paper-with-me

Papers Influence Approximation

“Influence Approximation” 태그가 달린 논문 7편 · 필터 해제

ClusterUCB: Efficient Gradient-Based Data Selection for Targeted Fine-Tuning of LLMs

2025-06-12 · Zige Wang, Qi Zhu, Fei Mi, Minghui Xu 외

Gradient-based data influence approximation has been leveraged to select useful data samples in the supervised fine-tuning of large language models. However, the computation of gradients throughout the fine-tuning proces…

ClusteringInfluence Approximation

Lazy But Effective: Collaborative Personalized Federated Learning with Heterogeneous Data

2025-05-05 · Ljubomir Rokvic, Panayiotis Danassis, Boi Faltings

In Federated Learning, heterogeneity in client data distributions often means that a single global model does not have the best performance for individual clients. Consider for example training a next-word prediction mod…

Federated LearningInfluence ApproximationPersonalized Federated Learning

Deeper Understanding of Black-box Predictions via Generalized Influence Functions

2023-12-09 · Hyeonsu Lyu, Jonggyu Jang, Sehyun Ryu, Hyun Jong Yang

Influence functions (IFs) elucidate how training data changes model behavior. However, the increasing size and non-convexity in large-scale models make IFs inaccurate. We suspect that the fragility comes from the first-o…

Influence ApproximationPhilosophy

DataInf: Efficiently Estimating Data Influence in LoRA-tuned LLMs and Diffusion Models

2023-10-02 · Yongchan Kwon, Eric Wu, Kevin Wu, James Zou

Quantifying the impact of training data points is crucial for understanding the outputs of machine learning models and for improving the transparency of the AI pipeline. The influence function is a principled and popular…

Influence Approximationparameter-efficient fine-tuning

LIA: Privacy-Preserving Data Quality Evaluation in Federated Learning Using a Lazy Influence Approximation

2022-05-23 · Ljubomir Rokvic, Panayiotis Danassis, Sai Praneeth Karimireddy, Boi Faltings

In Federated Learning, it is crucial to handle low-quality, corrupted, or malicious data. However, traditional data valuation methods are not suitable due to privacy concerns. To address this, we propose a simple yet eff…

Data ValuationFederated LearningInfluence ApproximationPrivacy Preserving

Explaining Neural Matrix Factorization with Gradient Rollback

2020-10-12 · Carolin Lawrence, Timo Sztyler, Mathias Niepert

Explaining the predictions of neural black-box models is an important problem, especially when such models are used in applications where user trust is crucial. Estimating the influence of training examples on a learned …

Graph EmbeddingInfluence ApproximationKnowledge Base CompletionKnowledge Graph Embedding

On the Accuracy of Influence Functions for Measuring Group Effects

2019-05-30 · NeurIPS 2019 12 · Pang Wei Koh, Kai-Siang Ang, Hubert H. K. Teo, Percy Liang

Influence functions estimate the effect of removing a training point on a model without the need to retrain. They are based on a first-order Taylor approximation that is guaranteed to be accurate for sufficiently small c…

Influence Approximation
1–7 / 7