Search Results for author: Jin Xu

Found 60 papers, 27 papers with code

cPAPERS: A Dataset of Situated and Multimodal Interactive Conversations in Scientific Papers

no code implementations12 Jun 2024 Anirudh Sundar, Jin Xu, William Gay, Christopher Richardson, Larry Heck

An emerging area of research in situated and multimodal interactive conversations (SIMMC) includes interactions in scientific papers.

Simple Multigraph Convolution Networks

1 code implementation8 Mar 2024 Danyang Wu, Xinjie Shen, Jitao Lu, Jin Xu, Feiping Nie

Existing multigraph convolution methods either ignore the cross-view interaction among multiple graphs, or induce extremely high computational cost due to standard cross-view polynomial operators.

FinReport: Explainable Stock Earnings Forecasting via News Factor Analyzing Model

1 code implementation5 Mar 2024 Xiangyu Li, Xinjie Shen, Yawen Zeng, Xiaofen Xing, Jin Xu

However, compared with financial institutions, it is not easy for ordinary investors to mine factors and analyze news.

Stock Market Prediction

AIR-Bench: Benchmarking Large Audio-Language Models via Generative Comprehension

no code implementations12 Feb 2024 Qian Yang, Jin Xu, Wenrui Liu, Yunfei Chu, Ziyue Jiang, Xiaohuan Zhou, Yichong Leng, YuanJun Lv, Zhou Zhao, Chang Zhou, Jingren Zhou

By revealing the limitations of existing LALMs through evaluation results, AIR-Bench can provide insights into the direction of future research.

2k Automatic Speech Recognition +4

SIG: Speaker Identification in Literature via Prompt-Based Generation

1 code implementation22 Dec 2023 Zhenlin Su, Liyan Xu, Jin Xu, Jiangnan Li, Mingdu Huangfu

Identifying speakers of quotations in narratives is an important task in literary analysis, with challenging scenarios including the out-of-domain inference for unseen speakers, and non-explicit cases where there are no speaker mentions in surrounding context.

Speaker Identification

Best Arm Identification in Batched Multi-armed Bandit Problems

no code implementations21 Dec 2023 Shengyu Cao, Simai He, Ruoqing Jiang, Jin Xu, Hongsong Yuan

The linear program leads to a two-stage algorithm that can achieve good theoretical properties.

Marketing Thompson Sampling

NP$^2$L: Negative Pseudo Partial Labels Extraction for Graph Neural Networks

no code implementations2 Oct 2023 Xinjie Shen, Danyang Wu, Jitao Lu, Junjie Liang, Jin Xu, Feiping Nie

Moreover, applications of pseudo labels in graph neural networks (GNNs) oversee the difference between graph learning and other machine learning tasks such as message passing mechanism.

Graph Learning Link Prediction +2

Understanding In-Context Learning from Repetitions

1 code implementation30 Sep 2023 Jianhao Yan, Jin Xu, Chiyu Song, Chenming Wu, Yafu Li, Yue Zhang

This paper explores the elusive mechanism underpinning in-context learning in Large Language Models (LLMs).

In-Context Learning Text Generation

The Whole Pathological Slide Classification via Weakly Supervised Learning

no code implementations12 Jul 2023 Qiehe Sun, Jiawen Li, Jin Xu, Junru Cheng, Tian Guan, Yonghong He

Due to its superior efficiency in utilizing annotations and addressing gigapixel-sized images, multiple instance learning (MIL) has shown great promise as a framework for whole slide image (WSI) classification in digital pathology diagnosis.

Contrastive Learning Data Augmentation +5

Investigating Graph Structure Information for Entity Alignment with Dangling Cases

no code implementations10 Apr 2023 Jin Xu, Yangning Li, Xiangjin Xie, Yinghui Li, Niu Hu, Haitao Zheng, Yong Jiang

To improve the exploitation of the structural information, we propose a novel entity alignment framework called Weakly-Optimal Graph Contrastive Learning (WOGCL), which is refined on three dimensions : (i) Model.

Contrastive Learning Entity Alignment +3

Effort Discrimination and Curvature of Contest Technology in Conflict Networks

no code implementations20 Feb 2023 Xiang Sun, Jin Xu, Junjie Zhou

When the contest technology in each battle is of Tullock form, a surprising neutrality result holds within the class of semi-symmetric conflict network structures: both the aggregate actions and equilibrium payoffs under two regimes are the same.

SBcoyote: An Extensible Python-Based Reaction Editor and Viewer

1 code implementation17 Feb 2023 Jin Xu, Gary Geng, Nhan D. Nguyen, Carmen Perena-Cortes, Claire Samuels, Herbert M. Sauro

A unique feature of the tool is the extensive Python plugin API, where third-party developers can include new functionality.

DC-MBR: Distributional Cooling for Minimum Bayesian Risk Decoding

no code implementations8 Dec 2022 Jianhao Yan, Jin Xu, Fandong Meng, Jie zhou, Yue Zhang

In this work, we show that the issue arises from the un-consistency of label smoothing on the token-level and sequence-level distributions.

Machine Translation NMT

A universal DNA computing model for solving NP-hard subset problems

no code implementations14 Nov 2022 Enqiang Zhu, Xianhang Luo, Chanjuan Liu, Xiaolong Shi, Jin Xu

Although DNA computing has been exploited to solve various intractable computational problems, such as the Hamiltonian path problem, SAT problem, and graph coloring problem, there has been little discussion of designing universal DNA computing-based models, which can solve a class of problems.

$N$-gram Is Back: Residual Learning of Neural Text Generation with $n$-gram Language Model

1 code implementation26 Oct 2022 Huayang Li, Deng Cai, Jin Xu, Taro Watanabe

The combination of $n$-gram and neural LMs not only allows the neural part to focus on the deeper understanding of language but also provides a flexible way to customize an LM by switching the underlying $n$-gram model without changing the neural model.

Domain Adaptation Language Modelling +2

Learning to Break the Loop: Analyzing and Mitigating Repetitions for Neural Text Generation

2 code implementations6 Jun 2022 Jin Xu, Xiaojiang Liu, Jianhao Yan, Deng Cai, Huayang Li, Jian Li

While large-scale neural language models, such as GPT2 and BART, have achieved impressive results on various text generation tasks, they tend to get stuck in undesirable sentence-level loops with maximization-based decoding algorithms (\textit{e. g.}, greedy search).

Sentence Text Generation +1

AGIC: Approximate Gradient Inversion Attack on Federated Learning

no code implementations28 Apr 2022 Jin Xu, Chi Hong, Jiyue Huang, Lydia Y. Chen, Jérémie Decouchant

Recent reconstruction attacks apply a gradient inversion optimization on the gradient update of a single minibatch to reconstruct the private data used by clients during training.

Federated Learning

Procedural Text Understanding via Scene-Wise Evolution

no code implementations15 Mar 2022 Jialong Tang, Hongyu Lin, Meng Liao, Yaojie Lu, Xianpei Han, Le Sun, Weijian Xie, Jin Xu

In this paper, we propose a new \textbf{scene-wise} paradigm for procedural text understanding, which jointly tracks states of all entities in a scene-by-scene manner.

Procedural Text Understanding

libRoadRunner 2.0: A High-Performance SBML Simulation and Analysis Library

no code implementations26 Feb 2022 Ciaran Welsh, Jin Xu, Lucian Smith, Matthias König, Kiri Choi, Herbert M. Sauro

Motivation: This paper presents libRoadRunner 2. 0, an extensible, high-performance, cross-platform, open-source software library for the simulation and analysis of models expressed using Systems Biology Markup Language SBML).

Vocal Bursts Intensity Prediction

CLS: Cross Labeling Supervision for Semi-Supervised Learning

1 code implementation17 Feb 2022 Yao Yao, Junyi Shen, Jin Xu, Bin Zhong, Li Xiao

Based on FixMatch, where a pseudo label is generated from a weakly-augmented sample to teach the prediction on a strong augmentation of the same input sample, CLS allows the creation of both pseudo and complementary labels to support both positive and negative learning.

Pseudo Label

Hybrid Contrastive Quantization for Efficient Cross-View Video Retrieval

1 code implementation7 Feb 2022 Jinpeng Wang, Bin Chen, Dongliang Liao, Ziyun Zeng, Gongfu Li, Shu-Tao Xia, Jin Xu

By performing Asymmetric-Quantized Contrastive Learning (AQ-CL) across views, HCQ aligns texts and videos at coarse-grained and multiple fine-grained levels.

Contrastive Learning Quantization +4

Speech-T: Transducer for Text to Speech and Beyond

no code implementations NeurIPS 2021 Jiawei Chen, Xu Tan, Yichong Leng, Jin Xu, Guihua Wen, Tao Qin, Tie-Yan Liu

Experiments on LJSpeech datasets demonstrate that Speech-T 1) is more robust than the attention based autoregressive TTS model due to its inherent monotonic alignments between text and speech; 2) naturally supports streaming TTS with good voice quality; and 3) enjoys the benefit of joint modeling TTS and ASR in a single network.

Automatic Speech Recognition Automatic Speech Recognition (ASR) +2

AutoHEnsGNN: Winning Solution to AutoGraph Challenge for KDD Cup 2020

1 code implementation25 Nov 2021 Jin Xu, Mingjian Chen, Jianqiang Huang, Xingyuan Tang, Ke Hu, Jian Li, Jia Cheng, Jun Lei

Graph Neural Networks (GNNs) have become increasingly popular and achieved impressive results in many graph-based applications.

Graph Classification Node Classification

FastCorrect 2: Fast Error Correction on Multiple Candidates for Automatic Speech Recognition

1 code implementation Findings (EMNLP) 2021 Yichong Leng, Xu Tan, Rui Wang, Linchen Zhu, Jin Xu, Wenjie Liu, Linquan Liu, Tao Qin, Xiang-Yang Li, Edward Lin, Tie-Yan Liu

Although multiple candidates are generated by an ASR system through beam search, current error correction approaches can only correct one sentence at a time, failing to leverage the voting effect from multiple candidates to better detect and correct error tokens.

Automatic Speech Recognition Automatic Speech Recognition (ASR) +3

Improving Hit-finding: Multilabel Neural Architecture with DEL

no code implementations NeurIPS Workshop AI4Scien 2021 Kehang Han, Steven Kearnes, Jin Xu, Wen Torng, JW Feng

DNA-Encoded Libraries (DEL thereafter) data, often with millions of data points, enables large deep learning models to make real contributions in the drug discovery process (e. g., hit-finding).

Drug Discovery

Analyzing and Mitigating Interference in Neural Architecture Search

no code implementations29 Aug 2021 Jin Xu, Xu Tan, Kaitao Song, Renqian Luo, Yichong Leng, Tao Qin, Tie-Yan Liu, Jian Li

In this paper, we investigate the interference issue by sampling different child models and calculating the gradient similarity of shared operators, and observe: 1) the interference on a shared operator between two child models is positively correlated with the number of different operators; 2) the interference is smaller when the inputs and outputs of the shared operator are more similar.

Neural Architecture Search Reading Comprehension

Knowledgeable or Educated Guess? Revisiting Language Models as Knowledge Bases

1 code implementation ACL 2021 Boxi Cao, Hongyu Lin, Xianpei Han, Le Sun, Lingyong Yan, Meng Liao, Tong Xue, Jin Xu

Previous literatures show that pre-trained masked language models (MLMs) such as BERT can achieve competitive factual knowledge extraction performance on some datasets, indicating that MLMs can potentially be a reliable knowledge source.

Group Equivariant Subsampling

1 code implementation NeurIPS 2021 Jin Xu, Hyunjik Kim, Tom Rainforth, Yee Whye Teh

We use these layers to construct group equivariant autoencoders (GAEs) that allow us to learn low-dimensional equivariant representations.


AKE-GNN: Effective Graph Learning with Adaptive Knowledge Exchange

no code implementations10 Jun 2021 Liang Zeng, Jin Xu, Zijun Yao, Yanqiao Zhu, Jian Li

In this paper, we propose to substitute these redundant channels with other informative channels to achieve this goal.

Graph Classification Graph Learning +4

FastCorrect: Fast Error Correction with Edit Alignment for Automatic Speech Recognition

1 code implementation NeurIPS 2021 Yichong Leng, Xu Tan, Linchen Zhu, Jin Xu, Renqian Luo, Linquan Liu, Tao Qin, Xiang-Yang Li, Ed Lin, Tie-Yan Liu

A straightforward solution to reduce latency, inspired by non-autoregressive (NAR) neural machine translation, is to use an NAR sequence generation model for ASR error correction, which, however, comes at the cost of significantly increased ASR error rate.

Automatic Speech Recognition Automatic Speech Recognition (ASR) +4

MixSpeech: Data Augmentation for Low-resource Automatic Speech Recognition

no code implementations25 Feb 2021 Linghui Meng, Jin Xu, Xu Tan, Jindong Wang, Tao Qin, Bo Xu

In this paper, we propose MixSpeech, a simple yet effective data augmentation method based on mixup for automatic speech recognition (ASR).

Automatic Speech Recognition Automatic Speech Recognition (ASR) +2

Task-Agnostic and Adaptive-Size BERT Compression

no code implementations1 Jan 2021 Jin Xu, Xu Tan, Renqian Luo, Kaitao Song, Li Jian, Tao Qin, Tie-Yan Liu

NAS-BERT trains a big supernet on a carefully designed search space containing various architectures and outputs multiple compressed models with adaptive sizes and latency.

Language Modelling Model Compression +1

Incorporate Semantic Structures into Machine Translation Evaluation via UCCA

no code implementations WMT (EMNLP) 2020 Jin Xu, Yinuo Guo, Junfeng Hu

Copying mechanism has been commonly used in neural paraphrasing networks and other text generation tasks, in which some important words in the input sequence are preserved in the output sequence.

Machine Translation Sentence +3

OFFER: A Motif Dimensional Framework for Network Representation Learning

no code implementations27 Aug 2020 Shuo Yu, Feng Xia, Jin Xu, Zhikui Chen, Ivan Lee

In order to assess the efficiency of the proposed framework, four popular network representation algorithms are modified and examined.

Clustering Graph Learning +2

Cognitive Representation Learning of Self-Media Online Article Quality

no code implementations13 Aug 2020 Yiru Wang, Shen Huang, Gongfu Li, Qiang Deng, Dongliang Liao, Pengda Si, Yujiu Yang, Jin Xu

The automatic quality assessment of self-media online articles is an urgent and new issue, which is of great value to the online recommendation and search.

Representation Learning

LRSpeech: Extremely Low-Resource Speech Synthesis and Recognition

no code implementations9 Aug 2020 Jin Xu, Xu Tan, Yi Ren, Tao Qin, Jian Li, Sheng Zhao, Tie-Yan Liu

However, there are more than 6, 000 languages in the world and most languages are lack of speech training data, which poses significant challenges when building TTS and ASR systems for extremely low-resource languages.

Automatic Speech Recognition Automatic Speech Recognition (ASR) +3

Multivariate Relations Aggregation Learning in Social Networks

no code implementations9 Aug 2020 Jin Xu, Shuo Yu, Ke Sun, Jing Ren, Ivan Lee, Shirui Pan, Feng Xia

Therefore, in graph learning tasks of social networks, the identification and utilization of multivariate relationship information are more important.

Attribute Graph Learning +1

Whole-Body Human Pose Estimation in the Wild

2 code implementations ECCV 2020 Sheng Jin, Lumin Xu, Jin Xu, Can Wang, Wentao Liu, Chen Qian, Wanli Ouyang, Ping Luo

This paper investigates the task of 2D human whole-body pose estimation, which aims to localize dense landmarks on the entire human body including face, hands, body, and feet.

2D Human Pose Estimation Facial Landmark Detection +2

A Bayesian Framework for Nash Equilibrium Inference in Human-Robot Parallel Play

no code implementations10 Jun 2020 Shray Bansal, Jin Xu, Ayanna Howard, Charles Isbell

We showed that using a Bayesian approach to infer the equilibrium enables the robot to complete the task with less than half the number of collisions while also reducing the task execution time as compared to the best baseline.

MultiSpeech: Multi-Speaker Text to Speech with Transformer

1 code implementation8 Jun 2020 Mingjian Chen, Xu Tan, Yi Ren, Jin Xu, Hao Sun, Sheng Zhao, Tao Qin, Tie-Yan Liu

Transformer-based text to speech (TTS) model (e. g., Transformer TTS~\cite{li2019neural}, FastSpeech~\cite{ren2019fastspeech}) has shown the advantages of training and inference efficiency over RNN-based model (e. g., Tacotron~\cite{shen2018natural}) due to its parallel computation in training and/or inference.


Weak Supervision for Fake News Detection via Reinforcement Learning

1 code implementation28 Dec 2019 Yaqing Wang, Weifeng Yang, Fenglong Ma, Jin Xu, Bin Zhong, Qiang Deng, Jing Gao

In order to tackle this challenge, we propose a reinforced weakly-supervised fake news detection framework, i. e., WeFEND, which can leverage users' reports as weak supervision to enlarge the amount of training data for fake news detection.

Fake News Detection reinforcement-learning +1

MetaFun: Meta-Learning with Iterative Functional Updates

1 code implementation ICML 2020 Jin Xu, Jean-Francois Ton, Hyunjik Kim, Adam R. Kosiorek, Yee Whye Teh

We develop a functional encoder-decoder approach to supervised meta-learning, where labeled data is encoded into an infinite-dimensional functional representation rather than a finite-dimensional one.

Decoder Few-Shot Image Classification +1

Transfer Value Iteration Networks

no code implementations11 Nov 2019 Junyi Shen, Hankz Hankui Zhuo, Jin Xu, Bin Zhong, Sinno Jialin Pan

However, based on our experiments, a policy learned by VINs still fail to generalize well on the domain whose action space and feature space are not identical to those in the domain where it is trained.

Transfer Learning

Immunological recognition by artificial neural networks

2 code implementations10 Aug 2018 Jin Xu, Junghyo Jo

To address this problem, we examine whether the affinity-based discrimination of peptide sequences is learnable and generalizable by artificial neural networks (ANNs) that process the digital experimental amino acid sequence information of receptors and peptides.

Controllable Semantic Image Inpainting

no code implementations15 Jun 2018 Jin Xu, Yee Whye Teh

We develop a method for user-controllable semantic image inpainting: Given an arbitrary set of observed pixels, the unobserved pixels can be imputed in a user-controllable range of possibilities, each of which is semantically coherent and locally consistent with the observed pixels.

Image Inpainting

Broad cross-reactivity of the T-cell repertoire achieves specific and sufficiently rapid target searching

1 code implementation13 Dec 2017 Jin Xu, Junghyo Jo

We examine sequences of 10, 000 human T-cell receptors and 10, 000 antigenic peptides, and obtain a full spectrum of cross-reactivity of the receptor-peptide binding.

A Local Counter-Regulatory Motif Modulates the Global Phase of Hormonal Oscillations

no code implementations19 Jul 2016 Dong-Ho Park, Taegeun Song, Danh-Tai Hoang, Jin Xu, Junghyo Jo

By testing all possible motifs governing the interactions of these three cell types, we found that a unique set of positive/negative intra-islet interactions between different islet cell types functions not only to reduce the superficially wasteful zero-sum action of glucagon and insulin but also to enhance/suppress the synchronization of hormone secretions between islets under high/normal glucose conditions.

Active Dictionary Learning in Sparse Representation Based Classification

no code implementations19 Sep 2014 Jin Xu, Haibo He, Hong Man

The classification accuracy and reconstruction error are used to evaluate the proposed dictionary learning method.

Active Learning Classification +3

Cannot find the paper you are looking for? You can Submit a new open access paper.