Imagen de Portada

Backward Compatibility in Attributive Explanation and Enhanced Model Training Method

Fuente: arXiv

Guardado en:

Detalles Bibliográficos
Autor principal:	Matsuno, Ryuta
Formato:	Preprint
Publicado:	2024
Materias:	Machine Learning
Acceso en línea:	Acceder al recurso
Etiquetas:	Agregar Etiqueta Sin Etiquetas, Sea el primero en etiquetar este registro!

Ejemplares similares

Source Component Shift Adaptation via Offline Decomposition and Online Mixing Approach
por: Matsuno, Ryuta
Publicado: (2025)

Agile Online Model Selection: Resolving Adaptation Lag via Safeguarded Large Learning Rates
por: Takemura, Kei, et al.
Publicado: (2026)

Improved Impossible Tuning and Lipschitz-Adaptive Universal Online Learning with Gradient Variations
por: Takemura, Kei, et al.
Publicado: (2025)

Towards Backwards-Compatible Data with Confounded Domain Adaptation
por: McCarter, Calvin
Publicado: (2022)

Learning Along the Arrow of Time: Hyperbolic Geometry for Backward-Compatible Representation Learning
por: Bui, Ngoc, et al.
Publicado: (2025)

Minimizing False-Positive Attributions in Explanations of Non-Linear Models
por: Gjølbye, Anders, et al.
Publicado: (2025)

Enhancing Training Data Attribution with Representational Optimization
por: Sun, Weiwei, et al.
Publicado: (2025)

Harnessing Explanations: LLM-to-LM Interpreter for Enhanced Text-Attributed Graph Representation Learning
por: He, Xiaoxin, et al.
Publicado: (2023)

Beyond Attribution: Unified Concept-Level Explanations
por: Liu, Junhao, et al.
Publicado: (2024)

Missingness Bias Calibration in Feature Attribution Explanations
por: Sridhar, Shailesh, et al.
Publicado: (2026)

Stochastic Forward-Backward Deconvolution: Training Diffusion Models with Finite Noisy Datasets
por: Lu, Haoye, et al.
Publicado: (2025)

Retrieval Backward Attention without Additional Training: Enhance Embeddings of Large Language Models via Repetition
por: Duan, Yifei, et al.
Publicado: (2025)

Weak Robust Compatibility Between Learning Algorithms and Counterfactual Explanation Generation Algorithms
por: Xu, Ao, et al.
Publicado: (2024)

Model-Based Counterfactual Explanations Incorporating Feature Space Attributes for Tabular Data
por: Sumiya, Yuta, et al.
Publicado: (2024)

On the Shelf Life of Fine-Tuned LLM-Judges: Future-Proofing, Backward-Compatibility, and Question Generalization
por: Singh, Janvijay, et al.
Publicado: (2025)

Thinking Forward and Backward: Effective Backward Planning with Large Language Models
por: Ren, Allen Z., et al.
Publicado: (2024)

When Explanations Lie: Why Many Modified BP Attributions Fail
por: Sixt, Leon, et al.
Publicado: (2019)

Hypothesis Class Determines Explanation: Why Accurate Models Disagree on Feature Attribution
por: B, Thackshanaramana
Publicado: (2026)

Unifying Attribution-Based Explanations Using Functional Decomposition
por: Gevaert, Arne, et al.
Publicado: (2024)

Looking Backward: Retrospective Backward Synthesis for Goal-Conditioned GFlowNets
por: He, Haoran, et al.
Publicado: (2024)

SHapley Estimated Explanation (SHEP): A Fast Post-Hoc Attribution Method for Interpreting Intelligent Fault Diagnosis
por: Chen, Qian, et al.
Publicado: (2025)

Backward Conformal Prediction
por: Gauthier, Etienne, et al.
Publicado: (2025)

Analyzing and Enhancing the Backward-Pass Convergence of Unrolled Optimization
por: Kotary, James, et al.
Publicado: (2023)

Backward-Friendly Optimization: Training Large Language Models with Approximate Gradients under Memory Constraints
por: Yang, Jing, et al.
Publicado: (2025)

Deep Backward and Galerkin Methods for the Finite State Master Equation
por: Cohen, Asaf, et al.
Publicado: (2024)

Attribution Explanations for Deep Neural Networks: A Theoretical Perspective
por: Deng, Huiqi, et al.
Publicado: (2025)

Counterfactual Training: Teaching Models Plausible and Actionable Explanations
por: Altmeyer, Patrick, et al.
Publicado: (2026)

Explanation-Guided Adversarial Training for Robust and Interpretable Models
por: Chen, Chao, et al.
Publicado: (2026)

ExPLAIND: Unifying Model, Data, and Training Attribution to Study Model Behavior
por: Eichin, Florian, et al.
Publicado: (2025)

Exploring the Relationship Between Feature Attribution Methods and Model Performance
por: Silva, Priscylla, et al.
Publicado: (2024)

Training Feature Attribution for Vision Models
por: Bacha, Aziz, et al.
Publicado: (2025)

Hybrid Attribution Priors for Explainable and Robust Model Training
por: Zhang, Zhuoran, et al.
Publicado: (2025)

An Augmented Backward-Corrected Projector Splitting Integrator for Dynamical Low-Rank Training
por: Kusch, Jonas, et al.
Publicado: (2025)

A Training-free Method for LLM Text Attribution
por: Radvand, Tara, et al.
Publicado: (2025)

GPU Memory Usage Optimization for Backward Propagation in Deep Network Training
por: Hong, Ding-Yong, et al.
Publicado: (2025)

Ilargi: a GPU Compatible Factorized ML Model Training Framework
por: Sun, Wenbo, et al.
Publicado: (2025)

Feature Attribution with Necessity and Sufficiency via Dual-stage Perturbation Test for Causal Explanation
por: Chen, Xuexin, et al.
Publicado: (2024)

Pessimistic Backward Policy for GFlowNets
por: Jang, Hyosoon, et al.
Publicado: (2024)

From Attribution Maps to Human-Understandable Explanations through Concept Relevance Propagation
por: Achtibat, Reduan, et al.
Publicado: (2022)

Collective Model Intelligence Requires Compatible Specialization
por: Pari, Jyothish, et al.
Publicado: (2024)