HMHebo Ma

Hebo Ma

*This is an algorithmically generated author record based on publicly available information.

Current Organizations / Institutes

The organizations/institutes from the scholar's latest article

Previous Organizations / Institutes

The organizations / institutes from the scholar's other articles in the past ten years


Hebo Ma has a total of 23 co-authors. Here are the top co-authors by number of shared publications:


Latest Publications

  • Confidence Matters: Balanced Pseudo-Label Selection for Semi-Supervised Few-Shot Learning

    by Kunlei Jing, Hebo Ma, Chen Zhang, Ziyang Shang, Zhiyuan Zha, Bihan Wen

    Semi-Supervised Few-Shot Learning (SSFSL) aims to classify categories given a few support samples and a number of unlabeled samples per class. Most existing methods focus on promoting the pseudo-labeling of unlabeled samples to boost SSFSL performance via more samples with confident pseudo-labels, which is inevitably limited by the scarcity of given support samples for pseudo-labeling training. We realize that confidence selection of pseudo-labeled samples is a promising alternative, for which both task-free generality and task-specific adaptability are crucial to guide accurate and fine-grained selection. To this end, we propose a two-step BalAnced pSeudo-label SelectiOn (BASSO) method that explores certainty entropy to characterize the confidence of pseudo-labels and learns the entropy distributions to guide selection. Specifically, step one rehearses the pseudo-labeling on large task-free samples to model the entropies of high-confidence and low-confidence pseudo-labels as prior general distributions. Step two devises a generator fed with task-specific prototypes to learn the adaptive distributions for each task. We further tailor balancing factors to balance the two types of distributions in guiding the selection during training episodes, ensuring both accurate and fine-grained selection. We perform confidence selection by casting the certainty entropies of pseudo-labeled samples into the balanced distributions and comparing their probabilities subject to high-confidence and low-confidence pseudo-labels, respectively. The comparison deviations denoting confidence levels are utilized to reweight the selected samples for later self-training. Extensive experiments on four benchmarks demonstrate that BASSO effectively balances selection accuracy and amount, showcasing competitive performance against state-of-the-art methods. Our code will be available at https://github.com/Klein-JING/BASSO.


  • Recursive Confidence Training for Pseudo-Labeling Calibration in Semi-Supervised Few-Shot Learning

    by Kunlei Jing, Hebo Ma, Chen Zhang, Lei Wen, Zhaorui Zhang

    Semi-Supervised Few-Shot Learning (SSFSL) aims to address the data scarcity in few-shot learning by leveraging both a few labeled support data and abundant unlabeled data. In SSFSL, a classifier trained on scarce support data is often biased and thus assigns inaccurate pseudo-labels to the unlabeled data, which will mislead downstream learning tasks. To combat this issue, we introduce a novel method called Certainty-Aware Recursive Confidence Training (CARCT). CARCT hinges on the insight that selecting pseudo-labeled data based on confidence levels can yield more informative support data, which is crucial for retraining an unbiased classifier to achieve accurate pseudo-labeling—a process we term pseudo-labeling calibration. We observe that accurate pseudo-labels typically exhibit smaller certainty entropy, indicating high-confidence pseudo-labeling compared to those of inaccurate pseudo-labels. Accordingly, CARCT constructs a joint double-Gaussian model to fit the certainty entropies collected across numerous SSFSL tasks. Thereby, A semi-supervised Prior Confidence Distribution (ssPCD) is learned to aid in distinguishing between high-confidence and low-confidence pseudo-labels. During an SSFSL task, ssPCD guides the selection of both high-confidence and low-confidence pseudo-labeled data to retrain the classifier that then assigns more accurate pseudo-labels to the low-confidence pseudo-labeled data. Such recursive confidence training continues until the low-confidence ones are exhausted, terminating the pseudo-labeling calibration. The unlabeled data all receive accurate pseudo-labels to expand the few support data to generalize the downstream learning task, which in return meta-refines the classifier, named self-training, to boost the pseudo-labeling in subsequent tasks. Extensive experiments on basic and extended SSFSL setups showcase the superiority of CARCT versus state-of-the-art methods, and comprehensive ablation studies and visualizations justify our insight. The source code is available at https://github.com/Klein-JING/CARCT.


  • Model-agnostic counterfactual reasoning for identifying and mitigating answer bias in knowledge tracing

    by Chaoran Cui, Hebo Ma, Xiaolin Dong, Chen Zhang, Chunyun Zhang, Yumo Yao, Meng Chen, Yuling Ma


  • CoSKT: A Collaborative Self-Supervised Learning Method for Knowledge Tracing

    by Chunyun Zhang, Hebo Ma, Chaoran Cui, Yumo Yao, Weiran Xu, Yunfeng Zhang, Yuling Ma

    Knowledge tracing (KT) aims to trace students' evolving knowledge states based on their learning sequences. Recently, some deep learning based models have been proposed to incorporate the historical information of individuals to trace students' knowledge states and achieve encouraging progress. However, these works ignore the collaborative information among those students who have similar exercise–answering experiences, which may contain some valuable information. In this article, we present a novel collaborative self-supervised learning method for KT (CoSKT), which exploits both similar students' collaborative information and individual information to improve KT. We first use the overlap rate of students' learning experiences to retrieve similar students. Based on similar students' exercise–answering sequences, we leverage attention mechanism to learn the representation of their common knowledge state and expected response to the target exercise. Then, we introduce self-supervised learning by encouraging the consistency between the common knowledge state and individual knowledge state. Finally, we integrate collaborative information and individual knowledge state with a gate mechanism to conduct the response prediction of the target exercise. We compare CoSKT with nine existing KT methods on three public datasets, and the results show that CoSKT achieves the state-of-the-art performance.


  • Top Cited Papers
    Open Access

    DGEKT: A Dual Graph Ensemble Learning Method for Knowledge Tracing

    by Chaoran Cui, Yumo Yao, Chunyun Zhang, Hebo Ma, Yuling Ma, Zhaochun Ren, Chen Zhang, James Ko

    Knowledge tracing aims to trace students’ evolving knowledge states by predicting their future performance on concept-related exercises. Recently, some graph-based models have been developed to incorporate the relationships between exercises to improve knowledge tracing, but only a single type of relationship information is generally explored. In this article, we present a novel Dual Graph Ensemble learning method for Knowledge Tracing (DGEKT), which establishes a dual graph structure of students’ learning interactions to capture the heterogeneous exercise–concept associations and interaction transitions by hypergraph modeling and directed graph modeling, respectively. To combine the dual graph models, we introduce the technique of online knowledge distillation. This choice arises from the observation that, while the knowledge tracing model is designed to predict students’ responses to the exercises related to different concepts, it is optimized merely with respect to the prediction accuracy on a single exercise at each step. With online knowledge distillation, the dual graph models are adaptively combined to form a stronger ensemble teacher model, which provides its predictions on all exercises as extra supervision for better modeling ability. In the experiments, we compare DGEKT against eight knowledge tracing baselines on three benchmark datasets, and the results demonstrate that DGEKT achieves state-of-the-art performance.


  • Open Access

    Do We Fully Understand Students' Knowledge States? Identifying and Mitigating Answer Bias in Knowledge Tracing

    by Chaoran Cui, Hebo Ma, Chen Zhang, Chunyun Zhang, Yumo Yao, Meng Chen, Yuling Ma

    Knowledge tracing (KT) aims to monitor students' evolving knowledge states through their learning interactions with concept-related questions, and can be indirectly evaluated by predicting how students will perform on future questions. In this paper, we observe that there is a common phenomenon of answer bias, i.e., a highly unbalanced distribution of correct and incorrect answers for each question. Existing models tend to memorize the answer bias as a shortcut for achieving high prediction performance in KT, thereby failing to fully understand students' knowledge states. To address this issue, we approach the KT task from a causality perspective. A causal graph of KT is first established, from which we identify that the impact of answer bias lies in the direct causal effect of questions on students' responses. A novel COunterfactual REasoning (CORE) framework for KT is further proposed, which separately captures the total causal effect and direct causal effect during training, and mitigates answer bias by subtracting the latter from the former in testing. The CORE framework is applicable to various existing KT models, and we implement it based on the prevailing DKT, DKVMN, and AKT models, respectively. Extensive experiments on three benchmark datasets demonstrate the effectiveness of CORE in making the debiased inference for KT. We have released our code at https://github.com/lucky7-code/CORE.

  • Prototype Correction via Contrastive Augmentation for Few-Shot Unconstrained Palmprint Recognition

    by Kunlei Jing, Xinman Zhang, Chen Zhang, Wanyu Lin, Hebo Ma, Meng Pang, Bihan Wen

    Unconstrained Palmprint Recognition (UPR) shows engaging potential owing to its high hygiene and privacy. The unconstrained acquisition usually produces wide variations, against which deep methods resort to large samples that are unavailable in practice, however. We focus on Few-Shot UPR (FS-UPR), a more general problem, recognizing query samples given a few support samples per class. Because scarce samples insufficiently represent potential variations, the augmentation methods train independent hallucinators on large samples to generate more ones. Whereas, the hallucinators trained independently of Few-Shot Learning (FSL) are blind of generating promising samples to boost the downstream FSL. Moreover, training hallucinators requires large samples per class, unavailable from unconstrained palmprint databases. We aim to address FS-UPR via contrastive augmentation merely on the support samples. Observing the variations to be transferable across samples, we exploit low-rank representation to disentangle support samples into principles and variations in embedding space and augment features by variation transfer. To this end, we devise an end-to-end Deep Low-Rank Representation Feature Augmentation Network (DLRR-FAN) to simultaneously learn the embedding space and augmentation features with guaranteed reality and diversity . Furthermore, a Contrastive Recognition Regularizer (CRR) is tailored to secure the discriminability of augmentation features. During each training episode, the task motivates DLRR-FAN to augment such features that correct the biased prototypes towards upcoming query samples with variations unseen in the support samples, namely task-driven prototype correction. Extensive experiments on both the typical and extended FS-UPR tasks demonstrate the efficacy of DLRR-FAN versus the state-of-the-art methods.