no code implementations • 6 Jun 2024 • Kun Song, Zhiquan Tan, Bochao Zou, Huimin Ma, Weiran Huang
In this paper, we use matrix information theory as an analytical tool to analyze the dynamics of the information interplay between data representations and classification head vectors in the supervised learning process.
no code implementations • 29 May 2024 • Yichen Wen, Zhiquan Tan, Kaipeng Zheng, Chuanlong Xie, Weiran Huang
In this work, we fill this gap by establishing theoretical performance guarantees, which reveal how the performance of the model is bounded by training losses of previous tasks in the contrastive continual learning framework.
1 code implementation • 12 Feb 2024 • Kang Zhang, Osamu Yoshie, Weiran Huang
To address these issues, we introduce BreakGPT, the first large language model for financial breakout detection.
no code implementations • 10 Feb 2024 • Di Zhang, Wei Liu, Qian Tan, Jingdan Chen, Hang Yan, Yuliang Yan, Jiatong Li, Weiran Huang, Xiangyu Yue, Wanli Ouyang, Dongzhan Zhou, Shufei Zhang, Mao Su, Han-sen Zhong, Yuqiang Li
However, the community lacks an LLM specifically designed for chemistry.
no code implementations • 1 Feb 2024 • Zhiquan Tan, Chenghai Li, Weiran Huang
This paper investigates the information encoded in the embeddings of large language models (LLMs).
1 code implementation • 30 Jan 2024 • Lai Wei, Zhiquan Tan, Chenghai Li, Jindong Wang, Weiran Huang
Large language models (LLMs) have revolutionized the field of natural language processing, extending their strong capabilities into multi-modal domains.
2 code implementations • 28 Dec 2023 • Zhengqing Yuan, Zhaoxu Li, Weiran Huang, Yanfang Ye, Lichao Sun
In recent years, multimodal large language models (MLLMs) such as GPT-4V have demonstrated remarkable advancements, excelling in a variety of vision-language tasks.
no code implementations • 12 Dec 2023 • Kaipeng Zheng, Weiran Huang, Lichao Sun
Our solution secures the 1st place in the MedFMC challenge.
1 code implementation • 25 Nov 2023 • Xiuyuan Chen, Yuan Lin, Yuchen Zhang, Weiran Huang
By using instance-specific rules as prompt, GPT-4, as an automatic evaluator, can achieve a stable evaluation accuracy of around 97. 0\%, comparable to the 94. 9\% - 97. 5\% accuracy of a human evaluator.
no code implementations • 11 Nov 2023 • Zhiquan Tan, Weiran Huang
Recently, an interesting phenomenon called grokking has gained much attention, where generalization occurs long after the models have initially overfitted the training data.
no code implementations • 26 Oct 2023 • Zhiquan Tan, Kaipeng Zheng, Weiran Huang
Semi-supervised learning has made remarkable strides by effectively utilizing a limited amount of labeled data while capitalizing on the abundant information present in unlabeled data.
2 code implementations • 29 Sep 2023 • Zhiquan Tan, Jingqin Yang, Weiran Huang, Yang Yuan, Yifan Zhang
In this paper, we conduct a comprehensive analysis of two dual-branch (Siamese architecture) self-supervised learning approaches, namely Barlow Twins and spectral contrastive learning, through the lens of matrix mutual information.
3 code implementations • 23 Aug 2023 • Lai Wei, Zihao Jiang, Weiran Huang, Lichao Sun
To achieve this, we first propose several metrics to access the quality of multimodal instruction data.
no code implementations • 9 Jul 2023 • Zihao Jiang, Yunkai Dang, Dong Pang, Huishuai Zhang, Weiran Huang
Few-shot learning aims to train models that can be generalized to novel classes with only a few samples.
no code implementations • 7 Jun 2023 • Jingyi Cui, Weiran Huang, Yifei Wang, Yisen Wang
Therefore, to explore the mechanical differences between semi-supervised and noisy-labeled information in helping contrastive learning, we establish a unified theoretical framework of contrastive learning under weak supervision.
3 code implementations • 27 May 2023 • Yifan Zhang, Zhiquan Tan, Jingqin Yang, Weiran Huang, Yang Yuan
Inspired by this framework, we introduce Matrix-SSL, a novel approach that leverages matrix information theory to interpret the maximum entropy encoding loss as matrix uniformity loss.
Ranked #1 on Contrastive Learning on imagenet-1k
no code implementations • 2 Mar 2023 • Xuyang Zhao, Tianqi Du, Yisen Wang, Jun Yao, Weiran Huang
Moreover, we show that contrastive learning fails to learn domain-invariant features, which limits its transferability.
no code implementations • ICCV 2023 • Manyi Zhang, Xuyang Zhao, Jun Yao, Chun Yuan, Weiran Huang
In this paper, to handle the problem and address the limitations of prior works, we propose a representation calibration method RCAL.
2 code implementations • 30 May 2022 • Tianyang Hu, Zhili Liu, Fengwei Zhou, Wenjia Wang, Weiran Huang
Contrastive learning, especially self-supervised contrastive learning (SSCL), has achieved great success in extracting powerful features from unlabeled data.
1 code implementation • 1 Nov 2021 • Weiran Huang, Mingyang Yi, Xuyang Zhao, Zihao Jiang
It reveals that the generalization ability of contrastive self-supervised learning is related to three key factors: alignment of positive samples, divergence of class centers, and concentration of augmented data.
no code implementations • 5 Mar 2021 • Jiaye Teng, Weiran Huang, Haowei He
Pretext-based self-supervised learning learns the semantic representation via a handcrafted pretext task over unlabeled data and then uses the learned representation for downstream tasks, which effectively reduces the sample complexity of downstream tasks under Conditional Independence (CI) condition.
1 code implementation • 22 Oct 2020 • Fuli Feng, Weiran Huang, Xiangnan He, Xin Xin, Qifan Wang, Tat-Seng Chua
To this end, we analyze the working mechanism of GCN with causal graph, estimating the causal effect of a node's local structure for the prediction.
no code implementations • 16 Jun 2020 • Jiacheng Sun, Xiangyong Cao, Hanwen Liang, Weiran Huang, Zewei Chen, Zhenguo Li
In recent years, a variety of normalization methods have been proposed to help train neural networks, such as batch normalization (BN), layer normalization (LN), weight normalization (WN), group normalization (GN), etc.
3 code implementations • NeurIPS 2020 • Kai Zheng, Tianle Cai, Weiran Huang, Zhenguo Li, Li-Wei Wang
We study locally differentially private (LDP) bandits learning in this paper.
no code implementations • CVPR 2020 • Aoxue Li, Weiran Huang, Xu Lan, Jiashi Feng, Zhenguo Li, Li-Wei Wang
Few-shot learning (FSL) has attracted increasing attention in recent years but remains challenging, due to the intrinsic difficulty in learning to generalize from a few examples.
Ranked #1 on Few-Shot Image Classification on ImageNet (1-shot)
no code implementations • 24 Dec 2019 • Yimin Huang, Weiran Huang, Liang Li, Zhenguo Li
In this paper, we mainly consider the scenario in which we have a common model set used for model averaging instead of selecting a single final model via a model selection procedure to account for this model's uncertainty to improve the reliability and accuracy of inferences.
1 code implementation • 5 Nov 2019 • Fenyu Hu, Yanqiao Zhu, Shu Wu, Weiran Huang, Liang Wang, Tieniu Tan
Then, in order to better capture the complicated non-linearity of graph data, we present a novel GraphAIR framework which models the neighborhood interaction in addition to neighborhood aggregation.
no code implementations • 13 Sep 2019 • Hanwen Liang, Shifeng Zhang, Jiacheng Sun, Xingqiu He, Weiran Huang, Kechen Zhuang, Zhenguo Li
Therefore, we propose a simple and effective algorithm, named "DARTS+", to avoid the collapse and improve the original DARTS, by "early stopping" the search procedure when meeting a certain criterion.
2 code implementations • ICCV 2019 • Tiange Luo, Aoxue Li, Tao Xiang, Weiran Huang, Li-Wei Wang
In this paper, we propose to tackle the challenging few-shot learning (FSL) problem by learning global class representations using both base and novel class training samples.
no code implementations • NeurIPS 2018 • Xiaowei Chen, Weiran Huang, Wei Chen, John C. S. Lui
We introduce the community exploration problem that has many real-world applications such as online advertising.
no code implementations • 13 Nov 2018 • Chang Xu, Weiran Huang, Hongwei Wang, Gang Wang, Tie-Yan Liu
In this paper, we propose an improved variant of RNN, Multi-Channel RNN (MC-RNN), to dynamically capture and leverage local semantic structure information.
no code implementations • 4 May 2018 • Weiran Huang, Jungseul Ok, Liang Li, Wei Chen
Each decision has a reward according to the distributions of arms.
1 code implementation • 12 Feb 2018 • Lichao Sun, Weiran Huang, Philip S. Yu, Wei Chen
In this paper, we study the Multi-Round Influence Maximization (MRIM) problem, where influence propagates in multiple rounds independently from possibly different seed sets, and the goal is to select seeds for each round to maximize the expected number of nodes that are activated in at least one round.
Social and Information Networks