相关论文: How Faithful Is Trajectory-Based Data Attribution?…

The performance of neural network models deteriorates due to their unreliable behavior on non-robust features of corrupted samples. Owing to their opaque nature, rectifying models to address this problem often necessitates arduous data…

Data attribution methods aim to answer useful counterfactual questions like "what would a ML model's prediction be if it were trained on a different dataset?" However, estimation of data attribution models through techniques like empirical…

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…

Training data attribution (TDA) techniques find influential training data for the model's prediction on the test data of interest. They approximate the impact of down- or up-weighting a particular training sample. While conceptually useful,…

Training autonomous agents with sparse rewards is a long-standing problem in online reinforcement learning (RL), due to low data efficiency. Prior work overcomes this challenge by extracting useful knowledge from offline data, often…

The success of the machine learning field has reliably depended on training on large datasets. While effective, this trend comes at an extraordinary cost. This is due to two deeply intertwined factors: the size of models and the size of…

Attribution explanation is a typical approach for explaining deep neural networks (DNNs), inferring an importance or contribution score for each input variable to the final output. In recent years, numerous attribution methods have been…

We propose probe-based data attribution, a method that traces behavioral changes in post-trained language models to responsible training datapoints. By computing activation-difference vectors for both test prompts and preference pairs and…

Data attribution methods, which quantify the influence of individual training data points on a machine learning model, have gained increasing popularity in data-centric applications in modern AI. Despite a recent surge of new methods…

Data attribution methods play a crucial role in understanding machine learning models, providing insight into which training data points are most responsible for model outputs during deployment. However, current state-of-the-art approaches…

Data attribution methods quantify the influence of training data on model outputs and are becoming increasingly relevant for a wide range of LLM research and applications, including dataset curation, model interpretability, data valuation.…

The inherently diverse and uncertain nature of trajectories presents a formidable challenge in accurately modeling them. Motion prediction systems must effectively learn spatial and temporal information from the past to forecast the future…

Safely deploying machine learning models to the real world is often a challenging process. Models trained with data obtained from a specific geographic location tend to fail when queried with data obtained elsewhere, agents trained in a…

Overfitting is a common problem in machine learning, which means the model too closely fits the training data while performing poorly in the test data. Among various methods of coping with overfitting, dropout is one of the representative…

Attribution methods provide an insight into the decision-making process of machine learning models, especially deep neural networks, by assigning contribution scores to each individual feature. However, the attribution problem has not been…

Training data attribution (TDA) methods aim to attribute model outputs back to specific training examples, and the application of these methods to large language model (LLM) outputs could significantly advance model transparency and data…

Diffusion models have shown strong competitiveness in offline reinforcement learning tasks by formulating decision-making as sequential generation. However, the practicality of these methods is limited due to the lengthy inference processes…

Trajectory optimization under uncertainty underpins a wide range of applications in robotics. However, existing methods are limited in terms of reasoning about sources of epistemic and aleatoric uncertainty, space and time correlations,…

Test-time adaptation harnesses test inputs to improve the accuracy of a model trained on source data when tested on shifted target data. Existing methods update the source model by (re-)training on each target domain. While effective,…

Trajectory datasets of road users have become more important in the last years for safety validation of highly automated vehicles. Several naturalistic trajectory datasets with each more than 10.000 tracks were released and others will…