MOE-Enhanced Explanable Deep Manifold Transformation for Complex Data Embedding and Visualization

• URL: http://arxiv.org/abs/2410.19504v2
• Date: Sun, 29 Jun 2025 13:59:31 GMT
• Title: MOE-Enhanced Explanable Deep Manifold Transformation for Complex Data Embedding and Visualization
• Authors: Zelin Zang, Yuhao Wang, Jinlin Wu, Hong Liu, Yue Shen, Zhen Lei, Stan. Z Li,
• Abstract summary: Dimensionality reduction (DR) plays a crucial role in various fields, including data engineering and visualization.<n>DR methods face a trade-off between precision and transparency, where optimizing for performance can lead to reduced explainability.<n>This work introduces the MOE-based Explainable Deep Manifold Transformation (DMT-ME)
• Score: 47.4136073281818
• License: http://creativecommons.org/licenses/by/4.0/
• Abstract: Dimensionality reduction (DR) plays a crucial role in various fields, including data engineering and visualization, by simplifying complex datasets while retaining essential information. However, achieving both high DR accuracy and strong explainability remains a fundamental challenge, especially for users dealing with high-dimensional data. Traditional DR methods often face a trade-off between precision and transparency, where optimizing for performance can lead to reduced explainability, and vice versa. This limitation is especially prominent in real-world applications such as image, tabular, and text data analysis, where both accuracy and explainability are critical. To address these challenges, this work introduces the MOE-based Explainable Deep Manifold Transformation (DMT-ME). The proposed approach combines hyperbolic embeddings, which effectively capture complex hierarchical structures, with Mixture of Experts (MOE) models, which dynamically allocate tasks based on input features. DMT-ME enhances DR accuracy by leveraging hyperbolic embeddings to represent the hierarchical nature of data, while also improving explainability by explicitly linking input data, embedding outcomes, and key features through the MOE structure. Extensive experiments demonstrate that DMT-ME consistently achieves superior performance in both DR accuracy and model explainability, making it a robust solution for complex data analysis. The code is available at https://github.com/zangzelin/code_dmtme

Related papers

• Dataset-Adaptive Dimensionality Reduction [11.180683480772373]
  We propose a dataset-adaptive approach to dimensionality reduction (DR) optimization guided by structural complexity metrics.<n>These metrics quantify the intrinsic complexity of a dataset, predicting whether higher-dimensional spaces are necessary to represent it accurately.<n>We empirically show that our dataset-adaptive workflow significantly enhances the efficiency of DR optimization without compromising accuracy.
  arXiv  Detail & Related papers  (2025-07-16T07:32:08Z)
• Capacity Matters: a Proof-of-Concept for Transformer Memorization on Real-World Data [6.885357232728911]
  This paper studies how the model architecture and data configurations influence the empirical memorization capacity of generative transformers.<n>The models are trained using synthetic text datasets derived from the Systematized Nomenclature of Medicine (SNOMED)
  arXiv  Detail & Related papers  (2025-06-17T16:42:54Z)
• Multi-Modal Dataset Distillation in the Wild [75.64263877043615]
  We propose Multi-modal dataset Distillation in the Wild, i.e., MDW, to distill noisy multi-modal datasets into compact clean ones for effective and efficient model training.<n>Specifically, MDW introduces learnable fine-grained correspondences during distillation and adaptively optimize distilled data to emphasize correspondence-discriminative regions.<n>Extensive experiments validate MDW's theoretical and empirical efficacy with remarkable scalability, surpassing prior methods by over 15% across various compression ratios.
  arXiv  Detail & Related papers  (2025-06-02T12:18:20Z)
• RefiDiff: Refinement-Aware Diffusion for Efficient Missing Data Imputation [13.401822039640297]
  Missing values in high-dimensional, mixed-type datasets pose significant challenges for data imputation.<n>We propose an innovative framework, RefiDiff, combining local machine learning predictions with a novel Mamba-based denoising network.<n>RefiDiff outperforms state-the-art (SOTA) methods across missing-value settings with a 4x faster training time than DDPM-based approaches.
  arXiv  Detail & Related papers  (2025-05-20T14:51:07Z)
• SCENT: Robust Spatiotemporal Learning for Continuous Scientific Data via Scalable Conditioned Neural Fields [11.872753517172555]
  We present SCENT, a novel framework for scalable and continuity-informed modeling learning.<n>SCENT unifies representation, reconstruction, and forecasting within a single architecture.<n>We validate SCENT through extensive simulations and real-world experiments, demonstrating state-of-the-art performance.
  arXiv  Detail & Related papers  (2025-04-16T17:17:31Z)
• Hybrid machine learning models based on physical patterns to accelerate CFD simulations: a short guide on autoregressive models [3.780691701083858]
  This study presents an innovative integration of High-Order Singular Value Decomposition with Long Short-Term Memory (LSTM) architectures to address the complexities of reduced-order modeling (ROM) in fluid dynamics. The methodology is tested across numerical and experimental data sets, including two- and three-dimensional (2D and 3D) cylinder wake flows, spanning both laminar and turbulent regimes. The results demonstrate that HOSVD outperforms SVD in all tested scenarios, as evidenced by using different error metrics.
  arXiv  Detail & Related papers  (2025-04-09T10:56:03Z)
• Physically Interpretable Representation and Controlled Generation for Turbulence Data [39.42376941186934]
  This paper proposes a data-driven approach to encode high-dimensional scientific data into low-dimensional, physically meaningful representations. We validate our approach using 2D Navier-Stokes simulations of flow past a cylinder over a range of Reynolds numbers.
  arXiv  Detail & Related papers  (2025-01-31T17:51:14Z)
• PolSAM: Polarimetric Scattering Mechanism Informed Segment Anything Model [76.95536611263356]
  PolSAR data presents unique challenges due to its rich and complex characteristics. Existing data representations, such as complex-valued data, polarimetric features, and amplitude images, are widely used. Most feature extraction networks for PolSAR are small, limiting their ability to capture features effectively. We propose the Polarimetric Scattering Mechanism-Informed SAM (PolSAM), an enhanced Segment Anything Model (SAM) that integrates domain-specific scattering characteristics and a novel prompt generation strategy.
  arXiv  Detail & Related papers  (2024-12-17T09:59:53Z)
• Towards a Theoretical Understanding of Memorization in Diffusion Models [76.85077961718875]
  Diffusion probabilistic models (DPMs) are being employed as mainstream models for Generative Artificial Intelligence (GenAI) We provide a theoretical understanding of memorization in both conditional and unconditional DPMs under the assumption of model convergence. We propose a novel data extraction method named textbfSurrogate condItional Data Extraction (SIDE) that leverages a time-dependent classifier trained on the generated data as a surrogate condition to extract training data from unconditional DPMs.
  arXiv  Detail & Related papers  (2024-10-03T13:17:06Z)
• A Framework for Fine-Tuning LLMs using Heterogeneous Feedback [69.51729152929413]
  We present a framework for fine-tuning large language models (LLMs) using heterogeneous feedback. First, we combine the heterogeneous feedback data into a single supervision format, compatible with methods like SFT and RLHF. Next, given this unified feedback dataset, we extract a high-quality and diverse subset to obtain performance increases.
  arXiv  Detail & Related papers  (2024-08-05T23:20:32Z)
• MDM: Advancing Multi-Domain Distribution Matching for Automatic Modulation Recognition Dataset Synthesis [35.07663680944459]
  Deep learning technology has been successfully introduced into Automatic Modulation Recognition (AMR) tasks. The success of deep learning is all attributed to the training on large-scale datasets. In order to solve the problem of large amount of data, some researchers put forward the method of data distillation.
  arXiv  Detail & Related papers  (2024-08-05T14:16:54Z)
• Discovering symbolic expressions with parallelized tree search [59.92040079807524]
  Symbolic regression plays a crucial role in scientific research thanks to its capability of discovering concise and interpretable mathematical expressions from data. Existing algorithms have faced a critical bottleneck of accuracy and efficiency over a decade when handling problems of complexity. We introduce a parallelized tree search (PTS) model to efficiently distill generic mathematical expressions from limited data.
  arXiv  Detail & Related papers  (2024-07-05T10:41:15Z)
• Memory-efficient High-resolution OCT Volume Synthesis with Cascaded Amortized Latent Diffusion Models [48.87160158792048]
  We introduce a cascaded amortized latent diffusion model (CA-LDM) that can synthesis high-resolution OCT volumes in a memory-efficient way. Experiments on a public high-resolution OCT dataset show that our synthetic data have realistic high-resolution and global features, surpassing the capabilities of existing methods.
  arXiv  Detail & Related papers  (2024-05-26T10:58:22Z)
• Modality Prompts for Arbitrary Modality Salient Object Detection [57.610000247519196]
  This paper delves into the task of arbitrary modality salient object detection (AM SOD) It aims to detect salient objects from arbitrary modalities, eg RGB images, RGB-D images, and RGB-D-T images. A novel modality-adaptive Transformer (MAT) will be proposed to investigate two fundamental challenges of AM SOD.
  arXiv  Detail & Related papers  (2024-05-06T11:02:02Z)
• Disentangled Representation Learning with Transmitted Information Bottleneck [57.22757813140418]
  We present textbfDisTIB (textbfTransmitted textbfInformation textbfBottleneck for textbfDisd representation learning), a novel objective that navigates the balance between information compression and preservation.
  arXiv  Detail & Related papers  (2023-11-03T03:18:40Z)
• Learning in latent spaces improves the predictive accuracy of deep neural operators [0.0]
  L-DeepONet is an extension of standard DeepONet, which leverages latent representations of high-dimensional PDE input and output functions identified with suitable autoencoders. We show that L-DeepONet outperforms the standard approach in terms of both accuracy and computational efficiency across diverse time-dependent PDEs.
  arXiv  Detail & Related papers  (2023-04-15T17:13:09Z)
• DBT-DMAE: An Effective Multivariate Time Series Pre-Train Model under Missing Data [16.589715330897906]
  MTS suffers from missing data problems, which leads to degradation or collapse of the downstream tasks. This paper presents a universally applicable MTS pre-train model,. -DMAE, to conquer the abovementioned obstacle.
  arXiv  Detail & Related papers  (2022-09-16T08:54:02Z)
• Feature Learning for Dimensionality Reduction toward Maximal Extraction of Hidden Patterns [25.558967594684056]
  Dimensionality reduction (DR) plays a vital role in the visual analysis of high-dimensional data. This paper presents a feature learning framework, FEALM, designed to generate an optimized set of data projections for nonlinear DR. We develop interactive visualizations to assist comparison of obtained DR results and interpretation of each DR result.
  arXiv  Detail & Related papers  (2022-06-28T11:18:19Z)
• Residual Dynamic Mode Decomposition: Robust and verified Koopmanism [0.0]
  Dynamic Mode Decomposition (DMD) describes complex dynamic processes through a hierarchy of simpler coherent features. We present Residual Dynamic Mode Decomposition (ResDMD), which overcomes challenges through the data-driven computation of residuals associated with the full infinite-dimensional Koopman operator. ResDMD computes spectra and pseudospectra of general Koopman operators with error control, and computes smoothed approximations of spectral measures (including continuous spectra) with explicit high-order convergence theorems.
  arXiv  Detail & Related papers  (2022-05-19T18:02:44Z)

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.