相关论文: CARTE: Pretraining and Transfer for Tabular Learni…

The transferability of deep neural networks (DNNs) has made significant progress in image and language processing. However, due to the heterogeneity among tables, such DNN bonus is still far from being well exploited on tabular data…

We propose a graph-oriented attention-based explainability method for tabular data. Tasks involving tabular data have been solved mostly using traditional tree-based machine learning models which have the challenges of feature selection and…

Tabular data pervades the landscape of the World Wide Web, playing a foundational role in the digital architecture that underpins online information. Given the recent influence of large-scale pretrained models like ChatGPT and SAM across…

Character-based neural models have recently proven very useful for many NLP tasks. However, there is a gap of sophistication between methods for learning representations of sentences and words. While most character models for learning…

Tabular data represent one of the most prevalent data formats in applied machine learning, largely because they accommodate a broad spectrum of real-world problems. Existing literature has studied many of the shortcomings of neural…

Language models pretrained on large collections of tabular data have demonstrated their effectiveness in several downstream tasks. However, many of these models do not take into account the row/column permutation invariances, hierarchical…

Neural Architecture Search (NAS) methods have been shown to outperform hand-designed models and help to democratize AI. However, NAS methods often start from scratch with each new task, making them computationally expensive and limiting…

We develop a continual learning method for pretrained models that \emph{requires no access to old-task data}, addressing a practical barrier in foundation model adaptation where pretraining distributions are often unavailable. Our key…

Tables contain valuable knowledge in a structured form. We employ neural language modeling approaches to embed tabular data into vector spaces. Specifically, we consider different table elements, such caption, column headings, and cells,…

Answering simple questions over knowledge graphs is a well-studied problem in question answering. Previous approaches for this task built on recurrent and convolutional neural network based architectures that use pretrained word embeddings.…

The Transformer architecture and transfer learning have marked a quantum leap in natural language processing, improving the state of the art across a range of text-based tasks. This paper examines how these advancements can be applied to…

Topological Deep Learning seeks to enhance the predictive performance of neural network models by harnessing topological structures in input data. Topological neural networks operate on spaces such as cell complexes and hypergraphs, that…

Tabular data (or tables) are the most widely used data format in machine learning (ML). However, ML models often assume the table structure keeps fixed in training and testing. Before ML modeling, heavy data cleaning is required to merge…

Charts are very popular for analyzing data, visualizing key insights and answering complex reasoning questions about data. To facilitate chart-based data analysis using natural language, several downstream tasks have been introduced…

Tabular data, widely used in industries like healthcare, finance, and transportation, presents unique challenges for deep learning due to its heterogeneous nature and lack of spatial structure. This survey reviews the evolution of deep…

Transferring latent structure from one environment or problem to another is a mechanism by which humans and animals generalize with very little data. Inspired by cognitive and neurobiological insights, we propose graph schemas as a…

Autoencoders have been successful in learning meaningful representations from image datasets. However, their performance on text datasets has not been widely studied. Traditional autoencoders tend to learn possibly trivial representations…

Although deep learning models have had great success in natural language processing and computer vision, we do not observe comparable improvements in the case of tabular data, which is still the most common data type used in biological,…

Transfer learning allows us to train deep architectures requiring a large number of learned parameters, even if the amount of available data is limited, by leveraging existing models previously trained for another task. Here we explore the…

Heterogeneous tabular data are the most commonly used form of data and are essential for numerous critical and computationally demanding applications. On homogeneous data sets, deep neural networks have repeatedly shown excellent…