Results 181 to 190 of about 3,537 (211)
Some of the next articles are maybe not open access.
Fourteenth ACM Conference on Recommender Systems, 2020
Multi-task learning (MTL) has been successfully applied to many recommendation applications. However, MTL models often suffer from performance degeneration with negative transfer due to the complex and competing task correlation in real-world recommender systems.
Hongyan Tang +3 more
openaire +1 more source
Multi-task learning (MTL) has been successfully applied to many recommendation applications. However, MTL models often suffer from performance degeneration with negative transfer due to the complex and competing task correlation in real-world recommender systems.
Hongyan Tang +3 more
openaire +1 more source
MTL-SLT: Multi-Task Learning for Spoken Language Tasks
Proceedings of the 4th Workshop on NLP for Conversational AI, 2022Zhiqi Huang 0001 +5 more
openaire +1 more source
JIT-MTL: Just-in-Time Defect Localization and Prediction with Multi-Task Learning
ACM Transactions on Software Engineering and MethodologySevere software defects can lead to significant issues and even result in substantial financial losses. As a result, automated code defect detection has garnered widespread attention. To fix these defects as soon as possible, J ust- I n-
Zongwen Shen +8 more
openaire +1 more source
Dr. MTL: Driver Recommendation using Federated Multi-Task Learning
2023 IEEE 98th Vehicular Technology Conference (VTC2023-Fall), 2023Jayant Vyas +3 more
openaire +1 more source
KG-MTL: Knowledge Graph Enhanced Multi-Task Learning for Molecular Interaction
IEEE Transactions on Knowledge and Data Engineering, 2022Tengfei Ma 0002 +4 more
openaire +1 more source
ACM Transactions on Software Engineering and Methodology
Fault localization (FL) and automated program repair (APR) are two main tasks of automatic software debugging. Compared with traditional methods, deep learning-based approaches have been demonstrated to achieve better performance in FL and APR tasks. However, the existing deep learning-based FL methods ignore the deep semantic features or only consider
Xu Wang 0007 +7 more
openaire +1 more source
Fault localization (FL) and automated program repair (APR) are two main tasks of automatic software debugging. Compared with traditional methods, deep learning-based approaches have been demonstrated to achieve better performance in FL and APR tasks. However, the existing deep learning-based FL methods ignore the deep semantic features or only consider
Xu Wang 0007 +7 more
openaire +1 more source
CFS-MTL: A Causal Feature Selection Mechanism for Multi-task Learning via Pseudo-intervention
Proceedings of the 31st ACM International Conference on Information & Knowledge Management, 2022Zhongde Chen +8 more
openaire +1 more source
LA-MTL: Latency-Aware Automated Multi-Task Learning
2025 62nd ACM/IEEE Design Automation Conference (DAC)Shambhavi Balamuthu Sampath +10 more
openaire +1 more source
Plasticity-Stability Preserving Multi-Task Learning for Remote Sensing Image Retrieval
IEEE Transactions on Geoscience and Remote Sensing, 2022Gençer Sumbul, Begum Demir
exaly