1 code implementation • 5 Apr 2024 • Tianqi Zhong, Zhaoyi Li, Quan Wang, Linqi Song, Ying WEI, Defu Lian, Zhendong Mao
Compositional generalization, representing the model's ability to generate text with new attribute combinations obtained by recombining single attributes from the training data, is a crucial property for multi-aspect controllable text generation (MCTG) methods.
no code implementations • 28 Mar 2024 • Yuxuan Yao, Han Wu, Zhijiang Guo, Biyan Zhou, Jiahui Gao, Sichun Luo, Hanxu Hou, Xiaojin Fu, Linqi Song
Large language models (LLMs) have demonstrated outstanding performance across various tasks, yet they still exhibit limitations such as hallucination, unfaithful reasoning, and toxic content.
no code implementations • 12 Mar 2024 • Haokun Lin, Haoli Bai, Zhili Liu, Lu Hou, Muyi Sun, Linqi Song, Ying WEI, Zhenan Sun
We find that directly using smaller pre-trained models and applying magnitude-based pruning on CLIP models leads to inflexibility and inferior performance.
1 code implementation • 10 Mar 2024 • Yuxuan Yao, Sichun Luo, Haohan Zhao, Guanzhi Deng, Linqi Song
We present CNER-UAV, a fine-grained \textbf{C}hinese \textbf{N}ame \textbf{E}ntity \textbf{R}ecognition dataset specifically designed for the task of address resolution in \textbf{U}nmanned \textbf{A}erial \textbf{V}ehicle delivery systems.
no code implementations • 22 Feb 2024 • Zhaoyi Li, Gangwei Jiang, Hong Xie, Linqi Song, Defu Lian, Ying WEI
LLMs have marked a revolutonary shift, yet they falter when faced with compositional reasoning tasks.
1 code implementation • 14 Feb 2024 • Yinya Huang, Xiaohan Lin, Zhengying Liu, Qingxing Cao, Huajian Xin, Haiming Wang, Zhenguo Li, Linqi Song, Xiaodan Liang
Recent large language models (LLMs) have witnessed significant advancement in various tasks, including mathematical reasoning and theorem proving.
no code implementations • 2 Feb 2024 • Guangfeng Yan, Tan Li, Yuanzhang Xiao, Hanxu Hou, Linqi Song
We consider a general family of heavy-tail gradients that follow a power-law distribution, we aim to minimize the error resulting from quantization, thereby determining optimal values for two critical parameters: the truncation threshold and the quantization density.
no code implementations • 2 Feb 2024 • Guangfeng Yan, Tan Li, Yuanzhang Xiao, Congduan Li, Linqi Song
To address the communication bottleneck challenge in distributed learning, our work introduces a novel two-stage quantization strategy designed to enhance the communication efficiency of distributed Stochastic Gradient Descent (SGD).
1 code implementation • 26 Jan 2024 • Haochen Tan, Zhijiang Guo, Zhan Shi, Lu Xu, Zhili Liu, Yunlong Feng, Xiaoguang Li, Yasheng Wang, Lifeng Shang, Qun Liu, Linqi Song
LLMs are prompted to generate extensive content in response to these meta-questions.
no code implementations • 25 Jan 2024 • Sichun Luo, Yuxuan Yao, Bowei He, Yinya Huang, Aojun Zhou, Xinyi Zhang, Yuanzhang Xiao, Mingjie Zhan, Linqi Song
Conventional recommendation methods have achieved notable advancements by harnessing collaborative or sequential information from user behavior.
no code implementations • 19 Jan 2024 • Lintai Wu, Junhui Hou, Linqi Song, Yong Xu
Specifically, we construct a prior bank consisting of representative shapes from the seen categories.
1 code implementation • 26 Dec 2023 • Sichun Luo, Bowei He, Haohan Zhao, Wei Shao, Yanlin Qi, Yinya Huang, Aojun Zhou, Yuxuan Yao, Zongpeng Li, Yuanzhang Xiao, Mingjie Zhan, Linqi Song
Large Language Models (LLMs) have demonstrated remarkable capabilities and have been extensively deployed across various domains, including recommender systems.
no code implementations • 29 Nov 2023 • Yinya Huang, Ruixin Hong, Hongming Zhang, Wei Shao, Zhicheng Yang, Dong Yu, ChangShui Zhang, Xiaodan Liang, Linqi Song
In this study, we delve into the realm of counterfactual reasoning capabilities of large language models (LLMs).
1 code implementation • 12 Oct 2023 • Yuxuan Yao, Han Wu, Qiling Xu, Linqi Song
General-purpose text decoding approaches are usually adopted for dialogue response generation.
1 code implementation • 5 Oct 2023 • Ke Wang, Houxing Ren, Aojun Zhou, Zimu Lu, Sichun Luo, Weikang Shi, Renrui Zhang, Linqi Song, Mingjie Zhan, Hongsheng Li
In this paper, we present a method to fine-tune open-source language models, enabling them to use code for modeling and deriving math equations and, consequently, enhancing their mathematical reasoning abilities.
Ranked #4 on Math Word Problem Solving on SVAMP (using extra training data)
1 code implementation • 15 Aug 2023 • Aojun Zhou, Ke Wang, Zimu Lu, Weikang Shi, Sichun Luo, Zipeng Qin, Shaoqing Lu, Anya Jia, Linqi Song, Mingjie Zhan, Hongsheng Li
We found that its success can be largely attributed to its powerful skills in generating and executing code, evaluating the output of code execution, and rectifying its solution when receiving unreasonable outputs.
Ranked #1 on Math Word Problem Solving on MATH
no code implementations • 13 May 2023 • Haochen Tan, Han Wu, Wei Shao, Xinyun Zhang, Mingjie Zhan, Zhaohui Hou, Ding Liang, Linqi Song
Meetings typically involve multiple participants and lengthy conversations, resulting in redundant and trivial content.
no code implementations • 11 May 2023 • Sichun Luo, Yuanzhang Xiao, Xinyi Zhang, Yang Liu, Wenbo Ding, Linqi Song
Each user learns a personalized model by combining the global federated model, the cluster-level federated model, and its own fine-tuned local model.
1 code implementation • 9 May 2023 • Han Wu, Mingjie Zhan, Haochen Tan, Zhaohui Hou, Ding Liang, Linqi Song
Compared to news and chat summarization, the development of meeting summarization is hugely decelerated by the limited data.
no code implementations • 26 Apr 2023 • Guangfeng Yan, Tan Li, Kui Wu, Linqi Song
Communication efficiency and privacy protection are two critical issues in distributed machine learning.
2 code implementations • 17 Apr 2023 • Xiaoming Xue, Cuie Yang, Liang Feng, Kai Zhang, Linqi Song, Kay Chen Tan
Lastly, a benchmark suite with 12 STO problems featured by a variety of customized similarity relationships is developed using the proposed generator.
no code implementations • 22 Feb 2023 • Baoliang Chen, Lingyu Zhu, Hanwei Zhu, Wenhan Yang, Linqi Song, Shiqi Wang
Subsequently, we propose an objective quality assessment measure that plays a critical role in bridging the gap between visual quality and enhancement.
no code implementations • 24 Oct 2022 • Mengzhe Ruan, Guangfeng Yan, Yuanzhang Xiao, Linqi Song, Weitao Xu
This paper proposes a novel adaptive Top-K in SGD framework that enables an adaptive degree of sparsification for each gradient descent step to optimize the convergence performance by balancing the trade-off between communication cost and convergence error.
no code implementations • 5 Oct 2022 • Haoyu Chen, Linqi Song, Zhenxing Qian, Xinpeng Zhang, Kede Ma
As an instantiation, we adopt a SinGAN, a pyramid of generative adversarial networks (GANs), to learn the patch distribution of one cover image.
no code implementations • 23 Aug 2022 • Sichun Luo, Yuanzhang Xiao, Yang Liu, Congduan Li, Linqi Song
Federated recommendations leverage the federated learning (FL) techniques to make privacy-preserving recommendations.
no code implementations • 20 Aug 2022 • Sichun Luo, Xinyi Zhang, Yuanzhang Xiao, Linqi Song
For example, in a mobile game recommendation, contextual features like locations, battery, and storage levels of mobile devices are frequently drifting over time.
no code implementations • 19 Aug 2022 • Sichun Luo, Yuanzhang Xiao, Linqi Song
In this paper, we propose a Graph Neural Network based Personalized Federated Recommendation (PerFedRec) framework via joint representation learning, user clustering, and model adaptation.
no code implementations • 16 Jun 2022 • Wei Shao, Lei Huang, Shuqi Liu, Shihua Ma, Linqi Song
In this paper, we propose an embedding regularized neural topic model, which applies the specially designed training constraints on word embedding and topic embedding to reduce the optimization space of parameters.
1 code implementation • 29 May 2022 • Han Wu, Haochen Tan, Mingjie Zhan, Gangming Zhao, Shaoqing Lu, Ding Liang, Linqi Song
Existing dialogue modeling methods have achieved promising performance on various dialogue tasks with the aid of Transformer and the large-scale pre-trained language models.
1 code implementation • Findings (NAACL) 2022 • Han Wu, Haochen Tan, Kun Xu, Shuqi Liu, Lianwei Wu, Linqi Song
While conversational semantic role labeling (CSRL) has shown its usefulness on Chinese conversational tasks, it is still under-explored in non-Chinese languages due to the lack of multilingual CSRL annotations for the parser training.
1 code implementation • Findings (ACL) 2022 • Haochen Tan, Wei Shao, Han Wu, Ke Yang, Linqi Song
Contrastive learning has shown great potential in unsupervised sentence embedding tasks, e. g., SimCSE.
no code implementations • 2 Nov 2021 • Tan Li, Linqi Song
Our bandit learning algorithms are based on epoch-wise sub-optimal arm eliminations at each agent and agents exchange learning knowledge with the server/each other at the end of each epoch.
1 code implementation • EMNLP 2021 • Han Wu, Kun Xu, Linqi Song
Conversational semantic role labeling (CSRL) is believed to be a crucial step towards dialogue understanding.
3 code implementations • 13 Sep 2021 • Jian Xu, Shao-Lun Huang, Linqi Song, Tian Lan
To this end, previous work either makes use of auxiliary data at parameter server to verify the received gradients (e. g., by computing validation error rate) or leverages statistic-based methods (e. g. median and Krum) to identify and remove malicious gradients from Byzantine clients.
no code implementations • 30 Jul 2021 • Guangfeng Yan, Shao-Lun Huang, Tian Lan, Linqi Song
Gradient quantization is an emerging technique in reducing communication costs in distributed learning.
no code implementations • ACL 2021 • Han Wu, Kun Xu, Linfeng Song, Lifeng Jin, Haisong Zhang, Linqi Song
Language models like BERT and SpanBERT pretrained on open-domain data have obtained impressive gains on various NLP tasks.
no code implementations • 11 Apr 2021 • Kun Xu, Han Wu, Linfeng Song, Haisong Zhang, Linqi Song, Dong Yu
Semantic role labeling (SRL) aims to extract the arguments for each predicate in an input sentence.
1 code implementation • 25 Jan 2021 • Lei Huang, Jiecong Lin, Xiangtao Li, Linqi Song, Ka-Chun Wong
To address such a problem, we propose EGFI for extracting and consolidating drug interactions from large-scale medical literature text data.
no code implementations • 1 Jan 2021 • Guangfeng Yan, Shao-Lun Huang, Tian Lan, Linqi Song
This paper addresses this issue by proposing a novel dynamic quantized SGD (DQSGD) framework, which enables us to optimize the quantization strategy for each gradient descent step by exploring the trade-off between communication cost and modeling error.
no code implementations • 3 Dec 2020 • Jing Dong, Tan Li, Shaolei Ren, Linqi Song
To further improve the performance of distributed Thompson Sampling, we propose a distributed Elimination based Thompson Sampling algorithm that allow the agents to learn collaboratively.
no code implementations • EMNLP 2020 • Kun Xu, Haochen Tan, Linfeng Song, Han Wu, Haisong Zhang, Linqi Song, Dong Yu
For multi-turn dialogue rewriting, the capacity of effectively modeling the linguistic knowledge in dialog context and getting rid of the noises is essential to improve its performance.
no code implementations • 14 May 2020 • Tan Li, Linqi Song, Christina Fragouli
In this paper, we are interested in what we term the federated private bandits framework, that combines differential privacy with multi-agent bandit learning.
1 code implementation • 16 Jul 2019 • Mengwei Yang, Linqi Song, Jie Xu, Congduan Li, Guozhen Tan
Our proposed federated XGBoost algorithm incorporates data aggregation and sparse federated update processes to balance the tradeoff between privacy and learning performance.
no code implementations • 5 Jul 2019 • Deepesh Data, Linqi Song, Suhas Diggavi
In this paper, we propose a method based on data encoding and error correction over real numbers to combat adversarial attacks.
1 code implementation • 16 Jun 2019 • Erkao Bao, Linqi Song
We provide a process to modify a neural network to an equivariant one, which we call equivarification.
no code implementations • 15 Oct 2018 • Linqi Song, Christina Fragouli, Devavrat Shah
We consider recommendation systems that need to operate under wireless bandwidth constraints, measured as number of broadcast transmissions, and demonstrate a (tight for some instances) tradeoff between regret and bandwidth for two scenarios: the case of multi-armed bandit with context, and the case where there is a latent structure in the message space that we can exploit to reduce the learning phase.
no code implementations • 24 Jan 2017 • Linqi Song, Jie Xu
The key feature of our algorithm is that in addition to sending a query to an annotator for the ground truth, prior information about the ground truth learned by the learner is sent together, thereby reducing the query cost.
no code implementations • 11 Jul 2016 • Linqi Song
In a stream-based active learning setting, obtaining the ground truth of the reward is costly, and the conventional contextual multi-armed bandit algorithm fails to achieve a sublinear regret due to this cost.