Related papers: TabMDA: Tabular Manifold Data Augmentation for Any…
Leveraging the in-context learning (ICL) capability of Large Language Models (LLMs) for tabular classification has gained significant attention for its training-free adaptability across diverse datasets. Recent advancements, like TabPFN,…
Foundation models have established unified representations for natural language processing, yet this paradigm remains largely unexplored for tabular data. Existing methods face fundamental limitations: LLM-based approaches lack…
In recent times Large Language Models have exhibited tremendous capabilities, especially in the areas of mathematics, code generation and general-purpose reasoning. However for specialized domains especially in applications that require…
Non-independent and identically distributed (non-IID) data is a key challenge in federated learning (FL), which usually hampers the optimization convergence and the performance of FL. Existing data augmentation methods based on federated…
The remarkable success of Deep Learning approaches is often based and demonstrated on large public datasets. However, when applying such approaches to internal, private datasets, one frequently faces challenges arising from structural…
Intermediate training of pre-trained transformer-based language models on domain-specific data leads to substantial gains for downstream tasks. To increase efficiency and prevent catastrophic forgetting alleviated from full domain-adaptive…
Tabular data is the most widely used data format in machine learning (ML). While tree-based methods outperform DL-based methods in supervised learning, recent literature reports that self-supervised learning with Transformer-based models…
Large language models (LLMs) perform remarkably well on tabular datasets in zero- and few-shot settings, since they can extract meaning from natural language column headers that describe features and labels. Similarly, TabPFN, a recent…
Tabular data is the most commonly used form of data in industry. Gradient Boosting Trees, Support Vector Machine, Random Forest, and Logistic Regression are typically used for classification tasks on tabular data. DNN models using…
Data augmentation has been widely used in low-resource NER tasks to tackle the problem of data sparsity. However, previous data augmentation methods have the disadvantages of disrupted syntactic structures, token-label mismatch, and…
Tabular data, structured as rows and columns, is among the most prevalent data types in machine learning classification and regression applications. Models for learning from tabular data have continuously evolved, with Deep Neural Networks…
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…
Missing data is a widespread problem in tabular settings. Existing solutions range from simple averaging to complex generative adversarial networks, but due to each method's large variance in performance across real-world domains and…
Tabular data is the most abundant data type in the world, powering systems in finance, healthcare, e-commerce, and beyond. As tabular datasets grow and span multiple related targets, there is an increasing need to exploit shared task…
While most ML models expect independent and identically distributed data, this assumption is often violated in real-world scenarios due to distribution shifts, resulting in the degradation of machine learning model performance. Until now,…
Advances in machine learning research drive progress in real-world applications. To ensure this progress, it is important to understand the potential pitfalls on the way from a novel method's success on academic benchmarks to its practical…
Tabular data is a fundamental form of data structure. The evolution of table analysis tools reflects humanity's continuous progress in data acquisition, management, and processing. The dynamic changes in table columns arise from…
The recently developed Prior-Data Fitted Networks (PFNs) have shown very promising results for applications in low-data regimes. The TabPFN model, a special case of PFNs for tabular data, is able to achieve state-of-the-art performance on a…
Deep learning has revolutionized the performance of classification, but meanwhile demands sufficient labeled data for training. Given insufficient data, while many techniques have been developed to help combat overfitting, the challenge…
Anomaly detection for tabular data has been a long-standing unsupervised learning problem that remains a major challenge for current deep learning models. Recently, in-context learning has emerged as a new paradigm that has shifted efforts…