Search

Your search keyword '"Lin, Gang"' showing total 2,074 results
Start Over Author "Lin, Gang" Publication Year Range Last 50 years
2,074 results on '"Lin, Gang"'

7. Leveraging Logical Rules in Knowledge Editing: A Cherry on the Top

Author

Cheng, Keyuan, Ali, Muhammad Asif, Yang, Shu, Lin, Gang, Zhai, Yuxuan, Fei, Haoyang, Xu, Ke, Yu, Lu, Hu, Lijie, and Wang, Di

Subjects
Computer Science - Computation and Language, Computer Science - Artificial Intelligence, Computer Science - Machine Learning
Abstract

Multi-hop Question Answering (MQA) under knowledge editing (KE) is a key challenge in Large Language Models (LLMs). While best-performing solutions in this domain use a plan and solve paradigm to split a question into sub-questions followed by response generation, we claim that this approach is sub-optimal as it fails for hard to decompose questions, and it does not explicitly cater to correlated knowledge updates resulting as a consequence of knowledge edits. This has a detrimental impact on the overall consistency of the updated knowledge. To address these issues, in this paper, we propose a novel framework named RULE-KE, i.e., RULE based Knowledge Editing, which is a cherry on the top for augmenting the performance of all existing MQA methods under KE. Specifically, RULE-KE leverages rule discovery to discover a set of logical rules. Then, it uses these discovered rules to update knowledge about facts highly correlated with the edit. Experimental evaluation using existing and newly curated datasets (i.e., RKE-EVAL) shows that RULE-KE helps augment both performances of parameter-based and memory-based solutions up to 92% and 112.9%, respectively., Comment: 18 pages

Published
2024

11. Multi-hop Question Answering under Temporal Knowledge Editing

Author

Cheng, Keyuan, Lin, Gang, Fei, Haoyang, zhai, Yuxuan, Yu, Lu, Ali, Muhammad Asif, Hu, Lijie, and Wang, Di

Subjects
Computer Science - Computation and Language, Computer Science - Artificial Intelligence, Computer Science - Machine Learning
Abstract

Multi-hop question answering (MQA) under knowledge editing (KE) has garnered significant attention in the era of large language models. However, existing models for MQA under KE exhibit poor performance when dealing with questions containing explicit temporal contexts. To address this limitation, we propose a novel framework, namely TEMPoral knowLEdge augmented Multi-hop Question Answering (TEMPLE-MQA). Unlike previous methods, TEMPLE-MQA first constructs a time-aware graph (TAG) to store edit knowledge in a structured manner. Then, through our proposed inference path, structural retrieval, and joint reasoning stages, TEMPLE-MQA effectively discerns temporal contexts within the question query. Experiments on benchmark datasets demonstrate that TEMPLE-MQA significantly outperforms baseline models. Additionally, we contribute a new dataset, namely TKEMQA, which serves as the inaugural benchmark tailored specifically for MQA with temporal scopes., Comment: 23 pages

Published
2024

13. Explaining Differences in Autism Detection Timing: Age of Diagnosis and Associated Individual and Socio-Familial Factors in Chinese Children

Author

Ling Li Leng, Yue Wen Zhu, and Lin Gang Zhou

Abstract

The timing of autism spectrum disorder detection in research and clinical practice is characterised by substantial heterogeneity ranging from infancy to school age. In this study, we examined the age of diagnosis and its associated individual and socio-familial factors in Chinese children diagnosed with autism spectrum disorder. A sample of 1235 autism spectrum disorder children from 132 rehabilitation organisations in Shenzhen was investigated in 2021. We found a mean age of diagnosis of 31.4 ± 12.7 months and a median of 30.0 months. Although 71.7% of the children received their diagnosis between 25 and 36 months of age, and 13.3% were diagnosed early (?24 months), 15.1% did not have their symptoms detected until preschool or later years (>36 months). The diagnosis was likely delayed (>36 months) if the children were older, were less severe and presented with no intellectual impairment. The odds of delayed autism spectrum disorder diagnosis were more than 9 times higher among migrant autism spectrum disorder children than those with local household registrations. The study underscores the importance of identifying culturally sensitive socio-economic determinants in autism spectrum disorder detection in addition to clinical factors, as the former are likely to affect the quality of life of many autism spectrum disorder children and their families.

Published
2024
Full Text
View/download PDF

15. Thermal Rectification Effect of Composite Cylinder Based on Interface Thermal Resistance

Author

Xie, Jianxiang, Chen, Yan, Fu, Zhichao, Lin, Gang, Chaari, Fakher, Series Editor, Gherardini, Francesco, Series Editor, Ivanov, Vitalii, Series Editor, Haddar, Mohamed, Series Editor, Cavas-Martínez, Francisco, Editorial Board Member, di Mare, Francesca, Editorial Board Member, Kwon, Young W., Editorial Board Member, Tolio, Tullio A. M., Editorial Board Member, Trojanowska, Justyna, Editorial Board Member, Schmitt, Robert, Editorial Board Member, Xu, Jinyang, Editorial Board Member, and Mo, John P. T., editor

Published
2024
Full Text
View/download PDF

17. Research on Construction and Application of Knowledge Graph for Coal Mine Safety Production Specifications

Author

Cao, Gong, Huang, Cui, Zhao, Jiayue, Gao, Yongzhe, Lin, Gang, Han, Wei, Angrisani, Leopoldo, Series Editor, Arteaga, Marco, Series Editor, Chakraborty, Samarjit, Series Editor, Chen, Jiming, Series Editor, Chen, Shanben, Series Editor, Chen, Tan Kay, Series Editor, Dillmann, Rüdiger, Series Editor, Duan, Haibin, Series Editor, Ferrari, Gianluigi, Series Editor, Ferre, Manuel, Series Editor, Jabbari, Faryar, Series Editor, Jia, Limin, Series Editor, Kacprzyk, Janusz, Series Editor, Khamis, Alaa, Series Editor, Kroeger, Torsten, Series Editor, Li, Yong, Series Editor, Liang, Qilian, Series Editor, Martín, Ferran, Series Editor, Ming, Tan Cher, Series Editor, Minker, Wolfgang, Series Editor, Misra, Pradeep, Series Editor, Mukhopadhyay, Subhas, Series Editor, Ning, Cun-Zheng, Series Editor, Nishida, Toyoaki, Series Editor, Oneto, Luca, Series Editor, Panigrahi, Bijaya Ketan, Series Editor, Pascucci, Federica, Series Editor, Qin, Yong, Series Editor, Seng, Gan Woon, Series Editor, Speidel, Joachim, Series Editor, Veiga, Germano, Series Editor, Wu, Haitao, Series Editor, Zamboni, Walter, Series Editor, Zhang, Junjie James, Series Editor, Tan, Kay Chen, Series Editor, Wang, Wei, editor, Mu, Jiasong, editor, Liu, Xin, editor, and Na, Zhenyu Na, editor

Published
2024
Full Text
View/download PDF

18. Coal Mine Risk Classification Prediction Model Based on BERT

Author

Lin, Gang, Li, Tao, Cao, Gong, Han, Wei, Angrisani, Leopoldo, Series Editor, Arteaga, Marco, Series Editor, Chakraborty, Samarjit, Series Editor, Chen, Jiming, Series Editor, Chen, Shanben, Series Editor, Chen, Tan Kay, Series Editor, Dillmann, Rüdiger, Series Editor, Duan, Haibin, Series Editor, Ferrari, Gianluigi, Series Editor, Ferre, Manuel, Series Editor, Jabbari, Faryar, Series Editor, Jia, Limin, Series Editor, Kacprzyk, Janusz, Series Editor, Khamis, Alaa, Series Editor, Kroeger, Torsten, Series Editor, Li, Yong, Series Editor, Liang, Qilian, Series Editor, Martín, Ferran, Series Editor, Ming, Tan Cher, Series Editor, Minker, Wolfgang, Series Editor, Misra, Pradeep, Series Editor, Mukhopadhyay, Subhas, Series Editor, Ning, Cun-Zheng, Series Editor, Nishida, Toyoaki, Series Editor, Oneto, Luca, Series Editor, Panigrahi, Bijaya Ketan, Series Editor, Pascucci, Federica, Series Editor, Qin, Yong, Series Editor, Seng, Gan Woon, Series Editor, Speidel, Joachim, Series Editor, Veiga, Germano, Series Editor, Wu, Haitao, Series Editor, Zamboni, Walter, Series Editor, Zhang, Junjie James, Series Editor, Tan, Kay Chen, Series Editor, Wang, Wei, editor, Mu, Jiasong, editor, Liu, Xin, editor, and Na, Zhenyu Na, editor

Published
2024
Full Text
View/download PDF

20. Effects of dietary supplementation with mannan-rich oligosaccharides and solid-state fermented Aspergillus niger on the growth performance of juvenile Asian seabass, Lates calcarifer

Author

Felix Gary Petol, Lyons Philip, Wong Henry, Lin Gang, Noordin Noordiyana Mat, Sung Yeong Yik, Danish-Daniel Muhd, and Wong Li Lian

Subjects
aquafeed, dietary supplement, growth promoter, nutrient utilization, Aquaculture. Fisheries. Angling, SH1-691
Abstract

Feed additives are gaining popularity as dietary supplements with the potential to support growth, immune competence, and the general health of aquaculture species. This study aimed to evaluate growth performance and feed utilization in juvenile Asian seabass, Lates calcarifer, fed experimental diets containing enzymes derived from the solid-state fermentation (SSF) of Aspergillus niger and mannan oligosaccharides (MOS), both individually and in combination. Fish were fed six experimental diets: control (no additives), SSF (0.025% & 0.05%), MOS (0.1% & 0.2%), and combined SSF (0.025%) + MOS (0.05%). The feeding trial was conducted for ten weeks in triplicate for each experimental diet consisting of 51 fish in 120 L tanks. Following the collection of growth performance metrics, proximate analysis of muscle and feces samples was performed, and all datasets were statistically analyzed with One-way ANOVA. The results showed that the highest specific growth rate (SGR = 1.29%) and lowest feed conversion rate (FCR = 1.0) were obtained by fish fed the diet supplemented with SSF (0.025%) + MOS (0.05%). The synergistic effects of SSF as an exogenous enzyme source and MOS in supporting gut health likely facilitated enhanced nutrient digestibility and absorption, which supported the growth of juvenile Asian seabass.

Published
2024
Full Text
View/download PDF

22. Susceptibilities of Ugandan Plasmodium falciparum Isolates to Proteasome Inhibitors

Author

Garg, Shreeya, Kreutzfeld, Oriana, Chelebieva, Sevil, Tumwebaze, Patrick K, Byaruhanga, Oswald, Okitwi, Martin, Orena, Stephen, Katairo, Thomas, Nsobya, Samuel L, Conrad, Melissa D, Aydemir, Ozkan, Legac, Jennifer, Gould, Alexandra E, Bayles, Brett R, Bailey, Jeffrey A, Duffey, Maelle, Lin, Gang, Kirkman, Laura A, Cooper, Roland A, and Rosenthal, Philip J

Subjects
Medical Microbiology, Biomedical and Clinical Sciences, Clinical Sciences, Biotechnology, Malaria, Rare Diseases, Infectious Diseases, Vector-Borne Diseases, Genetics, Development of treatments and therapeutic interventions, 5.1 Pharmaceuticals, Good Health and Well Being, Humans, Antimalarials, Asparagine, Drug Resistance, Ethylenediamines, Malaria, Falciparum, Peptides, Plasmodium falciparum, Proteasome Endopeptidase Complex, Proteasome Inhibitors, Uganda, antimalarial agents, proteasome, Microbiology, Pharmacology and Pharmaceutical Sciences, Medical microbiology, Pharmacology and pharmaceutical sciences
Abstract

The proteasome is a promising target for antimalarial chemotherapy. We assessed ex vivo susceptibilities of fresh Plasmodium falciparum isolates from eastern Uganda to seven proteasome inhibitors: two asparagine ethylenediamines, two macrocyclic peptides, and three peptide boronates; five had median IC50 values

Published
2022

44. QISTA-Net: DNN Architecture to Solve $\ell_q$-norm Minimization Problem and Image Compressed Sensing

Author

Lin, Gang-Xuan, Hu, Shih-Wei, and Lu, Chun-Shien

Subjects
Computer Science - Computer Vision and Pattern Recognition, Computer Science - Machine Learning, Electrical Engineering and Systems Science - Image and Video Processing
Abstract

In this paper, we reformulate the non-convex $\ell_q$-norm minimization problem with $q\in(0,1)$ into a 2-step problem, which consists of one convex and one non-convex subproblems, and propose a novel iterative algorithm called QISTA ($\ell_q$-ISTA) to solve the $\left(\ell_q\right)$-problem. By taking advantage of deep learning in accelerating optimization algorithms, together with the speedup strategy that using the momentum from all previous layers in the network, we propose a learning-based method, called QISTA-Net-s, to solve the sparse signal reconstruction problem. Extensive experimental comparisons demonstrate that the QISTA-Net-s yield better reconstruction qualities than state-of-the-art $\ell_1$-norm optimization (plus learning) algorithms even if the original sparse signal is noisy. On the other hand, based on the network architecture associated with QISTA, with considering the use of convolution layers, we proposed the QISTA-Net-n for solving the image CS problem, and the performance of the reconstruction still outperforms most of the state-of-the-art natural images reconstruction methods. QISTA-Net-n is designed in unfolding QISTA and adding the convolutional operator as the dictionary. This makes QISTA-Net-s interpretable. We provide complete experimental results that QISTA-Net-s and QISTA-Net-n contribute the better reconstruction performance than the competing.

Published
2020

Catalog

Books, media, physical & digital resources
See catalog results