Vincent W. S. Wong

Chaoxing Huang, Ziqiang Yu, Zijian Gao et al.

Fatty acid can potentially serve as biomarker for evaluating metabolic disorder and inflammation condition, and quantifying the double bonds is the key for revealing fatty acid information. This study presents an assessment of a deep learning approach utilizing Deep Image Prior (DIP) for the quantification of double bonds and methylene-interrupted double bonds of triglyceride derived from chemical-shift encoded multi-echo gradient echo images, all achieved without the necessity for network training. The methodology implemented a cost function grounded in signal constraints to continually refine the neural network's parameters on a single slice of images through iterative processes. Validation procedures encompassed both phantom experiments and in-vivo scans. The outcomes evidenced a concordance between the quantified values and the established reference standards, notably exemplified by a Pearson correlation coefficient of 0.96 (p = 0.0005) derived from the phantom experiments. The results in water-oil phantom also demonstrate the quantification reliability of the DIP method under the condition of having a relatively low-fat signal. Furthermore, the in-vivo assessments showcased the method's competency by showcasing consistent quantification results that closely mirrored previously published findings concerning subcutaneous fat. In summary, the study underscores the potential of Deep Image Prior in enabling the quantification of double bonds and methylene-interrupted double bonds from chemical-shift encoded multi-echo magnetic resonance imaging (MRI) data, suggesting potential avenues for future research and clinical applications in the field.

Mohammad Hossein Shokouhi, Vincent W. S. Wong

Agentic artificial intelligence (AI) is emerging as a key enabler for autonomous radio access networks (RANs), where multiple large language model (LLM)-based agents reason and collaborate to achieve operator-defined intents. The open RAN (O-RAN) architecture enables the deployment and coordination of such agents. However, most existing works consider simple intents handled by independent agents, while complex intents that require coordination among agents remain unexplored. In this paper, we propose an agentic AI framework for intent translation and optimization in cell-free O-RAN. A supervisor agent translates the operator intents into an optimization objective and minimum rate requirements. Based on this information, a user weighting agent retrieves relevant prior experience from a memory module to determine the user priority weights for precoding. If the intent includes an energy-saving objective, then an open radio unit (O-RU) management agent will also be activated to determine the set of active O-RUs by using a deep reinforcement learning (DRL) algorithm. A monitoring agent measures and monitors the user data rates and coordinates with other agents to guarantee the minimum rate requirements are satisfied. To enhance scalability, we adopt a parameter-efficient fine-tuning (PEFT) method that enables the same underlying LLM to be used for different agents. Simulation results show that the proposed agentic AI framework reduces the number of active O-RUs by 41.93% when compared with three baseline schemes in energy-saving mode. Using the PEFT method, the proposed framework reduces the memory usage by 92% when compared with deploying separate LLM agents.

Chuiyang Meng, Ming Tang, Vincent W. S. Wong

Parameter-efficient fine-tuning techniques such as low-rank adaptation (LoRA) enable large language models (LLMs) to adapt to downstream tasks efficiently. Federated learning (FL) further facilitates this process by enabling collaborative fine-tuning across distributed clients without sharing private data. However, the use of two separate low-rank matrices in LoRA for federated fine-tuning introduces two types of challenges. The first challenge arises from the error induced by separately aggregating those two low-rank matrices. The second challenge occurs even when the product of two low-rank matrices is aggregated. The server needs to recover factors via matrix decomposition, which is non-unique and can introduce decomposition drift. To tackle the aforementioned challenges, we propose FLoRG, a federated fine-tuning framework which employs a single low-rank matrix for fine-tuning and aggregates its Gram matrix (i.e., the matrix of inner products of its column vectors), eliminating the aggregation error while also reducing the communication overhead. FLoRG minimizes the decomposition drift by introducing a Procrustes alignment approach which aligns the decomposed matrix between consecutive fine-tuning rounds for consistent updates. We theoretically analyze the convergence of FLoRG and prove that adopting the Procrustes alignment results in a tighter convergence bound. Experimental results across multiple LLM fine-tuning benchmarks demonstrate that FLoRG outperforms five state-of-the-art baseline schemes in the downstream task accuracy and can reduce the communication overhead by up to 2041$\times$.

Hanqing Yang, Jingdi Chen, Marie Siew et al.

Developing intelligent agents for long-term cooperation in dynamic open-world scenarios is a major challenge in multi-agent systems. Traditional Multi-agent Reinforcement Learning (MARL) frameworks like centralized training decentralized execution (CTDE) struggle with scalability and flexibility. They require centralized long-term planning, which is difficult without custom reward functions, and face challenges in processing multi-modal data. CTDE approaches also assume fixed cooperation strategies, making them impractical in dynamic environments where agents need to adapt and plan independently. To address decentralized multi-agent cooperation, we propose Decentralized Adaptive Knowledge Graph Memory and Structured Communication System (DAMCS) in a novel Multi-agent Crafter environment. Our generative agents, powered by Large Language Models (LLMs), are more scalable than traditional MARL agents by leveraging external knowledge and language for long-term planning and reasoning. Instead of fully sharing information from all past experiences, DAMCS introduces a multi-modal memory system organized as a hierarchical knowledge graph and a structured communication protocol to optimize agent cooperation. This allows agents to reason from past interactions and share relevant information efficiently. Experiments on novel multi-agent open-world tasks show that DAMCS outperforms both MARL and LLM baselines in task efficiency and collaboration. Compared to single-agent scenarios, the two-agent scenario achieves the same goal with 63% fewer steps, and the six-agent scenario with 74% fewer steps, highlighting the importance of adaptive memory and structured communication in achieving long-term goals. We publicly release our project at: https://happyeureka.github.io/damcs.

Jong-Ik Park, Carlee Joe-Wong

Federated learning (FL) addresses privacy concerns in training language models by enabling multiple clients to contribute to the training, without sending their data to others. However, non-IID (identically and independently distributed) data across clients often limits FL's performance. This issue is especially challenging during model fine-tuning, as noise due to variations in clients' data distributions can harm model convergence near stationary points. This paper proposes a targeted layer update strategy for fine-tuning in FL. Instead of randomly updating layers of the language model, as often done in practice, we use a scoring mechanism to identify and update the most critical layers, avoiding excessively noisy or even poisoned updates by freezing the parameters in other layers. We show in extensive experiments that our method improves convergence and performance in non-IID settings, offering a more efficient approach to fine-tuning federated language models.

Manyou Ma, Vincent W. S. Wong

In this paper, we investigate the joint user pairing and association problem for multicell non-orthogonal multiple access (NOMA) systems. We consider a scenario where the user equipments (UEs) are located in a multicell network equipped with multiple base stations. Each base station has multiple orthogonal physical resource blocks (PRBs). Each PRB can be allocated to a pair of UEs using NOMA. Each UE has the additional freedom to be served by any one of the base stations, which further increases the complexity of the joint user pairing and association algorithm design. Leveraging the recent success on using machine learning to solve numerical optimization problems, we formulate the joint user pairing and association problem as a combinatorial optimization problem. The solution is found using an emerging deep learning architecture called Pointer Network (PtrNet), which has a lower computational complexity compared to solutions based on iterative algorithms and has been proven to achieve near-optimal performance. The training phase of the PtrNet is based on deep reinforcement learning (DRL), and does not require the use of the optimal solution of the formulated problem as training labels. Simulation results show that the proposed joint user pairing and association scheme achieves near-optimal performance in terms of the aggregate data rate, and outperforms the random user pairing and association heuristic by up to 30%.