1.4k citations · 3k across the 30 of their papers we have counts for
13 papers · 1 filter
Efficient Low Rank Attention for Long-Context Inference in Large Language Models
Tenghui Li, Guoxu Zhou, Xuyang Zhao +2
As the length of input text increases, the key-value (KV) cache in LLMs imposes prohibitive GPU memory costs and limits long-context inference on resource constrained devices. Exis…
tnGPS: Discovering Unknown Tensor Network Structure Search Algorithms via Large Language Models (LLMs)
Junhua Zeng, Chao Li, Zhun Sun +2
Tensor networks are efficient for extremely high-dimensional representation, but their model selection, known as tensor network structure search (TN-SS), is a challenging problem.…
Semi-supervised multi-view concept decomposition
Qi Jiang, Guoxu Zhou, Qibin Zhao
Concept Factorization (CF), as a novel paradigm of representation learning, has demonstrated superior performance in multi-view clustering tasks. It overcomes limitations such as t…
Transformed Low-Rank Parameterization Can Help Robust Generalization for Tensor Neural Networks
Andong Wang, Chao Li, Mingyuan Bai +3
Achieving efficient and robust multi-channel data learning is a challenging task in data science. By exploiting low-rankness in the transformed domain, i.e., transformed low-rankne…
Towards Efficient and Accurate Approximation: Tensor Decomposition Based on Randomized Block Krylov Iteration
Yichun Qiu, Weijun Sun, Guoxu Zhou +1
Efficient and accurate low-rank approximation (LRA) methods are of great significance for large-scale data analysis. Randomized tensor decompositions have emerged as powerful tools…
Latent Matrices for Tensor Network Decomposition and to Tensor Completion
Peilin Yang, Weijun Sun, Qibin Zhao +1
The prevalent fully-connected tensor network (FCTN) has achieved excellent success to compress data. However, the FCTN decomposition suffers from slow computational speed when faci…
A high-order tensor completion algorithm based on Fully-Connected Tensor Network weighted optimization
Peilin Yang, Yonghui Huang, Yuning Qiu +2
Tensor completion aimes at recovering missing data, and it is one of the popular concerns in deep learning and signal processing. Among the higher-order tensor decomposition algori…
Bayesian Robust Tensor Ring Model for Incomplete Multiway Data
Zhenhao Huang, Yuning Qiu, Xinqi Chen +2
Robust tensor completion (RTC) aims to recover a low-rank tensor from its incomplete observation with outlier corruption. The recently proposed tensor ring (TR) model has demonstra…
Efficient Tensor Robust PCA under Hybrid Model of Tucker and Tensor Train
Yuning Qiu, Guoxu Zhou, Zhenhao Huang +2
Tensor robust principal component analysis (TRPCA) is a fundamental model in machine learning and computer vision. Recently, tensor train (TT) decomposition has been verified effec…
Toward Understanding Convolutional Neural Networks from Volterra Convolution Perspective
Tenghui Li, Guoxu Zhou, Yuning Qiu +1
We make an attempt to understanding convolutional neural network by exploring the relationship between (deep) convolutional neural networks and Volterra convolutions. We propose a…
Fast Hypergraph Regularized Nonnegative Tensor Ring Factorization Based on Low-Rank Approximation
Xinhai Zhao, Yuyuan Yu, Guoxu Zhou +2
For the high dimensional data representation, nonnegative tensor ring (NTR) decomposition equipped with manifold learning has become a promising model to exploit the multi-dimensio…
Deep Approximately Orthogonal Nonnegative Matrix Factorization for Clustering
Yuning Qiu, Guoxu Zhou, Kan Xie
Nonnegative Matrix Factorization (NMF) is a widely used technique for data representation. Inspired by the expressive power of deep learning, several NMF variants equipped with dee…
Efficient Nonnegative Tucker Decompositions: Algorithms and Uniqueness
Guoxu Zhou, Andrzej Cichocki, Qibin Zhao +1
Nonnegative Tucker decomposition (NTD) is a powerful tool for the extraction of nonnegative parts-based and physically meaningful latent components from high-dimensional tensor dat…