SCALAR: Self-Calibrating Adaptive Latent Attention Representation Learning

• URL: http://arxiv.org/abs/2510.16474v1
• Date: Sat, 18 Oct 2025 12:41:18 GMT
• Title: SCALAR: Self-Calibrating Adaptive Latent Attention Representation Learning
• Abstract summary: High-dimensional, heterogeneous data with complex feature interactions pose significant challenges for traditional predictive modeling approaches.<n>Our architecture introduces an adaptive kernel-based attention mechanism that processes distinct feature groups separately before integration.<n> Experimental results show substantial improvements in performance metrics, compared to the state-of-the-art methods across diverse datasets.
• Score: 2.152549977410309
• License: http://creativecommons.org/licenses/by/4.0/
• Abstract: High-dimensional, heterogeneous data with complex feature interactions pose significant challenges for traditional predictive modeling approaches. While Projection to Latent Structures (PLS) remains a popular technique, it struggles to model complex non-linear relationships, especially in multivariate systems with high-dimensional correlation structures. This challenge is further compounded by simultaneous interactions across multiple scales, where local processing fails to capture crossgroup dependencies. Additionally, static feature weighting limits adaptability to contextual variations, as it ignores sample-specific relevance. To address these limitations, we propose a novel method that enhances predictive performance through novel architectural innovations. Our architecture introduces an adaptive kernel-based attention mechanism that processes distinct feature groups separately before integration, enabling capture of local patterns while preserving global relationships. Experimental results show substantial improvements in performance metrics, compared to the state-of-the-art methods across diverse datasets.

Related papers

• A unified framework for global and local interpretability using adaptive derivative-ordered random explanation [2.6717072353469997]
  Post-hoc interpretability of complex machine learning models is of paramount importance, especially in real-world high-stakes domains such as healthcare and finance.<n>This paper provides a novel method - Adaptive Derivative-Ordered Random Explanation (ADORE) - that leverages first- and second-order derivatives to accommodate nonlinear model complexities.<n>ADORE integrates global feature importance with local sample contributions, precisely quantifying feature impact by capturing both magnitude and direction.<n>It achieves computational efficiency through randomized singular value decomposition (SVD) and dynamic sparsity detection, making it scalable to large, high-dimensional datasets.
  arXiv  Detail & Related papers  (2026-09-15T13:34:10Z)
• A Deep Latent Variable Framework for Jointly Modeling Missingness, Measurement Error, and Heterogeneity [1.2716195762843876]
  We propose a unified probabilistic framework that jointly addresses missing data, measurement error, and population heterogeneity.<n>The proposed method integrates a novel hierarchical tree-routed variational autoencoder with pattern-aware latent representations and calibration-based denoising.<n>The framework accommodates missing data mechanisms, including MCAR, MAR, and MNAR, while simultaneously learning subgroup-specific and globally shared latent structure.
  arXiv  Detail & Related papers  (2026-08-30T20:56:57Z)
• Structured Nonparametric Variational Inference for Dependent Latent Modeling [11.146941243243248]
  Variational inference (VI) is a core engine of modern AI, enabling scalable learning and uncertainty-aware training of large probabilistic and generative models.<n>We propose Structured Non Variational Inference (SN-VI), a novel framework for modeling complex dependencies among latent variables in posterior approximation.<n> SN-VI preserves intricate latent variable dependencies, providing a flexible and accurate approximation of posterior boundeds with arbitrary shapes.
  arXiv  Detail & Related papers  (2026-06-13T20:29:04Z)
• Graph Structured Combinatorial Semi-Bandit with Nonlinear Reward Associations through Separable Signals [9.51084845180104]
  We develop novel generic and adaptive strategies equipped with routines for graph-based causal reward modeling.<n>We establish theoretical performance guarantees sublinear in time and linear in data volume over time.<n>We conduct numerical experiments using both benchmarked synthetic and real-world transportation datasets.
  arXiv  Detail & Related papers  (2026-06-12T17:11:56Z)
• SPARD: Self-Paced Curriculum for RL Alignment via Integrating Reward Dynamics and Data Utility [71.76390626651254]
  We propose SPARD, a framework that establishes an automated, self-paced curriculum by perceiving learning progress to adjust dynamically multi-objective reward weights and data importance.<n>Extensive experiments across multiple benchmarks demonstrate that SPARD significantly enhances model capabilities across all domains.
  arXiv  Detail & Related papers  (2026-04-09T05:37:22Z)
• AlignMamba-2: Enhancing Multimodal Fusion and Sentiment Analysis with Modality-Aware Mamba [56.52470564147458]
  We propose textbfAlignMamba-2, an effective and efficient framework for multimodal fusion and sentiment analysis.<n>Our approach introduces a dual alignment strategy that regularizes the model using both Optimal Transport distance and Maximum Mean Discrepancy.<n>More importantly, we design a Modality-Aware Mamba layer, which employs a Mixture-of-Experts architecture with modality-specific and modality-shared experts.
  arXiv  Detail & Related papers  (2026-03-19T03:47:21Z)
• SEHFS: Structural Entropy-Guided High-Order Correlation Learning for Multi-View Multi-Label Feature Selection [32.73824178667282]
  We propose Structural Entropy Guided High-Order Correlation Learning for Multi-View Multi-Label Feature Selection (SEHFS)<n>SEHFS group features with strong high-order redundancy into a single cluster within the encoding tree.<n>New framework based on the fusion of information theory and matrix methods is adopted, which learns a shared semantic matrix and view-specific contribution to reconstruct a global view matrix.
  arXiv  Detail & Related papers  (2026-03-03T14:15:18Z)
• An Integrated Fusion Framework for Ensemble Learning Leveraging Gradient Boosting and Fuzzy Rule-Based Models [59.13182819190547]
  Fuzzy rule-based models excel in interpretability and have seen widespread application across diverse fields.<n>They face challenges such as complex design specifications and scalability issues with large datasets.<n>This paper proposes an Integrated Fusion Framework that merges the strengths of both paradigms to enhance model performance and interpretability.
  arXiv  Detail & Related papers  (2025-11-11T10:28:23Z)
• Improving Deepfake Detection with Reinforcement Learning-Based Adaptive Data Augmentation [60.04281435591454]
  CRDA (Curriculum Reinforcement-Learning Data Augmentation) is a novel framework guiding detectors to progressively master multi-domain forgery features.<n>Central to our approach is integrating reinforcement learning and causal inference.<n>Our method significantly improves detector generalizability, outperforming SOTA methods across multiple cross-domain datasets.
  arXiv  Detail & Related papers  (2025-11-10T12:45:52Z)
• High-Fidelity Scientific Simulation Surrogates via Adaptive Implicit Neural Representations [51.90920900332569]
  Implicit neural representations (INRs) offer a compact and continuous framework for modeling spatially structured data.<n>Recent approaches address this by introducing additional features along rigid geometric structures.<n>We propose a simple yet effective alternative: Feature-Adaptive INR (FA-INR)
  arXiv  Detail & Related papers  (2025-06-07T16:45:17Z)
• Neural Network Reprogrammability: A Unified Theme on Model Reprogramming, Prompt Tuning, and Prompt Instruction [57.19302613163439]
  We introduce neural network reprogrammability as a unifying framework for model adaptation.<n>We present a taxonomy that categorizes such information manipulation approaches across four key dimensions.<n>We also analyze remaining technical challenges and ethical considerations.
  arXiv  Detail & Related papers  (2025-06-05T05:42:27Z)
• A Unified Framework for Variable Selection in Model-Based Clustering with Missing Not at Random [6.19101012807196]
  This paper introduces a unified framework designed to address these challenges simultaneously.<n>Our approach incorporates a data-driven penalty matrix into clustering to enable more flexible variable selection.<n>We demonstrate that, under certain regularity, the proposed framework achieves both clustering consistency and consistency, even in the presence of missing data.
  arXiv  Detail & Related papers  (2025-05-25T11:08:43Z)
• Intrinsic Tensor Field Propagation in Large Language Models: A Novel Approach to Contextual Information Flow [0.0]
  Intrinsic Field propagation improves contextual retention, dependency resolution, and inference across various linguistic structures.<n>Experiments conducted on an open-source transformer-based model demonstrate that I provides measurable improvements in contextual retention, dependency resolution, and inference across various linguistic structures.
  arXiv  Detail & Related papers  (2025-01-31T08:32:32Z)
• Regularized Neural Ensemblers [55.15643209328513]
  In this study, we explore employing regularized neural networks as ensemble methods.<n>Motivated by the risk of learning low-diversity ensembles, we propose regularizing the ensembling model by randomly dropping base model predictions.<n>We demonstrate this approach provides lower bounds for the diversity within the ensemble, reducing overfitting and improving generalization capabilities.
  arXiv  Detail & Related papers  (2024-10-06T15:25:39Z)
• Generalization Bounds of Surrogate Policies for Combinatorial Optimization Problems [53.03951222945921]
  We analyze smoothed (perturbed) policies, adding controlled random perturbations to the direction used by the linear oracle.<n>Our main contribution is a generalization bound that decomposes the excess risk into perturbation bias, statistical estimation error, and optimization error.<n>We illustrate the scope of the results on applications such as vehicle scheduling, highlighting how smoothing enables both tractable training and controlled generalization.
  arXiv  Detail & Related papers  (2024-07-24T12:00:30Z)
• Semantic Correspondence with Transformers [68.37049687360705]
  We propose Cost Aggregation with Transformers (CATs) to find dense correspondences between semantically similar images. We include appearance affinity modelling to disambiguate the initial correlation maps and multi-level aggregation. We conduct experiments to demonstrate the effectiveness of the proposed model over the latest methods and provide extensive ablation studies.
  arXiv  Detail & Related papers  (2021-06-04T14:39:03Z)
• Top-$k$ Regularization for Supervised Feature Selection [11.927046591097623]
  We introduce a novel, simple yet effective regularization approach, named top-$k$ regularization, to supervised feature selection. We show that the top-$k$ regularization is effective and stable for supervised feature selection.
  arXiv  Detail & Related papers  (2021-06-04T01:12:47Z)

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.