Image de couverture de livre

GraSS: Scalable Data Attribution with Gradient Sparsification and Sparse Projection

Fuente: arXiv

Enregistré dans:

Détails bibliographiques
Auteurs principaux:	Hu, Pingbang, Melkonian, Joseph, Tang, Weijing, Zhao, Han, Ma, Jiaqi W.
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

GraSS: Combining Graph Neural Networks with Expert Knowledge for SAT Solver Selection
par: Zhang, Zhanguang, et autres
Publié: (2024)

A Unified Theory of Random Projection for Influence Functions
par: Hu, Pingbang, et autres
Publié: (2026)

A Reliable Cryptographic Framework for Empirical Machine Unlearning Evaluation
par: Tu, Yiwen, et autres
Publié: (2024)

Dr. Post-Training: A Data Regularization Perspective on LLM Post-Training
par: Hu, Pingbang, et autres
Publié: (2026)

Adversarial Attacks on Data Attribution
par: Wang, Xinhe, et autres
Publié: (2024)

Daunce: Data Attribution through Uncertainty Estimation
par: Pan, Xingyuan, et autres
Publié: (2025)

A Versatile Influence Function for Data Attribution with Non-Decomposable Loss
par: Deng, Junwei, et autres
Publié: (2024)

Efficient Ensembles Improve Training Data Attribution
par: Deng, Junwei, et autres
Publié: (2024)

Most Influential Subset Selection: Challenges, Promises, and Beyond
par: Hu, Yuzheng, et autres
Publié: (2024)

Measuring Fine-Grained Relatedness in Multitask Learning via Data Attribution
par: Tu, Yiwen, et autres
Publié: (2025)

Sparse, Efficient and Explainable Data Attribution with DualXDA
par: Yolcu, Galip Ümit, et autres
Publié: (2024)

Influence Functions for Scalable Data Attribution in Diffusion Models
par: Mlodozeniec, Bruno, et autres
Publié: (2024)

Who Gets Credit or Blame? Attributing Accountability in Modern AI Systems
par: Zhang, Shichang, et autres
Publié: (2025)

SyGra: A Unified Graph-Based Framework for Scalable Generation, Quality Tagging, and Management of Synthetic Data
par: Pradhan, Bidyapati, et autres
Publié: (2025)

SecureBoost+: Large Scale and High-Performance Vertical Federated Gradient Boosting Decision Tree
par: Fan, Tao, et autres
Publié: (2021)

PSNE: Efficient Spectral Sparsification Algorithms for Scaling Network Embedding
par: Lin, Longlong, et autres
Publié: (2024)

Gradient Multi-Normalization for Stateless and Scalable LLM Training
par: Scetbon, Meyer, et autres
Publié: (2025)

Generalized Priority-Aware Shapley Value
par: Lee, Kiljae, et autres
Publié: (2026)

CABS: Conflict-Aware and Balanced Sparsification for Enhancing Model Merging
par: Yang, Zongzhen, et autres
Publié: (2025)

How Faithful Is Trajectory-Based Data Attribution? Error Sources, Remedies, and Practical Guidelines
par: Deng, Junwei, et autres
Publié: (2026)

Graph Sparsification via Mixture of Graphs
par: Zhang, Guibin, et autres
Publié: (2024)

SynthSAEBench: Evaluating Sparse Autoencoders on Scalable Realistic Synthetic Data
par: Chanin, David, et autres
Publié: (2026)

Metric-Gradient Projection for Stable Multi-Agent Policy Learning
par: Zhang, Zuyuan, et autres
Publié: (2026)

GraViti: Graph-Level Variational Autoencoders with Relaxed Permutation Invariance
par: Bresson, Roman, et autres
Publié: (2026)

AXIL: Exact Instance Attribution for Gradient Boosting
par: Geertsema, Paul, et autres
Publié: (2023)

DRAGD: A Federated Unlearning Data Reconstruction Attack Based on Gradient Differences
par: Ju, Bocheng, et autres
Publié: (2025)

First-Order Efficiency for Probabilistic Value Estimation via A Statistical Viewpoint
par: Liu, Ziqi, et autres
Publié: (2026)

Shapley-Value-Based Graph Sparsification for GNN Inference
par: Akkas, Selahattin, et autres
Publié: (2025)

GraDE: A Graph Diffusion Estimator for Frequent Subgraph Discovery in Neural Architectures
par: Yang, Yikang, et autres
Publié: (2026)

GraLoRA: Granular Low-Rank Adaptation for Parameter-Efficient Fine-Tuning
par: Jung, Yeonjoon, et autres
Publié: (2025)

Hierarchical Sparse Circuit Extraction from Billion-Parameter Language Models through Scalable Attribution Graph Decomposition
par: Uddin, Mohammed Mudassir, et autres
Publié: (2026)

Integrated Gradient Correlation: a Dataset-wise Attribution Method
par: Lelièvre, Pierre, et autres
Publié: (2024)

Gradient-Congruity Guided Federated Sparse Training
par: Tian, Chris Xing, et autres
Publié: (2024)

Sherry: Hardware-Efficient 1.25-Bit Ternary Quantization via Fine-grained Sparsification
par: Huang, Hong, et autres
Publié: (2026)

SAL: Selective Adaptive Learning for Backpropagation-Free Training with Sparsification
par: Liu, Fanping, et autres
Publié: (2026)

Learning Order Forest for Qualitative-Attribute Data Clustering
par: Zhao, Mingjie, et autres
Publié: (2026)

Towards Unified Attribution in Explainable AI, Data-Centric AI, and Mechanistic Interpretability
par: Zhang, Shichang, et autres
Publié: (2025)

Generalized Group Data Attribution
par: Ley, Dan, et autres
Publié: (2024)

Optimal Policy Sparsification and Low Rank Decomposition for Deep Reinforcement Learning
par: Goddla, Vikram
Publié: (2024)

Less Is More -- On the Importance of Sparsification for Transformers and Graph Neural Networks for TSP
par: Lischka, Attila, et autres
Publié: (2024)