相关论文: Incorporating Priors with Feature Attribution on T…

Fairness,the impartial treatment towards individuals or groups regardless of their inherent or acquired characteristics [20], is a critical challenge for the successful implementation of Artificial Intelligence (AI) in multiple fields like…

In order to allow machine learning algorithms to extract knowledge from raw data, these data must first be cleaned, transformed, and put into machine-appropriate form. These often very time-consuming phase is referred to as preprocessing.…

A proper form of data characterization can guide the process of learning-algorithm selection and model-performance estimation. The field of meta-learning has provided a rich body of work describing effective forms of data characterization…

The goal of data attribution for text-to-image models is to identify the training images that most influence the generation of a new image. Influence is defined such that, for a given output, if a model is retrained from scratch without the…

Societal biases are reflected in large pre-trained language models and their fine-tuned versions on downstream tasks. Common in-processing bias mitigation approaches, such as adversarial training and mutual information removal, introduce…

A common practice in transfer learning is to initialize the downstream model weights by pre-training on a data-abundant upstream task. In object detection specifically, the feature backbone is typically initialized with Imagenet classifier…

Bias in classifiers is a severe issue of modern deep learning methods, especially for their application in safety- and security-critical areas. Often, the bias of a classifier is a direct consequence of a bias in the training dataset,…

Contrastive representation learning has gained much attention due to its superior performance in learning representations from both image and sequential data. However, the learned representations could potentially lead to performance…

Interpretability is an important area of research for safe deployment of machine learning systems. One particular type of interpretability method attributes model decisions to input features. Despite active development, quantitative…

When humans perform inductive learning, they often enhance the process with background knowledge. With the increasing availability of well-formed collaborative knowledge bases, the performance of learning algorithms could be significantly…

We introduce an approach for incremental learning that preserves feature descriptors of training images from previously learned classes, instead of the images themselves, unlike most existing work. Keeping the much lower-dimensional feature…

Feature attribution aims to explain the reasoning behind a black-box model's prediction by identifying the impact of each feature on the prediction. Recent work has extended feature attribution to interactions between multiple features.…

In this paper, we propose a general framework for mitigating the disparities of the predicted classes with respect to secondary attributes within the data (e.g., race, gender etc.). Our proposed method involves learning a multi-objective…

Real-world datasets often encode stereotypes and societal biases. Such biases can be implicitly captured by trained models, leading to biased predictions and exacerbating existing societal preconceptions. Existing debiasing methods, such as…

There is a growing body of work that proposes methods for mitigating bias in machine learning systems. These methods typically rely on access to protected attributes such as race, gender, or age. However, this raises two significant…

In this paper, we propose an innovative approach to thoroughly explore dataset features that introduce bias in downstream machine-learning tasks. Depending on the data format, we use different techniques to map instances into a similarity…

The increasing complexity of AI systems has made understanding their behavior critical. Numerous interpretability methods have been developed to attribute model behavior to three key aspects: input features, training data, and internal…

From CNNs to attention mechanisms, encoding inductive biases into neural networks has been a fruitful source of improvement in machine learning. Adding auxiliary losses to the main objective function is a general way of encoding biases that…

While the majority of today's object class models provide only 2D bounding boxes, far richer output hypotheses are desirable including viewpoint, fine-grained category, and 3D geometry estimate. However, models trained to provide richer…

Language models often show a preference for using information from specific positions in the input regardless of semantic relevance. While positional bias has been studied in various contexts, from attention sinks to task performance…