Related papers: Measuring LLM Sensitivity in Transformer-based Tab…

Existing anomaly detection (AD) methods for tabular data usually rely on some assumptions about anomaly patterns, leading to inconsistent performance in real-world scenarios. While Large Language Models (LLMs) show remarkable reasoning…

As digital twins (DTs) to physical communication systems, network simulators can aid the design and deployment of communication networks. However, time-consuming simulations must be run for every new set of network configurations. Learnable…

Transformer-based large language models (LLMs) are comprised of billions of parameters arranged in deep and wide computational graphs. Several studies on LLM efficiency optimization argue that it is possible to prune a significant portion…

The rapid advancements in generative AI and large language models (LLMs) have opened up new avenues for producing synthetic data, particularly in the realm of structured tabular formats, such as product reviews. Despite the potential…

Dynamic graph learning plays a pivotal role in modeling evolving relationships over time, especially for temporal link prediction tasks in domains such as traffic systems, social networks, and recommendation platforms. While…

Relational databases, organized into tables connected by primary-foreign key relationships, are a common format for organizing data. Making predictions on relational data often involves transforming them into a flat tabular format through…

This article surveys the System Level Synthesis framework, which presents a novel perspective on constrained robust and optimal controller synthesis for linear systems. We show how SLS shifts the controller synthesis task from the design of…

Decision Transformers (DT) have demonstrated strong performances in offline reinforcement learning settings, but quickly adapting to unseen novel tasks remains challenging. To address this challenge, we propose a new framework, called…

As data volumes continue to grow, optimizing database performance has become increasingly critical, making the implementation of effective tuning methods essential. Among various approaches, database parameter tuning has proven to be a…

Our ability to synthesize sensory data that preserves specific statistical properties of the real data has had tremendous implications on data privacy and big data analytics. The synthetic data can be used as a substitute for selective real…

Dealing with tabular data is challenging due to partial information, noise, and heterogeneous structure. Existing techniques often struggle to simultaneously address key aspects of tabular data such as textual information, a variable number…

Synthetic data augmentation via large language models (LLMs) allows researchers to leverage additional training data, thus enhancing the performance of downstream tasks, especially when real-world data is scarce. However, the generated data…

Long-term time-series forecasting (LTTF) has become a pressing demand in many applications, such as wind power supply planning. Transformer models have been adopted to deliver high prediction capacity because of the high computational…

Transformer-based neural networks, empowered by Self-Supervised Learning (SSL), have demonstrated unprecedented performance across various domains. However, related literature suggests that tabular Transformers may struggle to outperform…

Change detection plays a fundamental role in Earth observation for analyzing temporal iterations over time. However, recent studies have largely neglected the utilization of multimodal data that presents significant practical and technical…

Transformer-based large language models (LLMs) have achieved strong performance across many natural language processing tasks. Nonetheless, their quadratic computational and memory requirements, particularly in self-attention layers, pose…

Deep generative models can help with data scarcity and privacy by producing synthetic training data, but they struggle in low-data, imbalanced tabular settings to fully learn the complex data distribution. We argue that striving for the…

This article provides a comprehensive synthesis of the recent developments in synthetic data generation via deep generative models, focusing on tabular datasets. We specifically outline the importance of synthetic data generation in the…

Imbalanced classification and spurious correlation are common challenges in data science and machine learning. Both issues are linked to data imbalance, with certain groups of data samples significantly underrepresented, which in turn would…

Synthetic training data generation with Large Language Models (LLMs) like Google's Gemma and OpenAI's GPT offer a promising solution to the challenge of obtaining large, labeled datasets for training classifiers. When rapid model deployment…