Deep Transfer Tensor Decomposition with Orthogonal Constraint for Recommender Systems

Chen, Zhengyu; Xu, Ziqing; Wang, Donglin

doi:10.1609/aaai.v35i5.16521

Cited by 33 publications

(8 citation statements)

References 32 publications

Supporting

Mentioning

Contrasting

Unclassified

Order By: Relevance

“…Evaluation Metrics. For offline evaluation, we employ top-k Hit Ratio (HR@k) and Normalized Discounted Cumulative Gain (NDCG@k) to evaluate the performance, which are widely used in related works (Chen, Wang, and Yin 2021;Chen, Xu, and Wang 2021;Chen, Gai, and Wang 2019;Xiao and Shen 2019). We report results on HR (H)@{5, 10} and NDCG (N)@{5, 10}.…”

Section: Methodsmentioning

confidence: 99%

A General Offline Reinforcement Learning Framework for Interactive Recommendation

Xiao

Wang

2021

AAAI

Self Cite

View full text Add to dashboard Cite

This paper studies the problem of learning interactive recommender systems from logged feedbacks without any exploration in online environments. We address the problem by proposing a general offline reinforcement learning framework for recommendation, which enables maximizing cumulative user rewards without online exploration. Specifically, we first introduce a probabilistic generative model for interactive recommendation, and then propose an effective inference algorithm for discrete and stochastic policy learning based on logged feedbacks. In order to perform offline learning more effectively, we propose five approaches to minimize the distribution mismatch between the logging policy and recommendation policy: support constraints, supervised regularization, policy constraints, dual constraints and reward extrapolation. We conduct extensive experiments on two public real-world datasets, demonstrating that the proposed methods can achieve superior performance over existing supervised learning and reinforcement learning methods for recommendation.

show abstract

Section: Methodsmentioning

confidence: 99%

A General Offline Reinforcement Learning Framework for Interactive Recommendation

Xiao

Wang

2021

AAAI

Self Cite

View full text Add to dashboard Cite

show abstract

“…We propose a novel encoder-decoder network in USTN for deep tensor decomposition and incorporate side information. As compensation for spectral sparsity of HSIs [5], the symmetric tensor framework in USTN is realizing by vertical spatial and horizontal spatial feature module. The structure of two spatial feature modules is encoder-decoder built by Tensor Factorization Network (TFNN).…”

Section: Symmetric Structurementioning

confidence: 99%

An unsupervised symmetric tensor network for change detection in multitemporal hyperspectral images

Liang

Chen²

2023

Earth and Space: From Infrared to Terahertz (ESIT 2022)

View full text Add to dashboard Cite

Since Hyperspectral images (HSIs) contain a large amount of spectral information, they can provide detailed spectral information and enable accurate CD. However, the spectral heterogeneity of HSIs may lead to false alarms which will reduce detection accuracy. Additionally, it is difficult to collect and annotate pixel-level labels for CD in HSIs. Therefore, we propose an unsupervised symmetric tensor network (USTN) for HSIs CD. We design a novel multidimensional symmetric tensor framework to solve the problem of high-dimensional data processing. Furthermore, the framework integrates a spatial edge loss to preserve detailed spectral-spatial information. Finally, we use feature fusion to suppress the invariant components (i.e., the background) and highlight the variant components (i.e., temporal changes). Experiments on two sets of multitemporal HSIs, Hermiston and Bay Area, demonstrate the effectiveness of USTN for binary change detection.

show abstract

“…Factor Matrix A (1) Factor Matrix A (2) Factor Matrix A (3) Input Tensor ! b1 (1) b1 (2) b1 (3) b2 (1) b2 (2) b2 (3) bR (1) bR (2) bR (3)…”

Section: Core Tensorunclassified

“…The tensor decomposition, which uses multiple lowrank feature matrices or tensors to represent the original tensor and preserves the multi-order structural information of the original tensor, emerges as the times require. At present, tensor methods based on tensor decomposition have been widely used in recommender system [3], social network [4], psychological testing [5], biology [6], stoichiometry [7], cryptography [8], signal processing [9], deep learning [10], [11], numerical analysis [12] and other fields.…”

Section: Introductionmentioning

confidence: 99%

cuFasterTucker: A Stochastic Optimization Strategy for Parallel Sparse FastTucker Decomposition on GPU Platform

Li¹

2022

Preprint

View full text Add to dashboard Cite

Currently, the size of scientific data is growing at an unprecedented rate. Data in the form of tensors exhibit high-order, high-dimensional, and highly sparse features. Although tensor-based analysis methods are very effective, the large increase in data size makes the original tensor impossible to process. Tensor decomposition decomposes a tensor into multiple low-rank matrices or tensors that can be exploited by tensor-based analysis methods. Tucker decomposition is such an algorithm, which decomposes a n-order tensor into n low-rank factor matrices and a low-rank core tensor. However, most Tucker decomposition methods are accompanied by huge intermediate variables and huge computational load, making them unable to process high-order and high-dimensional tensors.In this paper, we propose FasterTucker decomposition based on FastTucker decomposition, which is a variant of Tucker decomposition. And an efficient parallel FasterTucker decomposition algorithm cuFasterTucker on GPU platform is proposed. It has very low storage and computational requirements, and effectively solves the problem of high-order and high-dimensional sparse tensor decomposition. Compared with the state-of-theart algorithm, it achieves a speedup of around 15X and 7X in updating the factor matrices and updating the core matrices, respectively.

show abstract

Deep Transfer Tensor Decomposition with Orthogonal Constraint for Recommender Systems

Cited by 33 publications

References 32 publications

A General Offline Reinforcement Learning Framework for Interactive Recommendation

A General Offline Reinforcement Learning Framework for Interactive Recommendation

An unsupervised symmetric tensor network for change detection in multitemporal hyperspectral images

cuFasterTucker: A Stochastic Optimization Strategy for Parallel Sparse FastTucker Decomposition on GPU Platform

Contact Info

Product

Resources

About