Online meta-learning is emerging as an enabling technique for achieving edge intelligence in the IoT ecosystem. Nevertheless, to learn a good meta-model for within-task fast adaptation, a single agent alone has to learn over many tasks, and this is the so-called 'cold-start' problem. Observing that in a multi-agent network the learning tasks across different agents often share some model similarity, we ask the following fundamental question: "Is it possible to accelerate the online meta-learning across agents via limited communication and if yes how much benefit can be achieved? " To answer this question, we propose a multi-agent online meta-learning framework and cast it as an equivalent two-level nested online convex optimization (OCO) problem. By characterizing the upper bound of the agent-task-averaged regret, we show that the performance of multi-agent online meta-learning depends heavily on how much an agent can benefit from the distributed network-level OCO for meta-model updates via limited communication, which however is not well understood. To tackle this challenge, we devise a distributed online gradient descent algorithm with gradient tracking where each agent tracks the global gradient using only one communication step with its neighbors per iteration, and it results in an average regret $O(\sqrt{T/N})$ per agent, indicating that a factor of $\sqrt{1/N}$ speedup over the optimal single-agent regret $O(\sqrt{T})$ after $T$ iterations, where $N$ is the number of agents. Building on this sharp performance speedup, we next develop a multi-agent online meta-learning algorithm and show that it can achieve the optimal task-average regret at a faster rate of $O(1/\sqrt{NT})$ via limited communication, compared to single-agent online meta-learning. Extensive experiments corroborate the theoretic results.
Meta Learning has been in focus in recent years due to the meta-learner model's ability to adapt well and generalize to new tasks, thus, reducing both the time and data requirements for learning. However, a major drawback of meta learner is that, to reach to a state from where learning new tasks becomes feasible with less data, it requires a large number of iterations and a lot of time. We address this issue by proposing various acceleration techniques to speed up meta learning algorithms such as MAML (Model Agnostic Meta Learning). We present 3.73X acceleration on a well known RNN optimizer b…
Human-Machine Collaboration on Generative Meta-Learning: Model and Algorithm
School of Computer Science, University of Sheffield（谢菲尔德大学计算机科学学院）；Centre for Machine intelligence, University of Sheffield（谢菲尔德大学机器智能中心）；ELLIS Institute Finland（芬兰ELLIS研究所）；Department of Computer Science, Aalto University（阿尔托大学计算机科学系）
Université de Montréal（蒙特利尔大学）；Friedrich-Alexander-Universität Erlangen-Nürnberg（弗里德里希-亚历山大-埃尔兰根-纽伦堡大学）；Concordia University（康考迪亚大学）；Mila
The constant introduction of standardized benchmarks in the literature has helped accelerating the recent advances in meta-learning research. They offer a way to get a fair comparison between different algorithms, and the wide range of datasets available allows full control over the complexity of this evaluation. However, for a large majority of code available online, the data pipeline is often specific to one dataset, and testing on another dataset requires significant rework. We introduce Torchmeta, a library built on top of PyTorch that enables seamless and consistent evaluation of meta-lea…
RelayCaching: Accelerating LLM Collaboration via Decoding KV Cache Reuse
Beijing University of Posts（北京邮电大学）；Tsinghua University, Beijing, China（清华大学）；University of Electronic Science（电子科学大学）；Peking University, Beijing, China（北京大学）
Berkeley AI Research（伯克利人工智能研究院）；Stanford（斯坦福大学）；Mila（米拉人工智能研究院）
We develop a new continual meta-learning method to address challenges in sequential multi-task learning. In this setting, the agent's goal is to achieve high reward over any sequence of tasks quickly. Prior meta-reinforcement learning algorithms have demonstrated promising results in accelerating the acquisition of new tasks. However, they require access to all tasks during training. Beyond simply transferring past experience to new tasks, our goal is to devise continual reinforcement learning algorithms that learn to learn, using their experience on previous tasks to learn new tasks more quic…
Neural Adjoint Method for Meta-optics: Accelerating Volumetric Inverse Design via Fourier Neural Operators
Hanyang University, Department of Artificial Intelligence（翰阳大学人工智能系）；Hanyang University, Department of Artificial Intelligence Semiconductor Engineering（翰阳大学人工智能半导体工程系）；Hanyang University, Department of Electronic Engineering（翰阳大学电子工程系）
MIT Media Laboratory（麻省理工学院媒体实验室）；Harvard University（哈佛大学）
Methods for neural network hyperparameter optimization and meta-modeling are computationally expensive due to the need to train a large number of model configurations. In this paper, we show that standard frequentist regression models can predict the final performance of partially trained model configurations using features based on network architectures, hyperparameters, and time-series validation performance data. We empirically show that our performance prediction models are much more effective than prominent Bayesian counterparts, are simpler to implement, and are faster to train. Our mode…
Bidirectional human-AI collaboration in brain tumour assessments improves both expert human and AI agent performance
University College London（伦敦大学学院）；National Hospital for Neurology and Neurosurgery（国立神经病学和神经外科医院）；NVIDIA（英伟达）；Great Ormond Street Hospital for Children（大奥蒙德街儿童医院）；Royal National Orthopaedic Hospital（皇家国立骨科医院）；University College Hospitals NHS Foundation Trust（伦敦大学学院医院国民保健服务基金会信托）；Royal Free Hospital（皇家自由医院）；Imperial College Healthcare NHS Trust（帝国理工学院医疗保健国民保健服务信托）；Imperial College London（帝国理工学院）
ColaCare: Enhancing Electronic Health Record Modeling through Large Language Model-Driven Multi-Agent Collaboration
Peking University（北京大学）；ETH Zurich（苏黎世联邦理工学院）；Peking University Third Hospital（北京大学第三医院）；University of Edinburgh（爱丁堡大学）；Beihang University（北京航空航天大学）；Health Data Research UK（英国健康数据研究中心）
