Double-Stage Feature-Level Clustering-Based Mixture of Experts Framework

• URL: http://arxiv.org/abs/2503.09504v1
• Date: Wed, 12 Mar 2025 16:13:50 GMT
• Title: Double-Stage Feature-Level Clustering-Based Mixture of Experts Framework
• Authors: Bakary Badjie, José Cecílio, António Casimiro,
• Abstract summary: This paper introduces the Double-stage Feature-level Clustering and Pseudo-labeling-based Mixture of Experts (DFCP-MoE) framework.<n>It consists of input feature extraction, feature-level clustering, and a computationally efficient pseudo-labeling strategy.<n>We propose a conditional end-to-end joint training method that improves expert specialization by training the MoE model on well-labeled, clustered inputs.
• Score: 0.0
• License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
• Abstract: The Mixture-of-Experts (MoE) model has succeeded in deep learning (DL). However, its complex architecture and advantages over dense models in image classification remain unclear. In previous studies, MoE performance has often been affected by noise and outliers in the input space. Some approaches incorporate input clustering for training MoE models, but most clustering algorithms lack access to labeled data, limiting their effectiveness. This paper introduces the Double-stage Feature-level Clustering and Pseudo-labeling-based Mixture of Experts (DFCP-MoE) framework, which consists of input feature extraction, feature-level clustering, and a computationally efficient pseudo-labeling strategy. This approach reduces the impact of noise and outliers while leveraging a small subset of labeled data to label a large portion of unlabeled inputs. We propose a conditional end-to-end joint training method that improves expert specialization by training the MoE model on well-labeled, clustered inputs. Unlike traditional MoE and dense models, the DFCP-MoE framework effectively captures input space diversity, leading to competitive inference results. We validate our approach on three benchmark datasets for multi-class classification tasks.

Related papers

• Segment Concealed Objects with Incomplete Supervision [63.637733655439334]
  Incompletely-Supervised Concealed Object (ISCOS) involves segmenting objects that seamlessly blend into their surrounding environments.<n>This task remains highly challenging due to the limited supervision provided by the incompletely annotated training data.<n>In this paper, we introduce the first unified method for ISCOS to address these challenges.
  arXiv  Detail & Related papers  (2025-06-10T16:25:15Z)
• Unbiased Max-Min Embedding Classification for Transductive Few-Shot Learning: Clustering and Classification Are All You Need [83.10178754323955]
  Few-shot learning enables models to generalize from only a few labeled examples. We propose the Unbiased Max-Min Embedding Classification (UMMEC) Method, which addresses the key challenges in few-shot learning. Our method significantly improves classification performance with minimal labeled data, advancing the state-of-the-art in annotatedL.
  arXiv  Detail & Related papers  (2025-03-28T07:23:07Z)
• Towards Learnable Anchor for Deep Multi-View Clustering [49.767879678193005]
  In this paper, we propose the Deep Multi-view Anchor Clustering (DMAC) model that performs clustering in linear time. With the optimal anchors, the full sample graph is calculated to derive a discriminative embedding for clustering. Experiments on several datasets demonstrate superior performance and efficiency of DMAC compared to state-of-the-art competitors.
  arXiv  Detail & Related papers  (2025-03-16T09:38:11Z)
• Collaborative Feature-Logits Contrastive Learning for Open-Set Semi-Supervised Object Detection [75.02249869573994]
  In open-set scenarios, the unlabeled dataset contains both in-distribution (ID) classes and out-of-distribution (OOD) classes.<n>Applying semi-supervised detectors in such settings can lead to misclassifying OOD class as ID classes.<n>We propose a simple yet effective method, termed Collaborative Feature-Logits Detector (CFL-Detector)
  arXiv  Detail & Related papers  (2024-11-20T02:57:35Z)
• Dual-Decoupling Learning and Metric-Adaptive Thresholding for Semi-Supervised Multi-Label Learning [81.83013974171364]
  Semi-supervised multi-label learning (SSMLL) is a powerful framework for leveraging unlabeled data to reduce the expensive cost of collecting precise multi-label annotations.<n>Unlike semi-supervised learning, one cannot select the most probable label as the pseudo-label in SSMLL due to multiple semantics contained in an instance.<n>We propose a dual-perspective method to generate high-quality pseudo-labels.
  arXiv  Detail & Related papers  (2024-07-26T09:33:53Z)
• Generalized Category Discovery with Clustering Assignment Consistency [56.92546133591019]
  Generalized category discovery (GCD) is a recently proposed open-world task. We propose a co-training-based framework that encourages clustering consistency. Our method achieves state-of-the-art performance on three generic benchmarks and three fine-grained visual recognition datasets.
  arXiv  Detail & Related papers  (2023-10-30T00:32:47Z)
• Evaluation of Confidence-based Ensembling in Deep Learning Image Classification [0.6445605125467573]
  Conf-Ensemble is an adaptation to Boosting to create ensembles based on model confidence instead of model errors. We evaluate the Conf-Ensemble approach in the much more complex task of image classification with the ImageNet dataset.
  arXiv  Detail & Related papers  (2023-03-03T16:29:22Z)
• Rethinking Clustering-Based Pseudo-Labeling for Unsupervised Meta-Learning [146.11600461034746]
  Method for unsupervised meta-learning, CACTUs, is a clustering-based approach with pseudo-labeling. This approach is model-agnostic and can be combined with supervised algorithms to learn from unlabeled data. We prove that the core reason for this is lack of a clustering-friendly property in the embedding space.
  arXiv  Detail & Related papers  (2022-09-27T19:04:36Z)
• Deep Conditional Gaussian Mixture Model for Constrained Clustering [7.070883800886882]
  Constrained clustering can leverage prior information on a growing amount of only partially labeled data. We propose a novel framework for constrained clustering that is intuitive, interpretable, and can be trained efficiently in the framework of gradient variational inference.
  arXiv  Detail & Related papers  (2021-06-11T13:38:09Z)

This list is automatically generated from the titles and abstracts of the papers in this site.

This site does not guarantee the quality of this site (including all information) and is not responsible for any consequences.