no code implementations • ICML 2020 • Yuanyu Wan, Wei-Wei Tu, Lijun Zhang
To deal with complicated constraints via locally light computation in distributed online learning, recent study has presented a projection-free algorithm called distributed online conditional gradient (D-OCG), and achieved an $O(T^{3/4})$ regret bound, where $T$ is the number of prediction rounds.
no code implementations • 26 Feb 2024 • Junzhe Chen, Xuming Hu, Shuodi Liu, Shiyu Huang, Wei-Wei Tu, Zhaofeng He, Lijie Wen
Recent advancements in large language models (LLMs) have revealed their potential for achieving autonomous agents possessing human-level intelligence.
1 code implementation • 20 Dec 2023 • Shiyu Huang, Wentse Chen, Yiwen Sun, Fuqing Bie, Wei-Wei Tu
We present OpenRL, an advanced reinforcement learning (RL) framework designed to accommodate a diverse array of tasks, from single-agent challenges to complex multi-agent systems.
1 code implementation • 5 Sep 2023 • Haixu Song, Shiyu Huang, Yinpeng Dong, Wei-Wei Tu
The rise of deepfake images, especially of well-known personalities, poses a serious threat to the dissemination of authentic information.
no code implementations • 31 May 2023 • Lijun Zhang, Wei-Wei Tu
While traditional distributionally robust optimization (DRO) aims to minimize the maximal risk over a set of distributions, Agarwal and Zhang (2022) recently proposed a variant that replaces risk with excess risk.
1 code implementation • 15 Feb 2023 • Fanqi Lin, Shiyu Huang, Tim Pearce, Wenze Chen, Wei-Wei Tu
Multi-agent football poses an unsolved challenge in AI research.
no code implementations • 9 Feb 2023 • Sijia Chen, Yu-Jie Zhang, Wei-Wei Tu, Peng Zhao, Lijun Zhang
Inspired by their work, we investigate the theoretical guarantees of optimistic online mirror descent (OMD) for the SEA model.
1 code implementation • 8 Feb 2023 • Xinyi Yang, Shiyu Huang, Yiwen Sun, Yuxiang Yang, Chao Yu, Wei-Wei Tu, Huazhong Yang, Yu Wang
Goal-conditioned hierarchical reinforcement learning (HRL) provides a promising direction to tackle this challenge by introducing a hierarchical structure to decompose the search space, where the low-level policy predicts primitive actions in the guidance of the goals derived from the high-level policy.
Hierarchical Reinforcement Learning Multi-agent Reinforcement Learning +2
1 code implementation • 12 Jul 2022 • Wentse Chen, Shiyu Huang, Yuan Chiang, Tim Pearce, Wei-Wei Tu, Ting Chen, Jun Zhu
We propose Diversity-Guided Policy Optimization (DGPO), an on-policy algorithm that discovers multiple strategies for solving a given task.
no code implementations • 26 May 2022 • Tong Wei, Qian-Yu Liu, Jiang-Xin Shi, Wei-Wei Tu, Lan-Zhe Guo
TRAS transforms the imbalanced pseudo-label distribution of a traditional SSL model via a delicate function to enhance the supervisory signals for minority classes.
no code implementations • 11 Apr 2022 • Yuanyu Wan, Yibo Wang, Chang Yao, Wei-Wei Tu, Lijun Zhang
Projection-free online learning, which eschews the projection operation via less expensive computations such as linear optimization (LO), has received much interest recently due to its efficiency in handling high-dimensional problems with complex constraints.
1 code implementation • 6 Apr 2022 • Zhen Xu, Lanning Wei, Huan Zhao, Rex Ying, Quanming Yao, Wei-Wei Tu, Isabelle Guyon
Researchers naturally adopt Automated Machine Learning on Graph Learning, aiming to reduce the human effort and achieve generally top-performing GNNs, but their methods focus more on the architecture search.
1 code implementation • 7 Mar 2022 • German Barquero, Johnny Núñez, Zhen Xu, Sergio Escalera, Wei-Wei Tu, Isabelle Guyon, Cristina Palmero
In this work, we present the first systematic comparison of state-of-the-art approaches for behavior forecasting.
no code implementations • 4 Mar 2022 • German Barquero, Johnny Núñez, Sergio Escalera, Zhen Xu, Wei-Wei Tu, Isabelle Guyon, Cristina Palmero
Non-verbal social human behavior forecasting has increasingly attracted the interest of the research community in recent years.
1 code implementation • 4 Feb 2022 • Joseph Pedersen, Rafael Muñoz-Gómez, Jiangnan Huang, Haozhe Sun, Wei-Wei Tu, Isabelle Guyon
In both cases classification accuracy or error rate are used as the metric: Utility is evaluated with the classification accuracy of the Defender model; Privacy is evaluated with the membership prediction error of a so-called "Leave-Two-Unlabeled" LTU Attacker, having access to all of the Defender and Reserved data, except for the membership label of one sample from each.
2 code implementations • 17 Jan 2022 • Haozhe Sun, Wei-Wei Tu, Isabelle Guyon
We introduce OmniPrint, a synthetic data generator of isolated printed characters, geared toward machine learning research.
2 code implementations • 12 Oct 2021 • Zhen Xu, Sergio Escalera, Isabelle Guyon, Adrien Pavão, Magali Richard, Wei-Wei Tu, Quanming Yao, Huan Zhao
A public instance of Codabench (https://www. codabench. org/) is open to everyone, free of charge, and allows benchmark organizers to compare fairly submissions, under the same setting (software, hardware, data, algorithms), with custom protocols and data formats.
no code implementations • 26 Aug 2021 • Tong Wei, Jiang-Xin Shi, Wei-Wei Tu, Yu-Feng Li
To overcome this limitation, we establish a new prototypical noise detection method by designing a distance-based metric that is resistant to label noise.
Ranked #25 on Image Classification on mini WebVision 1.0
1 code implementation • 16 Aug 2021 • Mingcheng Chen, Zhenghui Wang, Zhiyun Zhao, Weinan Zhang, Xiawei Guo, Jian Shen, Yanru Qu, Jieli Lu, Min Xu, Yu Xu, Tiange Wang, Mian Li, Wei-Wei Tu, Yong Yu, Yufang Bi, Weiqing Wang, Guang Ning
To tackle the above challenges, we employ gradient boosting decision trees (GBDT) to handle data heterogeneity and introduce multi-task learning (MTL) to solve data insufficiency.
1 code implementation • 28 Jul 2021 • Zhen Xu, Wei-Wei Tu, Isabelle Guyon
Driven by business scenarios, we organized the first Automated Time Series Regression challenge (AutoSeries) for the WSDM Cup 2020.
1 code implementation • 31 Mar 2021 • Jingsong Wang, Yuxuan He, Chunyu Zhao, Qijie Shao, Wei-Wei Tu, Tom Ko, Hung-Yi Lee, Lei Xie
Auto-KWS 2021 challenge calls for automated machine learning (AutoML) solutions to automate the process of applying machine learning to a customized keyword spotting task.
no code implementations • 21 Mar 2021 • Yuanyu Wan, Wei-Wei Tu, Lijun Zhang
Specifically, we first extend the delayed variant of OGD for strongly convex functions, and establish a better regret bound of $O(d\log T)$, where $d$ is the maximum delay.
no code implementations • 20 Mar 2021 • Yuanyu Wan, Guanghui Wang, Wei-Wei Tu, Lijun Zhang
In this paper, we propose an improved variant of D-OCG, namely D-BOCG, which can attain the same $O(T^{3/4})$ regret bound with only $O(\sqrt{T})$ communication rounds for convex losses, and a better regret bound of $O(T^{2/3}(\log T)^{1/3})$ with fewer $O(T^{1/3}(\log T)^{2/3})$ communication rounds for strongly convex losses.
no code implementations • 1 Jan 2021 • Tong Wei, Wei-Wei Tu, Yu-Feng Li
Extreme multi-label learning (XML) works to annotate objects with relevant labels from an extremely large label set.
no code implementations • 25 Oct 2020 • Jingsong Wang, Tom Ko, Zhen Xu, Xiawei Guo, Souxiang Liu, Wei-Wei Tu, Lei Xie
The AutoSpeech challenge calls for automated machine learning (AutoML) solutions to automate the process of applying machine learning to speech processing tasks.
no code implementations • 20 May 2020 • Yuanfei Luo, Hao Zhou, Wei-Wei Tu, Yuqiang Chen, Wenyuan Dai, Qiang Yang
As a result, the intra-field information and the non-linear interactions between those operations (e. g. neural network and factorization machines) are ignored.
no code implementations • 24 Jul 2019 • Jorge G. Madrid, Hugo Jair Escalante, Eduardo F. Morales, Wei-Wei Tu, Yang Yu, Lisheng Sun-Hosoya, Isabelle Guyon, Michele Sebag
We extendAuto-Sklearn with sound and intuitive mechanisms that allow it to cope with this sort ofproblems.
no code implementations • NeurIPS 2021 • Lijun Zhang, Guanghui Wang, Wei-Wei Tu, Zhi-Hua Zhou
Along this line of research, this paper presents the first universal algorithm for minimizing the adaptive regret of convex functions.
2 code implementations • 30 May 2019 • Quanming Yao, Ju Xu, Wei-Wei Tu, Zhanxing Zhu
Recently, DARTS, which constructs a differentiable search space and then optimizes it by gradient descent, can obtain high-performance architecture and reduces the search time to several days.
1 code implementation • ICLR 2020 • Guanghui Wang, Shiyin Lu, Wei-Wei Tu, Lijun Zhang
In this paper, we give an affirmative answer by developing a variant of Adam (referred to as SAdam) which achieves a data-dependant $O(\log T)$ regret bound for strongly convex functions.
no code implementations • 29 Apr 2019 • Yuanfei Luo, Mengshuo Wang, Hao Zhou, Quanming Yao, Wei-Wei Tu, Yuqiang Chen, Qiang Yang, Wenyuan Dai
Feature crossing captures interactions among categorical features and is useful to enhance learning from tabular data in real-world businesses.
no code implementations • 12 Mar 2019 • Hugo Jair Escalante, Wei-Wei Tu, Isabelle Guyon, Daniel L. Silver, Evelyne Viegas, Yuqiang Chen, Wenyuan Dai, Qiang Yang
We organized a competition on Autonomous Lifelong Machine Learning with Drift that was part of the competition program of NeurIPS 2018.