Task sequencing (TS) is one of the core open problems in Deep Learning, arising in a plethora of real-world domains, from robotic assembly lines to autonomous driving. Unfortunately, prior work has not convincingly demonstrated the generalization ability of meta-learned TS methods to solve new TS problems, given few initial demonstrations. In this paper, we demonstrate that deep neural networks can meta-learn over an infinite prior of synthetically generated TS problems and achieve a few-shot generalization. We meta-learn a transformer-based architecture over datasets of sequencing trajectories generated from a prior distribution that samples sequencing problems as paths in directed graphs. In a large-scale experiment, we provide ample empirical evidence that our meta-learned models discover optimal task sequences significantly quicker than non-meta-learned baselines.
A Memetic Walrus Algorithm with Expert-guided Strategy for Adaptive Curriculum Sequencing
Zhejiang Key Laboratory of Intelligent Education Technology and Application(浙江智能教育技术与应用重点实验室);Zhejiang Normal University(浙江师范大学);College of Education, Zhejiang Normal University(浙江师范大学教育学院);School of Education Science, Guangdong Polytechnic Normal University(广东 polytechnic 正规大学教育科学学院);School of Computer Science and Technology, Zhejiang Gongshang University(浙江工商大学计算机科学与技术学院)
Cascade Submodular Maximization: Question Selection and Sequencing in Online Personality Quiz
Naveen Jindal School of Management, University of Texas at Dallas(德克萨斯大学达拉斯分校纳文·金达尔管理学院);Department of Computer Science, University of Texas at Dallas(德克萨斯大学达拉斯分校计算机科学系)
scLLM-DSC: LLM-Knowledge Enhanced Cross-Modal Deep Structural Clustering for Single-Cell RNA Sequencing
Computer Network Information Center, Chinese Academy of Sciences(中国科学院计算机网络信息中心);University of Chinese Academy of Sciences(中国科学院大学);Hangzhou Institute for Advanced Study, University of Chinese Academy of Sciences(中国科学院大学杭州高等研究院);School of Computing and Information Technology, Great Bay University(大湾区大学计算机科学与技术学院);School of Engineering, Westlake University(西湖大学工学院)
GeneFormer: Learned Gene Compression using Transformer-based Context Modeling
Institute for AI Industry Research (AIR), Tsinghua University(清华大学人工智能产业研究院(AIR));Beijing University of Posts and Telecommunications(北京邮电大学);University of Science and Technology of China(中国科学技术大学)