Tao Zhang

Liangyu Zha, Junlin Zhou, Liyao Li et al.

Tables are prevalent in real-world databases, requiring significant time and effort for humans to analyze and manipulate. The advancements in large language models (LLMs) have made it possible to interact with tables using natural language input, bringing this capability closer to reality. In this paper, we present TableGPT, a unified fine-tuned framework that enables LLMs to understand and operate on tables using external functional commands. It introduces the capability to seamlessly interact with tables, enabling a wide range of functionalities such as question answering, data manipulation (e.g., insert, delete, query, and modify operations), data visualization, analysis report generation, and automated prediction. TableGPT aims to provide convenience and accessibility to users by empowering them to effortlessly leverage tabular data. At the core of TableGPT lies the novel concept of global tabular representations, which empowers LLMs to gain a comprehensive understanding of the entire table beyond meta-information. By jointly training LLMs on both table and text modalities, TableGPT achieves a deep understanding of tabular data and the ability to perform complex operations on tables through chain-of-command instructions. Importantly, TableGPT offers the advantage of being a self-contained system rather than relying on external API interfaces. Moreover, it supports efficient data process flow, query rejection (when appropriate) and private deployment, enabling faster domain data fine-tuning and ensuring data privacy, which enhances the framework's adaptability to specific use cases.

Enmao Diao, Eric W. Tramel, Jie Ding et al.

Keyword Spotting (KWS) is a critical aspect of audio-based applications on mobile devices and virtual assistants. Recent developments in Federated Learning (FL) have significantly expanded the ability to train machine learning models by utilizing the computational and private data resources of numerous distributed devices. However, existing FL methods typically require that devices possess accurate ground-truth labels, which can be both expensive and impractical when dealing with local audio data. In this study, we first demonstrate the effectiveness of Semi-Supervised Federated Learning (SSL) and FL for KWS. We then extend our investigation to Semi-Supervised Federated Learning (SSFL) for KWS, where devices possess completely unlabeled data, while the server has access to a small amount of labeled data. We perform numerical analyses using state-of-the-art SSL, FL, and SSFL techniques to demonstrate that the performance of KWS models can be significantly improved by leveraging the abundant unlabeled heterogeneous data available on devices.

Tao Zhang, Quanyan zhu

Deception is a technique to mislead human or computer systems by manipulating beliefs and information. Successful deception is characterized by the information-asymmetric, dynamic, and strategic behaviors of the deceiver and the deceivee. This paper proposes a game-theoretic framework of a deception game to model the strategic behaviors of the deceiver and deceivee and construct strategies for both attacks and defenses over a continuous one-dimensional information space. We use the signaling game model to capture the information-asymmetric, dynamic, and strategic behaviors of deceptions by modeling the deceiver as a privately-informed player called sender and the deceivee as an uninformed player called receiver. We characterize perfect Bayesian Nash equilibrium (PBNE) solution of the game and study the deceivability. We highlight the condition of deceivee's knowledge enhancement through evidences to maintain the equilibrium and analyze the impacts of direct deception costs and players' conflict of interest on the deceivability.

Tao Zhang, Peer-Olaf Siebers, Uwe Aickelin

In this paper, we develop an agent-based model which integrates four important elements, i.e. organisational energy management policies/regulations, energy management technologies, electric appliances and equipment, and human behaviour, to simulate the electricity consumption in office buildings. Based on a case study, we use this model to test the effectiveness of different electricity management strategies, and solve practical office electricity consumption problems. This paper theoretically contributes to an integration of the four elements involved in the complex organisational issue of office electricity consumption, and practically contributes to an application of an agent-based approach for office building electricity consumption study.