Joint Training Research Articles

Pseudo label refining for semi-supervised temporal action localization.

The training of temporal action localization models relies heavily on a large amount of manually annotated data. Video annotation is more tedious and time-consuming compared with image annotation. Therefore, the semi-supervised method that combines labeled and unlabeled data for joint training has attracted increasing attention from academics and industry. This study proposes a method called pseudo-label refining (PLR) based on the teacher-student framework, which consists of three key components. First, we propose pseudo-label self-refinement which features in a temporal region interesting pooling to improve the boundary accuracy of TAL pseudo label. Second, we design a module named boundary synthesis to further refined temporal interval in pseudo label with multiple inference. Finally, an adaptive weight learning strategy is tailored for progressively learning pseudo labels with different qualities. The method proposed in this study uses ActionFormer and BMN as the detector and achieves significant improvement on the THUMOS14 and ActivityNet v1.3 datasets. The experimental results show that the proposed method significantly improve the localization accuracy compared to other advanced SSTAL methods at a label rate of 10% to 60%. Further ablation experiments show the effectiveness of each module, proving that the PLR method can improve the accuracy of pseudo-labels obtained by teacher model reasoning.

SCS-JPGD: Single-Channel-Signal Joint Projected Gradient Descent

The fault diagnosis of industrial equipment is crucial for ensuring production safety and improving the efficiency of equipment operation. With the advancement of sensor technologies, the number of data generated in industrial environments has increased dramatically. Deep learning techniques, with their powerful feature extraction and classification capabilities, have become a research hotspot in the field of fault diagnosis. However, deep learning models are vulnerable to adversarial attacks, which can lead to a decrease in diagnostic accuracy and compromise system safety. This paper proposes a Joint Projection Gradient Descent (SCS-JPGD) method based on single-channel signal features. The proposed method first introduces a gradient-based attack approach for signal samples, which can add tiny perturbations to the input samples, causing misclassification in black-box models. Secondly, a joint training strategy is proposed for gradient attacks on signal samples, aiming to enhance the model’s adaptability to small perturbations in a limited range. Experiments were conducted on the CWRU dataset under four different operating conditions. The results show that, under a deep learning model with diagnostic accuracy exceeding 90%, the joint training method allows the model to maintain an average accuracy of 84.6% even after the addition of adversarial samples, which are barely distinguishable by the human eye. The proposed SCS-JPGD method provides a safer and more accurate approach for fault diagnosis in deep learning research.

Keeping streets safe at night: navigating jurisdictional boundaries between the police and the private security industry

Purpose Keeping streets safe at night to protect users of the night-time economy (NTE) is a responsibility shared by the police and private security companies, yet little is known about this collaboration in practice. The study aims to explore the experience of both agencies to reveal examples of good practice as well as any tensions and risks that emanate from this partnership. Design/methodology/approach Focus groups with 19 police officers and four private security guards were conducted in one city in the Southeast of England, UK, during 2023, to elicit their narrative accounts of working at night and their attitudes towards one another. Findings The study revealed the importance of non-statutory agencies in maintaining order in the city centre at night, often in the absence of a police presence, at the expense of their own safety and without legal and physical protection. However, private security guards recognised that they sometimes traversed their jurisdictional boundaries. This practice concerned the police, as it compromised formal investigation and blurred lines of responsibility. Both the police and security guards identified training needs, experienced violence themselves, felt unsupported in their work and recognised that more could be done to build collaborative working relations. Practical implications The findings suggest several practical strategies that would enhance statutory and non-statutory collaboration, particularly through strengthening the understanding of where jurisdictional boundaries should be drawn. Specifically, the instatement of formal channels of communication between formal policing and private security, alongside joint training, would be beneficial. Originality/value This study explores a gap in the current knowledge and understanding of how order is maintained at night. There is limited research into the role of private security and our understanding of police experiences of night working is nascent. By holding focus groups simultaneously with both agencies gave new insights into the current working relationship and views of one another. The respondents articulated not only mutual respect but also significant levels of distrust and misunderstandings, leading to risks for both groups and users of the NTE. The findings provide recommendations to strengthen collaborative working.

Exploring Data Set Bias and Decision Support with Predictive Uncertainty Through Bayesian Approximations and Convolutional Neural Networks

Abstract Individual seismic catalogs can contain multiscale observations from fault level to global scales and associated waveforms from discrete events reflect crustal structure across many different scales and locations. Seismic network aperture, geographic location, and observation distance may not provide informative guidance or intuition on how different catalogs will behave across models trained under different conditions. We rely on uncertainty to provide guardrails for when to trust model decisions, but understanding when our uncertainty is trustworthy is an open challenge. Here, we explore Bayesian approximation methods for assigning predictive uncertainty in seismic event classification problems. We find that computationally expensive Bayesian approximations do not outperform simple ensemble methods. We also find that when exploiting multiple seismic event catalogs, joint training with data from all the catalogs combined with Bayesian approximations and supervised training for classification can obscure bias and result in less robust uncertainty while also not providing substantial performance benefits compared to training individual models for each catalog.

Joint embedding–classifier learning for interpretable collaborative filtering

BackgroundInterpretability is a topical question in recommender systems, especially in healthcare applications. An interpretable classifier quantifies the importance of each input feature for the predicted item-user association in a non-ambiguous fashion.ResultsWe introduce the novel Joint Embedding Learning-classifier for improved Interpretability (JELI). By combining the training of a structured collaborative-filtering classifier and an embedding learning task, JELI predicts new user-item associations based on jointly learned item and user embeddings while providing feature-wise importance scores. Therefore, JELI flexibly allows the introduction of priors on the connections between users, items, and features. In particular, JELI simultaneously (a) learns feature, item, and user embeddings; (b) predicts new item-user associations; (c) provides importance scores for each feature. Moreover, JELI instantiates a generic approach to training recommender systems by encoding generic graph-regularization constraints.ConclusionsFirst, we show that the joint training approach yields a gain in the predictive power of the downstream classifier. Second, JELI can recover feature-association dependencies. Finally, JELI induces a restriction in the number of parameters compared to baselines in synthetic and drug-repurposing data sets.

You Don’t Have to Say Where to Edit! jLED – Joint Learning to Localize and Edit Source Code

Learning to edit code automatically is becoming more and more feasible. Thanks to recent advances in Neural Machine Translation (NMT), various case studies are being investigated where patches are automatically produced and assessed either automatically (using test suites) or by developers themselves. An appealing setting remains when the developer must provide a natural language input of the requirement for the code change. A recent proof of concept in the literature showed that it is indeed feasible to translate these natural language requirements into code changes. A recent advancement, MODIT [8], has shown promising results in code editing by leveraging natural language, code context, and location information as input. However, it struggles when location information is unavailable. While several studies [29, 81] have demonstrated the ability to edit source code without explicitly specifying the edit location, they still tend to generate edits with less accuracy at the line level. In this work, we address the challenge of generating code edits without precise location information, a scenario we consider crucial for the practical adoption of NMT in code development. To that end, we develop a novel joint training approach for both localization and source code editions. Building a benchmark based on over 70k commits (patches and messages), we demonstrate that our jLED ( j oint L ocalize and ED it) approach is effective. An ablation study further demonstrates the importance of our design choice in joint training.

Efficient Multi-Task Training with Adaptive Feature Alignment for Universal Image Segmentation.

Universal image segmentation aims to handle all segmentation tasks within a single model architecture and ideally requires only one training phase. To achieve task-conditioned joint training, a task token needs to be used in the multi-task training to condition the model for specific tasks. Existing approaches generate the task token from a text input (e.g., "the task is panoptic"). However, such text-based inputs merely serve as labels and fail to capture the inherent differences between tasks, potentially misleading the model. In addition, the discrepancy between visual and textual modalities limits the performance gains in existing text-involved segmentation models. Nevertheless, prevailing modality-alignment methods rely on large-scale uni-modal encoders for both modalities and an extremely large amount of paired data for training, and therefore it is hard to apply these existing models to lightweight segmentation models and resource-constrained devices. In this paper, we propose Adaptive Feature Alignment (AFA) integrated with a learnable task token to address these issues. The learnable task token automatically captures inter-task differences from both image features and text queries during training, providing a more effective and efficient solution than a predefined text-based token. To efficiently align the two modalities without introducing extra complexity, we reconsider the differences between a text token and an image token and replace image features with class-specific means in our proposed AFA. We evaluate our model performance on the ADE20K and Cityscapes datasets. Experimental results demonstrate that our model surpasses baseline models in both efficiency and effectiveness, achieving state-of-the-art performance among segmentation models with a comparable amount of parameters.

An End-To-End Speech Recognition Model for the North Shaanxi Dialect: Design and Evaluation.

The coal mining industry in Northern Shaanxi is robust, with a prevalent use of the local dialect, known as "Shapu", characterized by a distinct Northern Shaanxi accent. This study addresses the practical need for speech recognition in this dialect. We propose an end-to-end speech recognition model for the North Shaanxi dialect, leveraging the Conformer architecture. To tailor the model to the coal mining context, we developed a specialized corpus reflecting the phonetic characteristics of the dialect and its usage in the industry. We investigated feature extraction techniques suitable for the North Shaanxi dialect, focusing on the unique pronunciation of initial consonants and vowels. A preprocessing module was designed to accommodate the dialect's rapid speech tempo and polyphonic nature, enhancing recognition performance. To enhance the decoder's text generation capability, we replaced the Conformer decoder with a Transformer architecture. Additionally, to mitigate the computational demands of the model, we incorporated Connectionist Temporal Classification (CTC) joint training for optimization. The experimental results on our self-established voice dataset for the Northern Shaanxi coal mining industry demonstrate that the proposed Conformer-Transformer-CTC model achieves a 9.2% and 10.3% reduction in the word error rate compared to the standalone Conformer and Transformer models, respectively, confirming the advancement of our method. The next step will involve researching how to improve the performance of dialect speech recognition by integrating external language models and extracting pronunciation features of different dialects, thereby achieving better recognition results.

Mindfulness Interfused with Humor: Insights From a Randomized Controlled Trial of a Humor-Enriched Mindfulness-Based Program

ObjectivesBoth mindfulness and humor are inherently connected to well-being. Recent research found evidence for their combined effect in a joint training, the Humor-Enriched Mindfulness-Based Program (HEMBP). This study extends these findings by exploring (1) effects of Mindfulness-Based Stress Reduction (MBSR) on different forms of humor, (2) differential effects of the HEMBP on outcomes compared to MBSR, and (3) whether the HEMBP and MBSR may alter worldviews.MethodNinety participants were randomly allocated to three conditions: the HEMBP, MBSR, and a wait-list control group. Participants’ mindfulness, psychological well-being, life satisfaction, perceived stress, comic styles, and primal world beliefs (primals) were assessed before and after the trainings, and at 1-, 3-, and 6-month follow-ups. Changes in outcome variables over time were modeled by applying linear mixed-effects models.ResultsThe HEMBP enhanced participants’ mindfulness, benevolent humor, psychological well-being, and life satisfaction compared to the wait-list control. Similarly, MBSR increased participants’ mindfulness and life satisfaction while reducing perceived stress and primal good, but no effects on humor were observed. Comparison between the two trainings revealed trends toward a greater increase in benevolent humor in the HEMBP group and a greater decrease in good in the MBSR group.ConclusionThe results largely replicate previous research on the efficacy of the HEMBP. Both programs demonstrated similar effects on outcomes, with only the HEMBP increasing benevolent humor and psychological well-being, while MBSR reduced stress. Further research is needed to investigate qualitative aspects of the integration of humor in MBPs and the long-term impact of MBPs on individuals’ worldviews.PreregistrationThis study is not preregistered.

On-the-fly Modulation for Balanced Multimodal Learning.

Multimodal learning is expected to boost model performance by integrating information from different modalities. However, its potential is not fully exploited because the widely-used joint training strategy, which has a uniform objective for all modalities, leads to imbalanced and under-optimized uni-modal representations. Specifically, we point out that there often exists modality with more discriminative information, e.g., vision of playing football and sound of blowing wind. They could dominate the joint training process, resulting in other modalities being significantly under-optimized. To alleviate this problem, we first analyze the under-optimized phenomenon from both the feed-forward and the back-propagation stages during optimization. Then, On-the-fly Prediction Modulation (OPM) and On-the-fly Gradient Modulation (OGM) strategies are proposed to modulate the optimization of each modality, by monitoring the discriminative discrepancy between modalities during training. Concretely, OPM weakens the influence of the dominant modality by dropping its feature with dynamical probability in the feed-forward stage, while OGM mitigates its gradient in the back-propagation stage. In experiments, our methods demonstrate considerable improvement across a variety of multimodal tasks. These simple yet effective strategies not only enhance performance in vanilla and task-oriented multimodal models, but also in more complex multimodal tasks, showcasing their effectiveness and flexibility.

An Ensemble-based Joint Training Framework for Robust Anomaly Detection

An Ensemble-based Joint Training Framework for Robust Anomaly Detection

Dinamika Interaksi Antara Karyawan Tetap dan Karyawan Kontrak di Lingkungan Hotel

The hospitality industry operates within a complex work dynamic, requiring collaboration between permanent and contract employees. This study aims to understand the interaction between these two groups in hotels located in Badung, Bali, focusing on collaboration, communication, task allocation, perceptions of fairness, and the impact of employment status differences on team productivity. A descriptive qualitative design was employed, using simple random sampling to select 34 respondents from various hotels in Badung. Data were collected through closed questionnaires and open-ended responses. The findings reveal that working relationships between permanent and contract employees are generally positive and professional, supported by effective communication and strong coordination. However, challenges persist, including perceptions of unfairness in benefits, career development opportunities, and unequal compensation. Good communication helps maintain team harmony, although contract employees may face difficulties expressing themselves in formal settings. Minor conflicts are usually resolved through communication and mutual understanding. The study recommends developing inclusive and fair policies, implementing joint training to strengthen team synergy, and creating participatory opportunities for contract employees in decision-making processes. Effective management can foster a harmonious work environment, enhance employee satisfaction, and support the sustainable operation of hotels.

Prototype‐Based Collaborative Learning in UAV‐Assisted Edge Computing Networks

ABSTRACTContextThe rise of artificial intelligence of things (AloT) has enabled smart cities and industries, and UAV‐assisted edge computing networks are an important technology to support the above scenarios. UAV‐assisted refers to leveraging UAVs as a dynamic, flexible infrastructure to assist edge network data processing and communication tasks. Multiple UAVs can use their own resources, and collaborate edge servers to train artificial intelligence (Al) models.ObjectiveCompared with cloud‐based collaborative computing scenarios, UAV‐assisted edge collaborative learning can reduce training and inference delays and improve user satisfaction. However, UAV‐assisted edge networks scenario brings new challenges in terms of transmission burden and energy consumption.MethodThis paper proposes a prototype‐based joint optimization and training software system. The system consists of an optimization module and a training module. The optimization module first models an optimization problem including energy consumption and prototype error. Then it solves the optimization problem by problem transformation and plans the location of each UAV given the objects' position. After UAVs fly to the designated area and complete data collection, UAVs and the edge server train a model according to the proposed prototype‐based collaborative training module. Our training module enables multiple UAVs and an edge server to collaboratively train a model by lightweight prototype transmission and prototype aggregation. We also prove the convergence of the proposed collaborative training method.ResultsResults show our method reduces prototype error and energy consumption by at least 12.31% and improves model accuracy by 3.62% with a little communication burden.ConclusionFinally, we verify system performance through experiments.

JTIS: enhancing biomedical document-level relation extraction through joint training with intermediate steps.

Biomedical Relation Extraction (RE) is central to Biomedical Natural Language Processing and is crucial for various downstream applications. Existing RE challenges in the field of biology have primarily focused on intra-sentential analysis. However, with the rapid increase in the volume of literature and the complexity of relationships between biomedical entities, it often becomes necessary to consider multiple sentences to fully extract the relationship between a pair of entities. Current methods often fail to fully capture the complex semantic structures of information in documents, thereby affecting extraction accuracy. Therefore, unlike traditional RE methods that rely on sentence-level analysis and heuristic rules, our method focuses on extracting entity relationships from biomedical literature titles and abstracts and classifying relations that are novel findings. In our method, a multitask training approach is employed for fine-tuning a Pre-trained Language Model in the field of biology. Based on a broad spectrum of carefully designed tasks, our multitask method not only extracts relations of better quality due to more effective supervision but also achieves a more accurate classification of whether the entity pairs are novel findings. Moreover, by applying a model ensemble method, we further enhance our model's performance. The extensive experiments demonstrate that our method achieves significant performance improvements, i.e. surpassing the existing baseline by 3.94% in RE and 3.27% in Triplet Novel Typing in F1 score on BioRED, confirming its effectiveness in handling complex biomedical literature RE tasks. Database URL: https://codalab.lisn.upsaclay.fr/competitions/13377#learn_the_details-dataset.

Leveraging Deep Learning for Robust Structural Damage Detection and Classification: A Transfer Learning Approach via CNN

Transfer learning techniques for structural health monitoring in bridge-type structures are investigated, focusing on model generalizability and domain adaptation challenges. Finite element models of bridge-type structures with varying geometry were simulated using the OpenSeesPy platform. Different levels of damage states were introduced at the midspans of these models, and Gaussian-based load time histories were applied at mid-span for dynamic time-history analysis to calculate acceleration data. Then, this acceleration time-history series was transformed into grayscale images, serving as inputs for a Convolutional Neural Network developed to detect and classify structural damage states. Initially, it was trained and tested on datasets derived from a Single-Source Domain structure, achieving perfect accuracy (1.0) in a ten-label multi-class classification task. However, this accuracy significantly decreased when the model was sequentially tested on structures with different geometry without retraining. To address this challenge, it is proposed that transfer learning be employed via feature extraction and joint training. The model showed a reduction in accuracy percentage when adapting from a Single-Source Domain to Multiple-Target Domains, revealing potential issues with non-homogeneous data distribution and catastrophic forgetting. Conversely, joint training, which involves training on all datasets except the specific Target Domain, generated a generalized network that effectively mitigated these issues and maintained high accuracy in predicting unseen class labels. This study highlights the integration of simulation data into the Deep Learning-based SHM framework, demonstrating that a generalized model created via Joint Learning utilizing FEM can potentially reduce the consequences of modeling errors and operational uncertainties unavoidable in real-world applications.

Label Deconvolution for Node Representation Learning on Large-Scale Attributed Graphs Against Learning Bias.

Node representation learning on attributed graphs-whose nodes are associated with rich attributes (e.g., texts and protein sequences)-plays a crucial role in many important downstream tasks. To encode the attributes and graph structures simultaneously, recent studies integrate pre-trained models with graph neural networks (GNNs), where pre-trained models serve as node encoders (NEs) to encode the attributes. As jointly training large NEs and GNNs on large-scale graphs suffers from severe scalability issues, many methods propose to train NEs and GNNs separately. Consequently, they do not take feature convolutions in GNNs into consideration in the training phase of NEs, leading to a significant learning bias relative to the joint training. To address this challenge, we propose an efficient label regularization technique, namely Label Deconvolution (LD), to alleviate the learning bias by a novel and highly scalable approximation to the inverse mapping of GNNs. The inverse mapping leads to an objective function that is equivalent to that by the joint training, while it can effectively incorporate GNNs in the training phase of NEs against the learning bias. More importantly, we show that LD converges to the optimal objective function values by the joint training under mild assumptions. Experiments demonstrate LD significantly outperforms state-of-the-art methods on Open Graph Benchmark datasets.

TDKI-Net: A Joint q-t Space Learning Network for Diffusion-Time-Dependent Kurtosis Imaging.

Time-dependent diffusion magnetic resonance imaging (TDDMRI) is useful for the non-invasive characterization of tissue microstructure. These models require both densely sampled q-t space data for microstructural fitting, leading to very time-consuming acquisition protocols. To overcome this problem, we present a joint q-t space model-tDKI-Net to estimate diffusion-time dependent kurtosis and the transmembrane exchange, using downsampled q-t space data. The tDKI-Net is composed of several q-Encoders and a t-Encoder, designed based on the extragradient mechanism, each integrated with their respective mapping networks. In the tDKI-Net, two types of encoders along with their mapping networks are employed sequentially to generate kurtosis at individual diffusion times and to fit the transmembrane exchange time ( τm) using the time-dependent kurtosis according the Kärger's model. Meanwhile, we proposed a three-stage training strategy, including physics-informed self-supervised pretraining, DKI warm-up, and joint training, to match the network structure. Our results demonstrated that the proposed tDKI-Net could effectively accelerate tDKI scans, resulting in lower estimation error compared with other methods. Our proposed three-stage training strategy demonstrated superior results than those training from scratch, e.g., the normalized root mean square error (NRMSE) of τm decreased by up to 1.4%. We also investigated the training data size effects and found that although we used one-subject training, the network achieved lower NRMSEs for Kavg, K0 and τm (2.50%, 3.04%, 10.86%) than previous work that used three-subject training (3.8%, 9.5%, 12.1%). tDKI-Net can considerably reduce the scan time by 10.5- fold by joint downsampling the q-t space data without compromising the estimation accuracy.

Diff-MTS: Temporal-Augmented Conditional Diffusion-Based AIGC for Industrial Time Series Toward the Large Model Era.

Industrial multivariate time series (MTS) is a critical view of the industrial field for people to understand the state of machines. However, due to data collection difficulty and privacy concerns, available data for building industrial intelligence and industrial large models is far from sufficient. Therefore, industrial time series data generation is of great importance. Existing research usually applies generative adversarial networks (GANs) to generate MTS. However, GANs suffer from the unstable training process due to the joint training of the generator and discriminator. This article proposes a temporal-augmented conditional adaptive diffusion model, termed Diff-MTS, for MTS generation. It aims to better handle the complex temporal dependencies and dynamics of MTS data. Specifically, a conditional adaptive maximum-mean discrepancy (Ada-MMD) method has been proposed for the controlled generation of MTS, which does not require a classifier to control the generation. It improves the condition consistency of the diffusion model. Moreover, a temporal decomposition reconstruction UNet (TDR-UNet) is established to capture complex temporal patterns and further improve the quality of the synthetic time series. Comprehensive experiments on the C-MAPSS and FEMTO datasets demonstrate that the proposed Diff-MTS performs substantially better in terms of diversity, fidelity, and utility compared with the GAN-based methods. These results show that Diff-MTS facilitates the generation of industrial data, contributing to intelligent maintenance and the construction of industrial large models.

Ricci Curvature-Based Graph Sparsification for Continual Graph Representation Learning.

Memory replay, which stores a subset of historical data from previous tasks to replay while learning new tasks, exhibits state-of-the-art performance for various continual learning applications on the Euclidean data. While topological information plays a critical role in characterizing graph data, existing memory replay-based graph learning techniques only store individual nodes for replay and do not consider their associated edge information. To this end, based on the message-passing mechanism in graph neural networks (GNNs), we present the Ricci curvature-based graph sparsification technique to perform continual graph representation learning. Specifically, we first develop the subgraph episodic memory (SEM) to store the topological information in the form of computation subgraphs. Next, we sparsify the subgraphs such that they only contain the most informative structures (nodes and edges). The informativeness is evaluated with the Ricci curvature, a theoretically justified metric to estimate the contribution of neighbors to represent a target node. In this way, we can reduce the memory consumption of a computation subgraph from O(dL) to O(1) and enable GNNs to fully utilize the most informative topological information for memory replay. Besides, to ensure the applicability on large graphs, we also provide the theoretically justified surrogate for the Ricci curvature in the sparsification process, which can greatly facilitate the computation. Finally, our empirical studies show that SEM outperforms state-of-the-art approaches significantly on four different public datasets. Unlike existing methods, which mainly focus on task incremental learning (task-IL) setting, SEM also succeeds in the challenging class incremental learning (class-IL) setting in which the model is required to distinguish all learned classes without task indicators and even achieves comparable performance to joint training, which is the performance upper bound for continual learning.

Investigation and implementation of case-based learning in the sino-foreign joint program of preventive medicine

BackgroundThe current objective of preventive medicine reform is to guarantee that clinical medical students possess a comprehensive understanding of preventive medicine concepts, knowledge, and skills. Previously, case-based learning (CBL) was mostly employed to reform the clinical medicine curriculum, but there was a lack of reform in preventive medicine for clinical students in Sino-foreign joint training programs. The aim of this study was to investigate the impact of case-based learning in the Sino-foreign joint program of preventive medicine.MethodsA total of 79 clinical medical students from the Sino-foreign joint program at Wenzhou Medical University were selected as participants to engage in 10 case-based learning sessions. The effectiveness of the instruction was assessed by analyzing the final exam scores and questionnaire responses, which encompassed instructor evaluation, self-assessment, and course learning effectiveness evaluation (CLEE).ResultsIn contrast to the traditional approach, which yielded a final score of 69.2, the case-based students achieved an average of 77.62. The results of instructor evaluation showed that students’ academic performance, problem-solving capabilities, research cooperation and communication, and learning attitude all improved significantly following case-based learning (P < 0.05). The self-assessment scores for all five case discussion courses exceeded 75 points, suggesting that students believed their overall competence had increased significantly. The CLEE demonstrated that CBL had a positive impact on students’ learning and was highly advantageous for students.ConclusionsIt is deserving of active promotion in medical education reform that case-based learning can enhance students’ comprehensive quality and classroom participation. Further research is required to ascertain whether it can replace traditional teaching methods.Trial registrationNot clinical trial.