One Loop, Two Gains: Can Active Learning win the Lottery for Free?
研究通过在主动学习的每次迭代中整合权重剪枝方法，解决非稳定数据环境下模型稀疏化问题，从而提高计算效率。
0 citationsRead paper
Selected work
Representative Papers
Robustness and User-Perceived Value of Popularity Calibration in Music Recommendation: A User Study
This study investigates whether popularity calibration genuinely enhances user experience in music recommendation and examines its reliability across varying levels of user listening history and item familiarity. The authors construct three types of playlists—high-popularity, low-popularity, and calibrated—and employ a controlled naive recommender to generate personalized lists. Calibration is quantified using Jensen–Shannon divergence (JSD), and subjective user feedback is collected through controlled experiments. This work presents the first systematic validation of JSD’s stability with respect to real users’ perceived calibration. Results indicate that while users can discern differences in popularity, they do not exhibit a significant preference for calibrated recommendations. Moreover, computed popularity labels show only weak alignment with users’ subjective judgments, and the relationship between JSD and perceived calibration is significantly moderated by item familiarity, playlist composition, and the availability of historical interaction data.
0 citationsRead paper
COntExt: Towards Context-Aware Ontology Extension from Operational Metrics
This study addresses the high cost and low efficiency of current ontology extension practices, which heavily rely on manual effort due to the underutilization of domain knowledge implicitly embedded in operational metrics. To overcome this limitation, the work proposes the first context-aware ontology extension framework that systematically leverages structured operational metrics as a source of contextual information. The framework formulates ontology extension as three subtasks: parent class prediction, relationship type prediction, and data property assignment, and integrates natural language processing with knowledge graph techniques to generate automated suggestions. Experimental evaluation on four cybersecurity ontologies demonstrates that the proposed approach significantly outperforms baseline methods relying solely on ontology-internal context, particularly in relationship type prediction and data property assignment, thereby effectively reducing the cost of ontology maintenance.
0 citationsRead paper
From Skill Extraction to Multistakeholder Recommendation: A Two-Stage Framework for Bias Governance in Skills-Based Job Matching
This study addresses bias in skill-oriented job matching systems that may undermine hiring fairness. The authors propose a unified two-stage governance framework: in the first stage, a chatbot extracts candidate skills and disentangles hard and soft constraint biases; in the second stage, preferences from candidates, employers, and regulators are integrated through a multi-stakeholder recommendation mechanism grounded in social choice theory. The framework incorporates distributional auditing, counterfactual testing, and dynamic fairness evaluation to enable auditable bias detection. It automatically triggers corrective actions or generates compliance reports when predefined fairness thresholds are violated, thereby significantly enhancing the system’s fairness, transparency, and regulatory alignment—such as with the EU AI Act.
0 citationsRead paper
Recent publications
Latest Papers
One Loop, Two Gains: Can Active Learning win the Lottery for Free?
研究通过在主动学习的每次迭代中整合权重剪枝方法，解决非稳定数据环境下模型稀疏化问题，从而提高计算效率。
0 citationsRead paper
Robustness and User-Perceived Value of Popularity Calibration in Music Recommendation: A User Study
This study investigates whether popularity calibration genuinely enhances user experience in music recommendation and examines its reliability across varying levels of user listening history and item familiarity. The authors construct three types of playlists—high-popularity, low-popularity, and calibrated—and employ a controlled naive recommender to generate personalized lists. Calibration is quantified using Jensen–Shannon divergence (JSD), and subjective user feedback is collected through controlled experiments. This work presents the first systematic validation of JSD’s stability with respect to real users’ perceived calibration. Results indicate that while users can discern differences in popularity, they do not exhibit a significant preference for calibrated recommendations. Moreover, computed popularity labels show only weak alignment with users’ subjective judgments, and the relationship between JSD and perceived calibration is significantly moderated by item familiarity, playlist composition, and the availability of historical interaction data.
0 citationsRead paper
COntExt: Towards Context-Aware Ontology Extension from Operational Metrics
This study addresses the high cost and low efficiency of current ontology extension practices, which heavily rely on manual effort due to the underutilization of domain knowledge implicitly embedded in operational metrics. To overcome this limitation, the work proposes the first context-aware ontology extension framework that systematically leverages structured operational metrics as a source of contextual information. The framework formulates ontology extension as three subtasks: parent class prediction, relationship type prediction, and data property assignment, and integrates natural language processing with knowledge graph techniques to generate automated suggestions. Experimental evaluation on four cybersecurity ontologies demonstrates that the proposed approach significantly outperforms baseline methods relying solely on ontology-internal context, particularly in relationship type prediction and data property assignment, thereby effectively reducing the cost of ontology maintenance.
0 citationsRead paper
From Skill Extraction to Multistakeholder Recommendation: A Two-Stage Framework for Bias Governance in Skills-Based Job Matching
This study addresses bias in skill-oriented job matching systems that may undermine hiring fairness. The authors propose a unified two-stage governance framework: in the first stage, a chatbot extracts candidate skills and disentangles hard and soft constraint biases; in the second stage, preferences from candidates, employers, and regulators are integrated through a multi-stakeholder recommendation mechanism grounded in social choice theory. The framework incorporates distributional auditing, counterfactual testing, and dynamic fairness evaluation to enable auditable bias detection. It automatically triggers corrective actions or generates compliance reports when predefined fairness thresholds are violated, thereby significantly enhancing the system’s fairness, transparency, and regulatory alignment—such as with the EU AI Act.
0 citationsRead paper