相关论文: Rethinking Attribute Representation and Injection …

Trained classification models can unintentionally lead to biased representations and predictions, which can reinforce societal preconceptions and stereotypes. Existing debiasing methods for classification models, such as adversarial…

Understanding biases and stereotypes encoded in the weights of Large Language Models (LLMs) is crucial for developing effective mitigation strategies. However, biased behaviour is often subtle and non-trivial to isolate, even when…

Attention mechanism plays a dominant role in the sequence generation models and has been used to improve the performance of machine translation and abstractive text summarization. Different from neural machine translation, in the task of…

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…

Concept-based explanation methods, such as concept bottleneck models (CBMs), aim to improve the interpretability of machine learning models by linking their decisions to human-understandable concepts, under the critical assumption that such…

Attention--or attribution--maps methods are methods designed to highlight regions of the model's input that were discriminative for its predictions. However, different attention maps methods can highlight different regions of the input,…

Automatic image captioning has recently approached human-level performance due to the latest advances in computer vision and natural language understanding. However, most of the current models can only generate plain factual descriptions…

Retrieval augmented models are becoming increasingly popular for computer vision tasks after their recent success in NLP problems. The goal is to enhance the recognition capabilities of the model by retrieving similar examples for the…

This paper presents a simple yet effective method for improving the performance of zero-shot learning (ZSL). ZSL classifies instances of unseen classes, from which no training data is available, by utilizing the attributes of the classes.…

Presentation bias is one of the key challenges when learning from implicit feedback in search engines, as it confounds the relevance signal. While it was recently shown how counterfactual learning-to-rank (LTR) approaches…

Feature importance is commonly used to explain machine predictions. While feature importance can be derived from a machine learning model with a variety of methods, the consistency of feature importance via different methods remains…

This work explores attention models to weight the contribution of local convolutional representations for the instance search task. We present a retrieval framework based on bags of local convolutional features (BLCF) that benefits from…

Few shot classification aims to learn to recognize novel categories using only limited samples per category. Most current few shot methods use a base dataset rich in labeled examples to train an encoder that is used for obtaining…

When evaluating the performance of clinical machine learning models, one must consider the deployment population. When the population of patients with observed labels is only a subset of the deployment population (label selection), standard…

Learning to quantify (a.k.a.\ quantification) is a task concerned with training unbiased estimators of class prevalence via supervised learning. This task originated with the observation that "Classify and Count" (CC), the trivial method of…

Recent deep learning methods for recommendation systems are highly sophisticated. For article recommendation task, a neural network encoder which generates a latent representation of the article content would prove useful. However, using…

Research in automatic affect recognition has seldom addressed the issue of computational resource utilization. With the advent of ambient intelligence technology which employs a variety of low-power, resource-constrained devices, this issue…

Large Language Models (LLMs) have rapidly become central to NLP, demonstrating their ability to adapt to various tasks through prompting techniques, including sentiment analysis. However, we still have a limited understanding of how these…

Recently, the enactment of privacy regulations has promoted the rise of the machine unlearning paradigm. Existing studies of machine unlearning mainly focus on sample-wise unlearning, such that a learnt model will not expose user's privacy…

Attention mechanisms are dominating the explainability of deep models. They produce probability distributions over the input, which are widely deemed as feature-importance indicators. However, in this paper, we find one critical limitation…