Search Results for author: Lei Cheng

Found 33 papers, 12 papers with code

Self-Distillation Improves DNA Sequence Inference

1 code implementation14 May 2024 Tong Yu, Lei Cheng, Ruslan Khalitov, Erland Brandser Olsson, Zhirong Yang

Self-supervised pretraining (SSP) has been recognized as a method to enhance prediction accuracy in various downstream tasks.

Contrastive Learning Language Modelling +1

CTRL: Continuous-Time Representation Learning on Temporal Heterogeneous Information Network

no code implementations11 May 2024 Chenglin Li, Yuanzhen Xie, Chenyun Yu, Lei Cheng, Bo Hu, Zang Li, Di Niu

We train the CTRL model with a future event (a subgraph) prediction task to capture the evolution of the high-order network structure.

Graph Embedding Link Prediction +1

Towards Robust Recommendation: A Review and an Adversarial Robustness Evaluation Library

1 code implementation27 Apr 2024 Lei Cheng, Xiaowen Huang, Jitao Sang, Jian Yu

In the adversarial robustness, we introduce the fundamental principles and classical methods of recommender system adversarial attacks and defenses.

Adversarial Robustness Non-Adversarial Robustness +1

Decomposition for Enhancing Attention: Improving LLM-based Text-to-SQL through Workflow Paradigm

1 code implementation16 Feb 2024 Yuanzhen Xie, Xinzhou Jin, Tao Xie, Mingxiong Lin, Liang Chen, Chenyun Yu, Lei Cheng, Chengxiang Zhuo, Bo Hu, Zang Li

To improve the contextual learning capabilities of LLMs in text-to-SQL, a workflow paradigm method is proposed, aiming to enhance the attention and problem-solving scope of LLMs through decomposition.

Active Learning In-Context Learning +1

Striking The Right Balance: Three-Dimensional Ocean Sound Speed Field Reconstruction Using Tensor Neural Networks

1 code implementation9 Aug 2023 Siyuan Li, Lei Cheng, Ting Zhang, Hangfang Zhao, Jianlong Li

Accurately reconstructing a three-dimensional ocean sound speed field (3D SSF) is essential for various ocean acoustic applications, but the sparsity and uncertainty of sound speed samples across a vast ocean region make it a challenging task.

Multipath Time-delay Estimation with Impulsive Noise via Bayesian Compressive Sensing

no code implementations5 Jul 2023 Xingyu Ji, Lei Cheng, Hangfang Zhao

The performance of our proposed method is compared with benchmark methods, including compressive sensing (CS), BCS, and Laplacian-prior BCS (L-BCS).

Compressive Sensing

To Fold or Not to Fold: Graph Regularized Tensor Train for Visual Data Completion

1 code implementation19 Jun 2023 Le Xu, Lei Cheng, Ngai Wong, Yik-Chung Wu

Tensor train (TT) representation has achieved tremendous success in visual data completion tasks, especially when it is combined with tensor folding.

Overcoming Beam Squint in Dual-Wideband mmWave MIMO Channel Estimation: A Bayesian Multi-Band Sparsity Approach

no code implementations19 Jun 2023 Le Xu, Lei Cheng, Ngai Wong, Yik-Chung Wu, H. Vincent Poor

A probabilistic model is built to induce the common sparsity in the spatial domain, and the first-order Taylor expansion is adopted to get rid of the grid mismatch in the dictionaries.

Can the Inference Logic of Large Language Models be Disentangled into Symbolic Concepts?

no code implementations3 Apr 2023 Wen Shen, Lei Cheng, Yuxiao Yang, Mingjie Li, Quanshi Zhang

In this paper, we explain the inference logic of large language models (LLMs) as a set of symbolic concepts.


GDOD: Effective Gradient Descent using Orthogonal Decomposition for Multi-Task Learning

no code implementations31 Jan 2023 Xin Dong, Ruize Wu, Chao Xiong, Hai Li, Lei Cheng, Yong He, Shiyou Qian, Jian Cao, Linjian Mo

GDOD decomposes gradients into task-shared and task-conflict components explicitly and adopts a general update rule for avoiding interference across all task gradients.

Multi-Task Learning

Output-Dependent Gaussian Process State-Space Model

1 code implementation15 Dec 2022 Zhidi Lin, Lei Cheng, Feng Yin, Lexi Xu, Shuguang Cui

Gaussian process state-space model (GPSSM) is a fully probabilistic state-space model that has attracted much attention over the past decade.

Tele-Knowledge Pre-training for Fault Analysis

1 code implementation20 Oct 2022 Zhuo Chen, Wen Zhang, Yufeng Huang, Mingyang Chen, Yuxia Geng, Hongtao Yu, Zhen Bi, Yichi Zhang, Zhen Yao, Wenting Song, Xinliang Wu, Yi Yang, Mingyi Chen, Zhaoyang Lian, YingYing Li, Lei Cheng, Huajun Chen

In this work, we share our experience on tele-knowledge pre-training for fault analysis, a crucial task in telecommunication applications that requires a wide range of knowledge normally found in both machine log data and product documents.

Language Modelling

Reconfigurable Intelligent Surface-Aided 6G Massive Access: Coupled Tensor Modeling and Sparse Bayesian Learning

no code implementations11 Jun 2022 Xiaodan Shao, Lei Cheng, Xiaoming Chen, Chongwen Huang, Derrick Wing Kwan Ng

Then, by associating the data sequences to multiple rank-one tensors and exploiting the angular sparsity of the RIS-BS channel, the detection problem is cast as a high-order coupled tensor decomposition problem without the need of exploiting pilot sequences.

Tensor Decomposition Variational Inference

Rethinking Bayesian Learning for Data Analysis: The Art of Prior and Inference in Sparsity-Aware Modeling

no code implementations28 May 2022 Lei Cheng, Feng Yin, Sergios Theodoridis, Sotirios Chatzis, Tsung-Hui Chang

However, a come back of Bayesian methods is taking place that sheds new light on the design of deep neural networks, which also establish firm links with Bayesian models and inspire new paths for unsupervised learning, such as Bayesian tensor decomposition.

Gaussian Processes Tensor Decomposition +1

Downlink Channel Covariance Matrix Reconstruction for FDD Massive MIMO Systems with Limited Feedback

no code implementations2 Apr 2022 Kai Li, Ying Li, Lei Cheng, Qingjiang Shi, Zhi-Quan Luo

The downlink channel covariance matrix (CCM) acquisition is the key step for the practical performance of massive multiple-input and multiple-output (MIMO) systems, including beamforming, channel tracking, and user scheduling.


Bayesian Low-rank Matrix Completion with Dual-graph Embedding: Prior Analysis and Tuning-free Inference

no code implementations18 Mar 2022 Yangge Chen, Lei Cheng, Yik-Chung Wu

Recently, there is a revival of interest in low-rank matrix completion-based unsupervised learning through the lens of dual-graph regularization, which has significantly improved the performance of multidisciplinary machine learning tasks such as recommendation systems, genotype imputation and image inpainting.

Graph Embedding Image Inpainting +4

Towards Tailored Models on Private AIoT Devices: Federated Direct Neural Architecture Search

no code implementations23 Feb 2022 Chunhui Zhang, Xiaoming Yuan, Qianyun Zhang, Guangxu Zhu, Lei Cheng, Ning Zhang

To further adapt to both various data distributions and different types of devices with heterogeneous embedded hardware platforms, inspired by meta-learning, a Cluster Federated Direct Neural Architecture Search (CFDNAS) framework is proposed to achieve device-aware NAS, in the sense that each device can learn a tailored deep learning model for its particular data distribution and hardware constraint.

Federated Learning Meta-Learning +1

Tensor-based Basis Function Learning for Three-dimensional Sound Speed Fields

no code implementations21 Jan 2022 Lei Cheng, Xingyu Ji, Hangfang Zhao, Jianlong Li, Wen Xu

In particular, a tensor-based basis function learning framework is proposed, which can include the classical basis functions (using EOFs and/or Fourier basis functions) as its special cases.

Tensor Decomposition

RecGURU: Adversarial Learning of Generalized User Representations for Cross-Domain Recommendation

1 code implementation19 Nov 2021 Chenglin Li, Mingjun Zhao, Huanming Zhang, Chenyun Yu, Lei Cheng, Guoqiang Shu, Beibei Kong, Di Niu

The learned GUR captures the overall preferences and characteristics of a user and thus can be used to augment the behavior data and improve recommendations in any single domain in which the user is involved.

Sequential Recommendation

Sparse Factorization of Large Square Matrices

1 code implementation16 Sep 2021 Ruslan Khalitov, Tong Yu, Lei Cheng, Zhirong Yang

The sparse factorization method is tested for a variety of synthetic and real-world square matrices.

Long-range modeling

Similarity Embedding Networks for Robust Human Activity Recognition

no code implementations31 May 2021 Chenglin Li, Carrie Lu Tong, Di Niu, Bei Jiang, Xiao Zuo, Lei Cheng, Jian Xiong, Jianming Yang

Deep learning models for human activity recognition (HAR) based on sensor data have been heavily studied recently.

Human Activity Recognition

Towards Overfitting Avoidance: Tuning-free Tensor-aided Multi-user Channel Estimation for 3D Massive MIMO Communications

no code implementations24 Jan 2021 Lei Cheng, Qingjiang Shi

Channel estimation has long been deemed as one of the most critical problems in three-dimensional (3D) massive multiple-input multiple-output (MIMO), which is recognized as the leading technology that enables 3D spatial signal processing in the fifth-generation (5G) wireless communications and beyond.

Tensor Decomposition

FDNAS: Improving Data Privacy and Model Diversity in AutoML

no code implementations6 Nov 2020 Chunhui Zhang, Yongyuan Liang, Xiaoming Yuan, Lei Cheng

To further adapt for various data distributions of clients, inspired by meta-learning, a cluster Federated Direct Neural Architecture Search (CFDNAS) framework is proposed to achieve client-aware NAS, in the sense that each client can learn a tailored deep learning model for its particular data distribution.

Federated Learning Meta-Learning +1

Pushing The Limit of Type I Codebook For FDD Massive MIMO Beamforming: A Channel Covariance Reconstruction Approach

no code implementations22 Oct 2020 Kai Li, Ying Li, Lei Cheng, Qingjiang Shi, Zhi-Quan Luo

There is a fundamental trade-off between the channel representation resolution of codebooks and the overheads of feedback communications in the fifth generation new radio (5G NR) frequency division duplex (FDD) massive multiple-input and multiple-output (MIMO) systems.

Vocal Bursts Type Prediction

Tensor Train Factorization and Completion under Noisy Data with Prior Analysis and Rank Estimation

no code implementations13 Oct 2020 Le Xu, Lei Cheng, Ngai Wong, Yik-Chung Wu

Tensor train (TT) decomposition, a powerful tool for analyzing multidimensional data, exhibits superior performance in many machine learning tasks.

Image Classification Variational Inference

Edge Learning with Unmanned Ground Vehicle: Joint Path, Energy and Sample Size Planning

no code implementations7 Sep 2020 Dan Liu, Shuai Wang, Zhigang Wen, Lei Cheng, Miaowen Wen, Yik-Chung Wu

However, different devices may transmit different data for different machine learning jobs and a fundamental question is how to jointly plan the UGV path, the devices' energy consumption, and the number of samples for different jobs?

BIG-bench Machine Learning Edge-computing

Modeling the Biological Pathology Continuum with HSIC-regularized Wasserstein Auto-encoders

no code implementations20 Jan 2019 Denny Wu, Hirofumi Kobayashi, Charles Ding, Lei Cheng, Keisuke Goda Marzyeh Ghassemi

A crucial challenge in image-based modeling of biomedical data is to identify trends and features that separate normality and pathology.

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