Image de couverture de livre

Dynamic Influence Tracker: Measuring Time-Varying Sample Influence During Training

Fuente: arXiv

Enregistré dans:

Détails bibliographiques
Auteurs principaux:	Xu, Jie, Wu, Zihan
Format:	Preprint
Publié:	2025
Sujets:	Machine Learning Artificial Intelligence
Accès en ligne:	Acceder al recurso
Tags:	Ajouter un tag Pas de tags, Soyez le premier à ajouter un tag!

Documents similaires

Towards Understanding the Influence of Training Samples on Explanations
par: Artelt, André, et autres
Publié: (2024)

Distributional Training Data Attribution: What do Influence Functions Sample?
par: Mlodozeniec, Bruno, et autres
Publié: (2025)

LiveVal: Time-aware Data Valuation via Adaptive Reference Points
par: Xu, Jie, et autres
Publié: (2025)

Diffusion Attribution Score: Evaluating Training Data Influence in Diffusion Models
par: Lin, Jinxu, et autres
Publié: (2024)

Faithful and Fast Influence Function via Advanced Sampling
par: Koh, Jungyeon, et autres
Publié: (2025)

IFFair: Influence Function-driven Sample Reweighting for Fair Classification
par: Yang, Jingran, et autres
Publié: (2025)

Fairness Without Harm: An Influence-Guided Active Sampling Approach
par: Pang, Jinlong, et autres
Publié: (2024)

A Poisson-Gamma Dynamic Factor Model with Time-Varying Transition Dynamics
par: Wang, Jiahao, et autres
Publié: (2024)

IMPACT: Influence Modeling for Open-Set Time Series Anomaly Detection
par: Zhou, Xiaohui, et autres
Publié: (2026)

Influence-based Attributions can be Manipulated
par: Yadav, Chhavi, et autres
Publié: (2024)

Knowledge-Guided Time-Varying Causal Inference for Arctic Sea Ice Dynamics
par: Sampath, Akila, et autres
Publié: (2026)

Machine Unlearning: Solutions and Challenges
par: Xu, Jie, et autres
Publié: (2023)

WAVE: Weighted Autoregressive Varying Gate for Time Series Forecasting
par: Lu, Jiecheng, et autres
Publié: (2024)

Learning from Complexity: Exploring Dynamic Sample Pruning of Spatio-Temporal Training
par: Chen, Wei, et autres
Publié: (2026)

Concept Influence: Leveraging Interpretability to Improve Performance and Efficiency in Training Data Attribution
par: Kowal, Matthew, et autres
Publié: (2026)

Leaning Time-Varying Instruments for Identifying Causal Effects in Time-Series Data
par: Cheng, Debo, et autres
Publié: (2024)

Efficient Machine Unlearning via Influence Approximation
par: Liu, Jiawei, et autres
Publié: (2025)

f-INE: A Hypothesis Testing Framework for Estimating Influence under Training Randomness
par: Panda, Subhodip, et autres
Publié: (2025)

Accumulative SGD Influence Estimation for Data Attribution
par: Shi, Yunxiao, et autres
Publié: (2025)

Graph Unlearning Meets Influence-aware Negative Preference Optimization
par: Chen, Qiang, et autres
Publié: (2025)

The Approximate Fisher Influence Function: Faster Estimation of Data Influence in Statistical Models
par: Lev, Omri, et autres
Publié: (2024)

Characterizing the Influence of Topology on Graph Learning Tasks
par: Wu, Kailong, et autres
Publié: (2024)

Chain-of-Influence: Tracing Interdependencies Across Time and Features in Clinical Predictive Modelings
par: Li, Yubo, et autres
Publié: (2025)

TimeMaster: Training Time-Series Multimodal LLMs to Reason via Reinforcement Learning
par: Zhang, Junru, et autres
Publié: (2025)

The Power of Training: How Different Neural Network Setups Influence the Energy Demand
par: Geißler, Daniel, et autres
Publié: (2024)

Temporal Dynamic Embedding for Irregularly Sampled Time Series
par: Kim, Mincheol, et autres
Publié: (2025)

Coupled Data and Measurement Space Dynamics for Enhanced Diffusion Posterior Sampling
par: Hamidi, Shayan Mohajer, et autres
Publié: (2025)

Grouter: Decoupling Routing from Representation for Accelerated MoE Training
par: Xu, Yuqi, et autres
Publié: (2026)

Group-robust Sample Reweighting for Subpopulation Shifts via Influence Functions
par: Qiao, Rui, et autres
Publié: (2025)

Feature Learning Dynamics in Infinite-Depth Neural Networks
par: Yao, Zihan, et autres
Publié: (2025)

SIMU: Selective Influence Machine Unlearning
par: Agarwal, Anu, et autres
Publié: (2025)

Revisiting Data Attribution for Influence Functions
par: Zhu, Hongbo, et autres
Publié: (2025)

Influence Functions for Preference Dataset Pruning
par: Fein, Daniel, et autres
Publié: (2025)

Integrated Influence: Data Attribution with Baseline
par: Yang, Linxiao, et autres
Publié: (2025)

TimeAutoDiff: A Unified Framework for Generation, Imputation, Forecasting, and Time-Varying Metadata Conditioning of Heterogeneous Time Series Tabular Data
par: Suh, Namjoon, et autres
Publié: (2024)

LMEraser: Large Model Unlearning through Adaptive Prompt Tuning
par: Xu, Jie, et autres
Publié: (2024)

Model-Based Safe Reinforcement Learning with Time-Varying State and Control Constraints: An Application to Intelligent Vehicles
par: Zhang, Xinglong, et autres
Publié: (2021)

From Parameter Dynamics to Risk Scoring : Quantifying Sample-Level Safety Degradation in LLM Fine-tuning
par: Wang, Xiao, et autres
Publié: (2026)

Influence of Recommender Systems on Users: A Dynamical Systems Analysis
par: Lankireddy, Prabhat, et autres
Publié: (2024)

Time-Varying Constraint-Aware Reinforcement Learning for Energy Storage Control
par: Jeong, Jaeik, et autres
Publié: (2024)