arXiv subjects

Linxin Guo

Publications and source records attributed to Linxin Guo.

4 recordsLinked to original sources

arXiv2024

Consistency and Discrepancy-Based Contrastive Tripartite Graph Learning for Recommendations

Tripartite graph-based recommender systems markedly diverge from traditional models by recommending unique combinations such as user groups and item bundles. Despite their effectiveness, these systems exacerbate the longstanding cold-start problem in traditional recommender systems, because any number of user groups or item bundles can be formed among users or items. To address this issue, we introduce a Consistency and Discrepancy-based graph contrastive learning method for tripartite graph-based Recommendation. This approach leverages two novel meta-path-based metrics consistency and discrepancy to capture nuanced, implicit associations between the recommended objects and the recommendees. These metrics, indicative of high-order similarities, can be efficiently calculated with infinite graph convolutional networks layers under a multi-objective optimization framework, using the limit theory of GCN.

cs.IR↗

arXiv2023

Deep learning inter-atomic potential for irradiation damage in 3C-SiC

We developed and validated an accurate inter-atomic potential for molecular dynamics simulation in cubic silicon carbide (3C-SiC) using a deep learning framework combined with smooth Ziegler-Biersack-Littmark (ZBL) screened nuclear repulsion potential interpolation. Comparisons of multiple important properties were made between the deep-learning potential and existing analytical potentials which are most commonly used in molecular dynamics simulations of 3C-SiC. Not only for equilibrium properties but also for significant properties of radiation damage such as defect formation energies and threshold displacement energies, our deep-learning potential gave closer predictions to DFT criterion than analytical potentials. The deep-learning potential framework solved the long-standing dilemma that traditional empirical potentials currently applied in 3C-SiC radiation damage simulations gave large disparities with each other and were inconsistent with ab-initio calculations. A more realistic depiction of the primary irradiation damage process in 3C-SiC can be given and the accuracy of classical molecular dynamics simulation for cubic silicon carbide can be expected to the level of quantum mechanics.

cond-mat.mtrl-sci↗

arXiv2022

Efficient Bi-Level Optimization for Recommendation Denoising

The acquisition of explicit user feedback (e.g., ratings) in real-world recommender systems is often hindered by the need for active user involvement. To mitigate this issue, implicit feedback (e.g., clicks) generated during user browsing is exploited as a viable substitute. However, implicit feedback possesses a high degree of noise, which significantly undermines recommendation quality. While many methods have been proposed to address this issue by assigning varying weights to implicit feedback, two shortcomings persist: (1) the weight calculation in these methods is iteration-independent, without considering the influence of weights in previous iterations, and (2) the weight calculation often relies on prior knowledge, which may not always be readily available or universally applicable. To overcome these two limitations, we model recommendation denoising as a bi-level optimization problem. The inner optimization aims to derive an effective model for the recommendation, as well as guiding the weight determination, thereby eliminating the need for prior knowledge. The outer optimization leverages gradients of the inner optimization and adjusts the weights in a manner considering the impact of previous weights. To efficiently solve this bi-level optimization problem, we employ a weight generator to avoid the storage of weights and a one-step gradient-matching-based loss to significantly reduce computational time. The experimental results on three benchmark datasets demonstrate that our proposed approach outperforms both state-of-the-art general and denoising recommendation models. The code is available at https://github.com/CoderWZW/BOD.

cs.IR↗

arXiv2022

A Radiation Tolerant Proton Detector Based on MAPbBr3 single crystal

The performance and radiation tolerance of the proton detector based on MAPbBr3 perovskite single crystal are investigated here with 3MeV protons. The detector can monitor fluence rate and dose quantificationally at a low applied bias electric field(0.01$V/{\mu}m$) within a dose range of 45 kGy. The detector can also be worked at zero bias due to the Dember effect. The dark current of the detector reduced to 20% of the initial value after being irradiated with protons to a total fluence of $7.3\times 10^{13} p/cm^2$ (1 MGy), however, it can be recovered at room temperature within hours. These results suggest that this kind of detector has a promising application in proton therapy and proton imaging etc.

physics.ins-det↗