Notice: The reproducibility variables underlying each score are classified using an automated LLM-based pipeline, validated against a manually labeled dataset. LLM-based classification introduces uncertainty and potential bias; scores should be interpreted as estimates. Full accuracy metrics and methodology are described in Coakley et alK. L. Coakley, T. Snelleman, H. Hoos, and O. E. Gundersen, "The embrace of open science: An analysis of a decade of AI research and 56 800 conference papers," Under Review, 2026..

Gaussian Regression-Driven Tensorized Incomplete Multi-View Clustering with Dual Manifold Regularization

Authors: Zhenhao Zhong, Zhibin Gu, Pengpeng Yang, Yaqian zhou, Ruiqiang Guo

NeurIPS 2025 | Venue PDF | LLM Run Details

Reproducibility Variable Result LLM Response
Research Type Experimental Extensive experiments on six datasets demonstrate that our method outperforms SOTA approaches.
Researcher Affiliation Academia 1College of Computer and Cyber Security, Hebei Normal University, China 2College of computer and Information Technology, China Three Gorges University, China
Pseudocode Yes Algorithm 1 Optimization Algorithm of GUITAR
Open Source Code Yes The code is available at https://github.com/Rockfire Tip/GUITAR.
Open Datasets Yes We conduct experiments on six datasets: Yale3 [40], MSRC_v1 [41], EYale B10 [42], COIL20MV, Mfeat [43], and Scene [44].
Dataset Splits No The paper describes how incomplete multi-view data is constructed by randomly setting a fraction of samples to zero (missing rates r = {0.1, 0.3, 0.5}), which defines experimental conditions. However, it does not specify explicit training, validation, or test dataset splits in the conventional machine learning sense for model learning or evaluation.
Hardware Specification Yes All experiments are conducted in MATLAB R2023b on a machine equipped with a 2.30 GHz i7-12650H CPU and 16GB RAM.
Software Dependencies Yes All experiments are conducted in MATLAB R2023b on a machine equipped with a 2.30 GHz i7-12650H CPU and 16GB RAM.
Experiment Setup Yes For our method, we search for the optimal values of λ1, λ2, and λ3 from the set {10 3, 10 2, 10 1, 100, 101}, while δ is tuned over {10 3, 10 2, 10 1, 100}. ACC is used as the evaluation criterion. As illustrated in Figure 2, the performance on the Mfeat dataset remains consistently stable when λ1, λ2, and λ3 are chosen from {10 3, 10 2, 10 1}. Algorithm 1 ... 1: Initialize: v, Zv = 1, Ev = 0, Yv = 0, G = 0, Q = 0, µ = 10 4, ρ = 10 4, ηµ = ηρ = 1.2, µmax = ρmax = 1012, ϵ = 10 7