23 May 2024 in IEEE Transactions on Neural Networks and Learning Systems
Active learning seeks to achieve strong performance with fewer training samples. It does this by iteratively asking an oracle to label newly selected samples in a human-in-the-loop manner. This technique has gained increasing popularity due to its broad applicability, yet its survey papers, especially for deep active learning (DAL), remain scarce. Therefore, we conduct an advanced and comprehensive survey on DAL. We first introduce reviewed paper collection and filtering. Second, we formally define the DAL task and summarize the most influential baselines and widely used datasets. Third, we systematically provide a taxonomy of DAL methods from five perspectives, including annotation types, query strategies, deep model architectures, learning paradigms, and training processes, and objectively analyze their strengths and weaknesses. Then, we comprehensively summarize the main applications of DAL in natural language processing (NLP), computer vision (CV), data mining (DM), and so on. Finally, we discuss challenges and perspectives after a detailed analysis of current studies. This work aims to serve as a useful and quick guide for researchers in overcoming difficulties in DAL. We hope that this survey will spur further progress in this burgeoning field.
29 March 2021 in IEEE/ACM Transactions on Computational Biology and Bioinformatics
Tracking the dynamic modules (modules change over time) during cancer progression is essential for studying cancer pathogenesis, diagnosis, and therapy. However, current algorithms only focus on detecting dynamic modules from temporal cancer networks without integrating the heterogeneous genomic data, thereby resulting in undesirable performance. To attack this issue, we propose a novel algorithm (aka TANMF ) to detect dynamic modules in cancer temporal attributed networks, which integrates the temporal networks and gene attributes. To obtain the dynamic modules, the temporality and gene attributed are incorporated into an overall objective function, which transforms the dynamic module detection into an optimization problem. TANMF jointly decomposes the snapshots at two subsequent time steps to obtain the latent features of dynamic modules, where the attributes are fused via regulations. Furthermore, the $L_{1}$ constraint is imposed to improve the robustness. Experimental results demonstrate that TANMF is more accurate than state-of-the-art methods in terms of accuracy. By applying TANMF to breast cancer data, the obtained dynamic modules are more enriched by the known pathways and associated with patients’ survival time. The proposed model and algorithm provide an effective way for the integrative analysis of heterogeneous omics.
1 June 2021 in Knowledge-Based Systems
8 September 2021 in IEEE Transactions on Cybernetics
Temporal networks are ubiquitous in nature and society, and tracking the dynamics of networks is fundamental for investigating the mechanisms of systems. Dynamic communities in temporal networks simultaneously reflect the topology of the current snapshot (clustering accuracy) and historical ones (clustering drift). Current algorithms are criticized for their inability to characterize the dynamics of networks at the vertex level, independence of feature extraction and clustering, and high time complexity. In this study, we solve these problems by proposing a novel joint learning model for dynamic community detection in temporal networks (also known as jLMDC) via joining feature extraction and clustering. This model is formulated as a constrained optimization problem. Vertices are classified into dynamic and static groups by exploring the topological structure of temporal networks to fully exploit their dynamics at each time step. Then, jLMDC updates the features of dynamic vertices by preserving features of static ones during optimization. The advantage of jLMDC is that features are extracted under the guidance of clustering, promoting performance, and saving the running time of the algorithm. Finally, we extend jLMDC to detect the overlapping dynamic community in temporal networks. The experimental results on 11 temporal networks demonstrate that jLMDC improves accuracy up to 8.23% and saves 24.89% of running time on average compared to state-of-the-art methods.
6 January 2025 in IEEE Access
Continuous Sign Language Recognition (CSLR) seeks to interpret the gestures used by deaf-mute individuals and translate them into natural language, thereby enhancing communication and interaction. A successful CSLR method relies on the continuous tracking of the presenter’s gestures and facial movements. Existing CSLR methods struggle with fully leveraging fine-grained continuous frame information and often overlook the importance of multi-scale feature integration during decoding. To solve the above-mentioned issues, in this paper, we propose a spatial-temporal feature-enhanced network, called STNet for CSLR task. Firstly, for better continuous frame information exploration, based on the optimal transport algorithm, we first propose a spatial resonance module, which is used to extract the global common spatial features of two adjacent frames along the frame sequence. Secondly, we design a frame-wise loss to preserve and enhance the specific features of each frame. Lastly, to emphasize the multi-scale feature fusion, on the decoder side, we design a multi-temporal perception module, to allow each frame to focus on a larger range of other frames and enhance information interaction from different scales. Extensive experiments on three benchmark datasets including PHOENIX14, PHOENIX14-T, and CSL-Daily demonstrate that STNet consistently outperforms state-of-the-art methods, with a notable improvement of 2.9% in CSLR, showcasing its effectiveness and generalizability. Our approach provides a robust foundation for real-world applications such as sign language education and communication tools, while ablation and case studies highlight the impact of each module, paving the way for future research in CSLR.