相关论文: Faithful and Fast Influence Function via Advanced …

Detecting influential features in non-linear and/or high-dimensional data is a challenging and increasingly important task in machine learning. Variable selection methods have thus been gaining much attention as well as post-selection…

Understanding the black-box prediction for neural networks is challenging. To achieve this, early studies have designed influence function (IF) to measure the effect of removing a single training point on neural networks. However, the…

Fairness in machine learning has attained significant focus due to the widespread application in high-stake decision-making tasks. Unregulated machine learning classifiers can exhibit bias towards certain demographic groups in data, thus…

Data attribution aims to explain model predictions by estimating how they would change if certain training points were removed, and is used in a wide range of applications, from interpretability and credit assignment to unlearning and…

Sharpness-aware Minimization (SAM) improves generalization in large-scale model training by linking loss landscape geometry to generalization. However, challenges such as mislabeled noisy data and privacy concerns have emerged as…

A critical aspect of analyzing and improving modern machine learning systems lies in understanding how individual training examples influence a model's predictive behavior. Estimating this influence enables critical applications, including…

Influence functions are a popular tool for attributing a model's output to training data. The traditional approach relies on the calculation of inverse Hessian-vector products (iHVP), but the classical solver "Linear time Stochastic…

Influence diagnostics such as influence functions and approximate maximum influence perturbations are popular in machine learning and in AI domain applications. Influence diagnostics are powerful statistical tools to identify influential…

Language models are commonly fine-tuned via reinforcement learning to alter their behavior or elicit new capabilities. Datasets used for these purposes, and particularly human preference datasets, are often noisy. The relatively small size…

Contrastive learning, commonly applied in large-scale multimodal models, often relies on data from diverse and often unreliable sources, which can include misaligned or mislabeled text-image pairs. This frequently leads to robustness issues…

Fine-tuning large language models (LLMs) on chain-of-thought (CoT) data shows that a small amount of high-quality data can outperform massive datasets. Yet, what constitutes "quality" remains ill-defined. Existing reasoning methods rely on…

Due to growing privacy concerns, machine unlearning, which aims at enabling machine learning models to ``forget" specific training data, has received increasing attention. Among existing methods, influence-based unlearning has emerged as a…

Machine learning systems such as large scale recommendation systems or natural language processing systems are usually trained on billions of training points and are associated with hundreds of billions or trillions of parameters. Improving…

Machine unlearning aims to efficiently remove the influence of specific training data from a model without full retraining. While much progress has been made in unlearning for LLMs, document classification models remain relatively…

Causal influence measures for machine learnt classifiers shed light on the reasons behind classification, and aid in identifying influential input features and revealing their biases. However, such analyses involve evaluating the classifier…

In this work, we introduce a novel paradigm for generalized In-Context Learning (ICL), termed Indirect In-Context Learning. In Indirect ICL, we explore demonstration selection strategies tailored for two distinct real-world scenarios:…

Large Language Models (LLMs) have showcased their In-Context Learning (ICL) capabilities, enabling few-shot learning without the need for gradient updates. Despite its advantages, the effectiveness of ICL heavily depends on the choice of…

In the last few years, many works have tried to explain the predictions of deep learning models. Few methods, however, have been proposed to verify the accuracy or faithfulness of these explanations. Recently, influence functions, which is…

Generative Adversarial Networks (GAN) training process, in most cases, apply Uniform or Gaussian sampling methods in the latent space, which probably spends most of the computation on examples that can be properly handled and easy to…

Randomness is an unavoidable part of training deep learning models, yet something that traditional training data attribution algorithms fail to rigorously account for. They ignore the fact that, due to stochasticity in the initialisation…