Zobrazeno 1 - 10
of 6 877
pro vyhledávání: '"‐Yuan, Jun"'
Multi-task ranking models have become essential for modern real-world recommendation systems. While most recommendation researches focus on designing sophisticated models for specific scenarios, achieving performance improvement for multi-task rankin
Externí odkaz:
http://arxiv.org/abs/2410.05806
Autor:
Li, Zhen, Yang, Weikai, Yuan, Jun, Wu, Jing, Chen, Changjian, Ming, Yao, Yang, Fan, Zhang, Hui, Liu, Shixia
The high performance of tree ensemble classifiers benefits from a large set of rules, which, in turn, makes the models hard to understand. To improve interpretability, existing methods extract a subset of rules for approximation using model reduction
Externí odkaz:
http://arxiv.org/abs/2409.03164
Autor:
Yuan, Jun, Dasgupta, Aritra
Explainable AI~(XAI) methods such as SHAP can help discover feature attributions in black-box models. If the method reveals a significant attribution from a ``protected feature'' (e.g., gender, race) on the model output, the model is considered unfai
Externí odkaz:
http://arxiv.org/abs/2408.06509
The availability of coherent sources of higher order Poincare optical beams have opened up new opportunities for applications such as in the optical trapping of atoms and small particles, the manipulation of chirally-sensitive systems and in improved
Externí odkaz:
http://arxiv.org/abs/2407.00652
Publikováno v:
Journal of Software [2024]
In recent years, defect prediction techniques based on deep learning have become a prominent research topic in the field of software engineering. These techniques can identify potential defects without executing the code. However, existing approaches
Externí odkaz:
http://arxiv.org/abs/2405.10511
Predicting click-through rates (CTR) is a fundamental task for Web applications, where a key issue is to devise effective models for feature interactions. Current methodologies predominantly concentrate on modeling feature interactions within an indi
Externí odkaz:
http://arxiv.org/abs/2404.02249
TRIVEA: Transparent Ranking Interpretation using Visual Explanation of Black-Box Algorithmic Rankers
Ranking schemes drive many real-world decisions, like, where to study, whom to hire, what to buy, etc. Many of these decisions often come with high consequences. For example, a university can be deemed less prestigious if not featured in a top-k list
Externí odkaz:
http://arxiv.org/abs/2308.14622
Autor:
Wang, Jinpeng, Zeng, Ziyun, Wang, Yunxiao, Wang, Yuting, Lu, Xingyu, Li, Tianxiang, Yuan, Jun, Zhang, Rui, Zheng, Hai-Tao, Xia, Shu-Tao
The goal of sequential recommendation (SR) is to predict a user's potential interested items based on her/his historical interaction sequences. Most existing sequential recommenders are developed based on ID features, which, despite their widespread
Externí odkaz:
http://arxiv.org/abs/2308.11175
Autor:
Li, Yangning, Lu, Tingwei, Li, Yinghui, Yu, Tianyu, Huang, Shulin, Zheng, Hai-Tao, Zhang, Rui, Yuan, Jun
The Entity Set Expansion (ESE) task aims to expand a handful of seed entities with new entities belonging to the same semantic class. Conventional ESE methods are based on mono-modality (i.e., literal modality), which struggle to deal with complex en
Externí odkaz:
http://arxiv.org/abs/2307.14878
Autor:
Yuan, Jun, Zhang, Rui
Multi-task learning (MTL) has achieved great success in various research domains, such as CV, NLP and IR etc. Due to the complex and competing task correlation, naive training all tasks may lead to inequitable learning, i.e. some tasks are learned we
Externí odkaz:
http://arxiv.org/abs/2306.09373