Search Results for author: Jian Song

Found 17 papers, 4 papers with code

GNOT: A General Neural Operator Transformer for Operator Learning

no code implementations28 Feb 2023 Zhongkai Hao, Chengyang Ying, Zhengyi Wang, Hang Su, Yinpeng Dong, Songming Liu, Ze Cheng, Jun Zhu, Jian Song

However, there are several challenges for learning operators in practical applications like the irregular mesh, multiple input functions, and complexity of the PDEs' solution.

Operator learning

Deep learning for full-field ultrasonic characterization

no code implementations6 Jan 2023 Yang Xu, Fatemeh Pourahmadian, Jian Song, Conglin Wang

This study takes advantage of recent advances in machine learning to establish a physics-based data analytic platform for distributed reconstruction of mechanical properties in layered components from full waveform data.


Improving Semantic Matching through Dependency-Enhanced Pre-trained Model with Adaptive Fusion

no code implementations16 Oct 2022 Jian Song, Di Liang, Rumei Li, Yuntao Li, Sirui Wang, Minlong Peng, Wei Wu, Yongxin Yu

Transformer-based pre-trained models like BERT have achieved great progress on Semantic Sentence Matching.

DABERT: Dual Attention Enhanced BERT for Semantic Matching

no code implementations COLING 2022 Sirui Wang, Di Liang, Jian Song, Yuntao Li, Wei Wu

To alleviate this problem, we propose a novel Dual Attention Enhanced BERT (DABERT) to enhance the ability of BERT to capture fine-grained differences in sentence pairs.

Bi-level Physics-Informed Neural Networks for PDE Constrained Optimization using Broyden's Hypergradients

no code implementations15 Sep 2022 Zhongkai Hao, Chengyang Ying, Hang Su, Jun Zhu, Jian Song, Ze Cheng

In this paper, we present a novel bi-level optimization framework to resolve the challenge by decoupling the optimization of the targets and constraints.

Single-scatter channel impulse response model of non-line-of-sight ultraviolet communications

no code implementations28 Aug 2022 Tian Cao, Shihan Chen, Tianfeng Wu, Changyong Pan, Jian Song

Previous studies on the temporal characteristics of single-scatter transmission in non-line-of-sight (NLOS) ultraviolet communications (UVC) were based on the prolate-spheroidal coordinate system.

GSmooth: Certified Robustness against Semantic Transformations via Generalized Randomized Smoothing

no code implementations9 Jun 2022 Zhongkai Hao, Chengyang Ying, Yinpeng Dong, Hang Su, Jun Zhu, Jian Song

Under the GSmooth framework, we present a scalable algorithm that uses a surrogate image-to-image network to approximate the complex transformation.

Simple Contrastive Representation Adversarial Learning for NLP Tasks

no code implementations26 Nov 2021 Deshui Miao, JiaQi Zhang, WenBo Xie, Jian Song, Xin Li, Lijuan Jia, Ning Guo

In this paper, adversarial training is performed to generate challenging and harder learning adversarial examples over the embedding space of NLP as learning pairs.

Contrastive Learning Natural Language Understanding +3

Graph Contrastive Learning for Anomaly Detection

2 code implementations17 Aug 2021 Bo Chen, Jing Zhang, Xiaokang Zhang, Yuxiao Dong, Jian Song, Peng Zhang, Kaibo Xu, Evgeny Kharlamov, Jie Tang

To achieve the contrastive objective, we design a graph neural network encoder that can infer and further remove suspicious links during message passing, as well as learn the global context of the input graph.

Anomaly Detection Contrastive Learning +1

Transition behavior of the seizure dynamics modulated by the astrocyte inositol triphosphate noise

no code implementations26 May 2021 Jiajia Li, Peihua Feng, Liang Zhao, Junying Chen, Mengmeng Du, Yangyang Yu, Jian Song, Ying Wu

Our simulation results show that the increase of the IP3 noise intensity induces the depolarization-block epileptic seizures together with an increase in neuronal firing frequency.

Binarized Aggregated Network with Quantization: Flexible Deep Learning Deployment for CSI Feedback in Massive MIMO System

1 code implementation1 May 2021 Zhilin Lu, Xudong Zhang, Hongyi He, Jintao Wang, Jian Song

Massive multiple-input multiple-output (MIMO) is one of the key techniques to achieve better spectrum and energy efficiency in 5G system.

Binarization Quantization

On eigenvalues of the Brownian sheet matrix

no code implementations12 Mar 2021 Jian Song, Yimin Xiao, Wangjun Yuan

We derive a system of stochastic partial differential equations satisfied by the eigenvalues of the symmetric matrix whose entries are the Brownian sheets.


Skorohod and Stratonovich integrals for controlled processes

no code implementations4 Feb 2021 Jian Song, Samy Tindel

Given a continuous Gaussian process $x$ which gives rise to a $p$-geometric rough path for $p\in (2, 3)$, and a general continuous process $y$ controlled by $x$, under proper conditions we establish the relationship between the Skorohod integral $\int_0^t y_s {\mathrm{d}}^\diamond x_s$ and the Stratonovich integral $\int_0^t y_s {\mathrm{d}} {\mathbf x}_s$.


Aggregated Network for Massive MIMO CSI Feedback

no code implementations17 Jan 2021 Zhilin Lu, Hongyi He, Zhengyang Duan, Jintao Wang, Jian Song

In frequency division duplexing (FDD) mode, it is necessary to send the channel state information (CSI) from user equipment to base station.

Binary Neural Network Aided CSI Feedback in Massive MIMO System

1 code implementation5 Nov 2020 Zhilin Lu, Jintao Wang, Jian Song

In massive multiple-input multiple-output (MIMO) system, channel state information (CSI) is essential for the base station to achieve high performance gain.


Multi-resolution CSI Feedback with deep learning in Massive MIMO System

1 code implementation31 Oct 2019 Zhilin Lu, Jintao Wang, Jian Song

In massive multiple-input multiple-output (MIMO) system, user equipment (UE) needs to send downlink channel state information (CSI) back to base station (BS).

Joint Transceiver Optimization for Wireless Communication PHY with Convolutional Neural Network

no code implementations9 Aug 2018 Banghua Zhu, Jintao Wang, Longzhuang He, Jian Song

The simulation results show that the performance of neural network based system is superior to traditional modulation and equalization methods in terms of time complexity and bit error rate (BER) under fading channels.

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