相关论文: Self-Attentive Ensemble Transformer: Representing …

Most companies utilize demographic information to develop their strategy in a market. However, such information is not available to most retail companies. Several studies have been conducted to predict the demographic attributes of users…

Supervised machine-learning models often underperform in predicting user behaviors from conversational text, hindered by poor crowdsourced label quality and low NLP task accuracy. We introduce the Metadata-Sensitive Weighted-Encoding…

Ensemble weather forecasts enable a measure of uncertainty to be attached to each forecast, by computing the ensemble's spread. However, generating an ensemble with a good spread-error relationship is far from trivial, and a wide range of…

The transformer-based semantic segmentation approaches, which divide the image into different regions by sliding windows and model the relation inside each window, have achieved outstanding success. However, since the relation modeling…

In the recent past, complex deep neural networks have received huge interest in various document understanding tasks such as document image classification and document retrieval. As many document types have a distinct visual style, learning…

Attention-based neural networks, such as Transformers, have become ubiquitous in numerous applications, including computer vision, natural language processing, and time-series analysis. In all kinds of attention networks, the attention maps…

Transformer models are revolutionizing machine learning, but their inner workings remain mysterious. In this work, we present a new visualization technique designed to help researchers understand the self-attention mechanism in transformers…

Transformer-based models have emerged as a leading architecture for natural language processing, natural language generation, and image generation tasks. A fundamental element of the transformer architecture is self-attention, which allows…

We propose an extension to the transformer neural network architecture for general-purpose graph learning by adding a dedicated pathway for pairwise structural information, called edge channels. The resultant framework - which we call…

Ensemble models refer to methods that combine a typically large number of classifiers into a compound prediction. The output of an ensemble method is the result of fitting a base-learning algorithm to a given data set, and obtaining diverse…

Window-based transformers have demonstrated outstanding performance in super-resolution tasks due to their adaptive modeling capabilities through local self-attention (SA). However, they exhibit higher computational complexity and inference…

Although group convolutional networks are able to learn powerful representations based on symmetry patterns, they lack explicit means to learn meaningful relationships among them (e.g., relative positions and poses). In this paper, we…

An attention matrix of a transformer self-attention sublayer can provably be decomposed into two components and only one of them (effective attention) contributes to the model output. This leads us to ask whether visualizing effective…

Recurrent Neural Networks were, until recently, one of the best ways to capture the timely dependencies in sequences. However, with the introduction of the Transformer, it has been proven that an architecture with only attention-mechanisms…

Structured data, which constitutes a significant portion of existing data types, has been a long-standing research topic in the field of machine learning. Various representation learning methods for tabular data have been proposed, ranging…

Transformers have become an indispensable module for text generation models since their great success in machine translation. Previous works attribute the~success of transformers to the query-key-value dot-product attention, which provides…

Artificial neural networks have been successfully applied to a variety of machine learning tasks, including image recognition, semantic segmentation, and machine translation. However, few studies fully investigated ensembles of artificial…

Electrical Resistivity Tomography (ERT) is increasingly used to study subsurface hydrological processes. It shows promising potential for estimating soil water content, a key but challenging property to quantify. However, converting the…

Ensembles of classifier models typically deliver superior performance and can outperform single classifier models given a dataset and classification task at hand. However, the gain in performance comes together with the lack in…

Tracking entities in procedural language requires understanding the transformations arising from actions on entities as well as those entities' interactions. While self-attention-based pre-trained language encoders like GPT and BERT have…