Related papers: Enhanced-FQL($\lambda$), an Efficient and Interpre…

As a promising paradigm to collaboratively train models with decentralized data, Federated Learning (FL) can be exploited to fine-tune Large Language Models (LLMs). While LLMs correspond to huge size, the scale of the training data…

This paper proposes an agent with particle swarm optimization (PSO) based on a Fuzzy Markup Language (FML) for students learning performance evaluation and educational applications, and the proposed agent is according to the response data…

Reinforcement learning (RL) for complex tasks remains a challenge, primarily due to the difficulties of engineering scalar reward functions and the inherent inefficiency of training models from scratch. Instead, it would be better to…

This paper introduces an advanced approach for fortifying Federated Learning (FL) systems against label-flipping attacks. We propose a simplified consensus-based verification process integrated with an adaptive thresholding mechanism. This…

Conventional federated learning assumes that greater learner participation improves training performance, by leveraging abundant, independently generated local data. However, in federated reinforcement learning (FRL) for unmanned aerial…

Federated learning-based semantic segmentation (FSS) has drawn widespread attention via decentralized training on local clients. However, most FSS models assume categories are fixed in advance, thus heavily undergoing forgetting on old…

Reinforcement learning has become the central approach for language models (LMs) to learn from environmental reward or feedback. In practice, the environmental feedback is usually sparse and delayed. Learning from such signals is…

In the complex landscape of multivariate time series forecasting, achieving both accuracy and interpretability remains a significant challenge. This paper introduces the Fuzzy Transformer (Fuzzformer), a novel recurrent neural network…

Deep learning models are often unaware of the inherent constraints of the task they are applied to. However, many downstream tasks require logical consistency. For ontology classification tasks, such constraints include subsumption and…

Federated Class Continual Learning (FCCL) merges the challenges of distributed client learning with the need for seamless adaptation to new classes without forgetting old ones. The key challenge in FCCL is catastrophic forgetting, an issue…

Reinforcement learning (RL) has been pivotal in enhancing the reasoning capabilities of large language models (LLMs), but it often suffers from limited exploration and entropy collapse, where models exploit a narrow set of solutions,…

A model's interpretability is essential to many practical applications such as clinical decision support systems. In this paper, a novel interpretable machine learning method is presented, which can model the relationship between input…

While data is distributed in multiple edge devices, Federated Learning (FL) is attracting more and more attention to collaboratively train a machine learning model without transferring raw data. FL generally exploits a parameter server and…

Federated Learning (FL) enables collaborative model training among participants while guaranteeing the privacy of raw data. Mainstream FL methodologies overlook the dynamic nature of real-world data, particularly its tendency to grow in…

Reinforcement learning (RL) is crucial for data science decision-making but suffers from sample inefficiency, particularly in real-world scenarios with costly physical interactions. This paper introduces a novel human-inspired framework to…

In UAV dynamic decision, complex and variable hazardous factors pose severe challenges to the generalization capability of algorithms. Despite offering semantic understanding and scene generalization, Large Language Models (LLM) lack…

We investigate a Federated Reinforcement Learning with Environment Heterogeneity (FRL-EH) framework, where local environments exhibit statistical heterogeneity. Within this framework, agents collaboratively learn a global policy by…

Learning from Demonstration (LfD) is a well-established problem in Reinforcement Learning (RL), which aims to facilitate rapid RL by leveraging expert demonstrations to pre-train the RL agent. However, the limited availability of expert…

Due to the nature of risk management in learning applicable policies, risk-sensitive reinforcement learning (RSRL) has been realized as an important direction. RSRL is usually achieved by learning risk-sensitive objectives characterized by…

The potential of reinforcement learning (RL) to deliver aligned and performant agents is partially bottlenecked by the reward engineering problem. One alternative to heuristic trial-and-error is preference-based RL (PbRL), where a reward…