no code implementations • 20 Jun 2024 • Yu-Neng Chuang, Songchen Li, Jiayi Yuan, Guanchu Wang, Kwei-Herng Lai, Leisheng Yu, Sirui Ding, Chia-Yuan Chang, Qiaoyu Tan, Daochen Zha, Xia Hu
Moreover, we propose \emph{time series prompt}, a novel statistical prompting strategy tailored to time series data.
no code implementations • 2 Oct 2023 • Chia-Yuan Chang, Yu-Neng Chuang, Zhimeng Jiang, Kwei-Herng Lai, Anxiao Jiang, Na Zou
In real-world applications, machine learning models often become obsolete due to shifts in the joint distribution arising from underlying temporal trends, a phenomenon known as the "concept drift".
1 code implementation • 4 Sep 2023 • Yu-Neng Chuang, Guanchu Wang, Chia-Yuan Chang, Kwei-Herng Lai, Daochen Zha, Ruixiang Tang, Fan Yang, Alfredo Costilla Reyes, Kaixiong Zhou, Xiaoqian Jiang, Xia Hu
The exponential growth in scholarly publications necessitates advanced tools for efficient article retrieval, especially in interdisciplinary fields where diverse terminologies are used to describe similar research.
no code implementations • 2 Sep 2023 • Huiyuan Chen, Kaixiong Zhou, Kwei-Herng Lai, Chin-Chia Michael Yeh, Yan Zheng, Xia Hu, Hao Yang
To address the gradient mismatch problem in STE, we further consider the quantized errors and its second-order derivatives for better stability.
no code implementations • 28 Aug 2023 • Kwei-Herng Lai, Daochen Zha, Huiyuan Chen, Mangesh Bendre, Yuzhong Chen, Mahashweta Das, Hao Yang, Xia Hu
Imbalanced datasets are commonly observed in various real-world applications, presenting significant challenges in training classifiers.
no code implementations • 9 Jul 2023 • Chia-Yuan Chang, Yu-Neng Chuang, Kwei-Herng Lai, Xiaotian Han, Xia Hu, Na Zou
Those studies face challenges, either in inaccurate predictions of sensitive attributes or the need to mitigate unequal distribution of manually defined non-sensitive attributes related to bias.
no code implementations • 15 Apr 2023 • Kwei-Herng Lai, Lan Wang, Huiyuan Chen, Kaixiong Zhou, Fei Wang, Hao Yang, Xia Hu
We formulate context sampling into the Markov decision process and exploit deep reinforcement learning to optimize the time series domain adaptation process via context sampling and design a tailored reward function to generate domain-invariant features that better align two domains for anomaly detection.
10 code implementations • 17 Mar 2023 • Daochen Zha, Zaid Pervaiz Bhat, Kwei-Herng Lai, Fan Yang, Zhimeng Jiang, Shaochen Zhong, Xia Hu
Artificial Intelligence (AI) is making a profound impact in almost every domain.
1 code implementation • 12 Jan 2023 • Daochen Zha, Zaid Pervaiz Bhat, Kwei-Herng Lai, Fan Yang, Xia Hu
The role of data in building AI systems has recently been significantly magnified by the emerging concept of data-centric AI (DCAI), which advocates a fundamental shift from model advancements to ensuring data quality and reliability.
no code implementations • 26 Nov 2022 • Yu-Neng Chuang, Kwei-Herng Lai, Ruixiang Tang, Mengnan Du, Chia-Yuan Chang, Na Zou, Xia Hu
Knowledge graph data are prevalent in real-world applications, and knowledge graph neural networks (KGNNs) are essential techniques for knowledge graph representation learning.
1 code implementation • 5 Oct 2022 • Daochen Zha, Louis Feng, Qiaoyu Tan, Zirui Liu, Kwei-Herng Lai, Bhargav Bhushanam, Yuandong Tian, Arun Kejariwal, Xia Hu
Although prior work has explored learning-based approaches for the device placement of computational graphs, embedding table placement remains to be a challenging problem because of 1) the operation fusion of embedding tables, and 2) the generalizability requirement on unseen placement tasks with different numbers of tables and/or devices.
2 code implementations • 26 Aug 2022 • Daochen Zha, Kwei-Herng Lai, Qiaoyu Tan, Sirui Ding, Na Zou, Xia Hu
Motivated by this, we investigate developing a learning-based over-sampling algorithm to optimize the classification performance, which is a challenging task because of the huge and hierarchical decision space.
Hierarchical Reinforcement Learning reinforcement-learning +2
1 code implementation • 5 Jan 2022 • Daochen Zha, Kwei-Herng Lai, Kaixiong Zhou, Xia Hu
Prior work has approached TSC from two major directions: (1) similarity-based methods that classify time-series based on the nearest neighbors, and (2) deep learning models that directly learn the representations for classification in a data-driven manner.
1 code implementation • 9 Aug 2021 • Daochen Zha, Zaid Pervaiz Bhat, Yi-Wei Chen, Yicheng Wang, Sirui Ding, Jiaben Chen, Kwei-Herng Lai, Mohammad Qazim Bhat, Anmoll Kumar Jain, Alfredo Costilla Reyes, Na Zou, Xia Hu
Action recognition is an important task for video understanding with broad applications.
1 code implementation • 10 Jun 2021 • Daochen Zha, Kwei-Herng Lai, Kaixiong Zhou, Xia Hu
Supervised regression to demonstrations has been demonstrated to be a stable way to train deep policy networks.
1 code implementation • 18 Sep 2020 • Kwei-Herng Lai, Daochen Zha, Guanchu Wang, Junjie Xu, Yue Zhao, Devesh Kumar, Yile Chen, Purav Zumkhawaka, Minyang Wan, Diego Martinez, Xia Hu
We present TODS, an automated Time Series Outlier Detection System for research and industrial applications.
1 code implementation • 16 Sep 2020 • Daochen Zha, Kwei-Herng Lai, Mingyang Wan, Xia Hu
Specifically, existing strategies have been focused on making the top instances more likely to be anomalous based on the feedback.
1 code implementation • 26 Jun 2020 • Kwei-Herng Lai, Daochen Zha, Kaixiong Zhou, Xia Hu
It is a challenging task to develop an effective aggregation strategy for each node, given complex graphs and sparse features.
1 code implementation • 7 Jun 2020 • Kwei-Herng Lai, Daochen Zha, Yuening Li, Xia Hu
In this work, we introduce dual policy distillation(DPD), a student-student framework in which two learners operate on the same environment to explore different perspectives of the environment and extract knowledge from each other to enhance their learning.
9 code implementations • 10 Oct 2019 • Daochen Zha, Kwei-Herng Lai, Yuanpu Cao, Songyi Huang, Ruzhe Wei, Junyu Guo, Xia Hu
The goal of RLCard is to bridge reinforcement learning and imperfect information games, and push forward the research of reinforcement learning in domains with multiple agents, large state and action space, and sparse reward.
no code implementations • 19 Jun 2019 • Daochen Zha, Kwei-Herng Lai, Kaixiong Zhou, Xia Hu
Experience replay enables reinforcement learning agents to memorize and reuse past experiences, just as humans replay memories for the situation at hand.
no code implementations • 28 Aug 2018 • Chih-Chun Hsia, Kwei-Herng Lai, Yi-An Chen, Chuan-Ju Wang, Ming-Feng Tsai
Image perception is one of the most direct ways to provide contextual information about a user concerning his/her surrounding environment; hence images are a suitable proxy for contextual recommendation.
no code implementations • 28 Aug 2018 • Kwei-Herng Lai, Ting-Hsiang Wang, Heng-Yu Chi, Yi-An Chen, Ming-Feng Tsai, Chuan-Ju Wang
Cross-domain collaborative filtering (CF) aims to alleviate data sparsity in single-domain CF by leveraging knowledge transferred from related domains.