts, composing course units (e.g., videos) in MOOCs, refer to topics and skills that students are expected to master. Compared to traditional course recommendation in MOOCs, knowledge concepts recommendation has drawn more attention because students’ interests over knowledge concepts can better revealstudents’ real intention in a more refined granularity. However, there are three unique challenges in knowledge concept recommendation: (1) How to design an appropriate data structure to capture complex relationships between knowledge concepts, course units, and other participants (e.g., students, teachers)? (2) How to model interactions between students and knowledge concepts? (3) How to make explainable recommendation results to students? To tackle these challenges, we formulate the knowledge concept recommendation as a reinforcement learning task integrated with MOOC knowledge graph (KG). Specifically, we first construct MOOC KG as the environment to capture all the relationships and behavioral histories by considering all the entities (e.g., students, teachers, videos, courses, and knowledge concepts) on the MOOC provider. Then, to model the interactions between students and knowledge concepts, we train an agent to mimic students’ learning behavioral patterns facing the complex environment. Moreover, to provide explainable recommendation results, we generate recommended knowledge concepts in the format of a path from MOOC KG to indicate semantic reasons. Finally, we conduct extensive experiments on a real-world MOOC dataset to demonstrate the effectiveness of our proposed method.

This article presents FLGC, a simple yet effective fully linear graph convolutional network for semi-supervised and unsupervised learning. Instead of using gradient descent, we train FLGC based on computing a global optimal closed-form solution with a decoupled procedure, resulting in a generalized linear framework and making it easier to implement, train, and apply. We show that (1) FLGC is powerful to deal with both graph-structured data and regular data, (2) training graph convolutional models with closed-form solutions improve computational efficiency without degrading performance, and (3) FLGC acts as a natural generalization of classic linear models in the non-Euclidean domain (e.g., ridge regression and subspace clustering). Furthermore, we implement a semi-supervised FLGC and an unsupervised FLGC by introducing an initial residual strategy, enabling FLGC to aggregate long-range neighborhoods and alleviate over-smoothing. We compare our semi-supervised and unsupervised FLGCs against many state-of-the-art methods on a variety of classification and clustering benchmarks, demonstrating that the proposed FLGC models consistently outperform previous methods in terms of accuracy, robustness, and learning efficiency. The core code of our FLGC is released at https://github.com/AngryCai/FLGC .

Nowadays, graph structure data has played a key role in machine learning because of its simple topological structure, and therefore, the graph representation learning methods have attracted great attention. And it turns out that the low-dimensional embedding representation obtained by graph representation learning is extremely useful in various typical tasks, such as node classification and content recommendation. However, most of the existing methods do not further dig out potential structural information on the original graph structure. Here, we propose wGCN, which utilizes random walk to obtain the node-specific mesoscopic structures (high-order local structure) of the graph and utilizes these mesoscopic structures to enhance the graph and organize the characteristic information of the nodes. Our method can effectively generate node embedding for data of previously unknown categories, which has been proven in a series of experiments conducted on many types of graph networks. And compared to baselines, our method shows the best performance on most datasets and achieves competitive results on others. It is believed that combining the mesoscopic structure to further explore the structural information of the graph will greatly improve the learning efficiency of the graph neural network.