Federated averaging (FedAvg) is a communication-efficient algorithm for distributed training with an enormous number of clients. In FedAvg, clients keep their data locally for privacy protection; a central parameter server is used to communicate between clients. This central server distributes the parameters to each client and collects the updated parameters from clients. FedAvg is mostly studied in centralized fashions, requiring massive communications between the central server and clients, which leads to possible channel blocking. Moreover, attacking the central server can break the whole system's privacy. Indeed, decentralization can significantly reduce the communication of the busiest node (the central one) because all nodes only communicate with their neighbors. To this end, in this paper, we study the decentralized FedAvg with momentum (DFedAvgM), implemented on clients that are connected by an undirected graph. In DFedAvgM, all clients perform stochastic gradient descent with momentum and communicate with their neighbors only. To further reduce the communication cost, we also consider the quantized DFedAvgM. The proposed algorithm involves the mixing matrix, momentum, client training with multiple local iterations, and quantization, introducing extra items in the Lyapunov analysis. Thus, the analysis of this paper is much more challenging than previous decentralized (momentum) SGD or FedAvg. We prove convergence of the (quantized) DFedAvgM under trivial assumptions; the convergence rate can be improved to sublinear when the loss function satisfies the PŁ property. Numerically, we find that the proposed algorithm outperforms FedAvg in both convergence speed and communication cost.

Deep reinforcement learning (RL) has become one of the most popular topics in artificial intelligence research. It has been widely used in various fields,

In recent years, it has been witnessed that the systolic array is a successful architecture for DNN hardware accelerators. However, the design of systolic arrays also encountered many challenges. As DNN structures and applications become more complex, a DNN hardware accelerator based on the typical systolic array architecture suffers severe performance and efficiency penalties. So, it has motivated a significant amount of research on the redesign and optimization of the systolic array architecture. In this article, we survey these works on analyzing, redesigning, and improving the performance and efficiency of the systolic array architecture. These works are critical to the design flow of DNN accelerators based on systolic arrays. We also provide a technique classification of these works on the basis of their main research idea. Further, we attempt to compare the advantages and disadvantages of different designs and different technologies and provide quantitative results for reference. The aim of this survey is to provide researchers with knowledge of the state-of-the-art in the systolic array architecture and motivate them to design highly efficient DNN accelerators of tomorrow.

Foundation models are in the process of becoming the dominant deep learning technology. Pretraining a foundation model is always time-consuming due to the large scale of both the model parameter and training dataset. Besides being computing-intensive, the pretraining process is extremely memory- and communication-intensive. These challenges make it necessary to apply 3D parallelism, which integrates data parallelism, pipeline model parallelism, and tensor model parallelism, to achieve high training efficiency. However, current 3D parallelism frameworks still encounter two issues: i) they are not transparent to model developers, requiring manual model modification to parallelize training, and ii) their utilization of computation resources, GPU memory, and network bandwidth is insufficient. We propose Merak , an automated 3D parallelism deep learning training framework with high resource utilization. Merak automatically deploys 3D parallelism with an automatic model partitioner, which includes a graph-sharding algorithm and proxy node-based model graph. Merak also offers a non-intrusive API to scale out foundation model training with minimal code modification. In addition, we design a high-performance 3D parallel runtime engine that employs several techniques to exploit available training resources, including a shifted critical path pipeline schedule that increases computation utilization, stage-aware recomputation that makes use of idle worker memory, and sub-pipelined tensor model parallelism that overlaps communication and computation. Experiments on 64 GPUs demonstrate Merak's capability to speed up training performance over state-of-the-art 3D parallelism frameworks of models with 1.5, 2.5, 8.3, and 20 billion parameters by up to 1.42, 1.39, 1.43, and 1.61×, respectively.

The rapid evolution of the web has led to an exponential growth in content. Recommender systems play a crucial role in human–computer interaction (HCI) by tailoring content based on individual preferences. Despite their importance, challenges persist in balancing recommendation accuracy with user satisfaction, addressing biases while preserving user privacy, and solving cold-start problems in cross-domain situations. This research argues that addressing these issues is not solely the recommender systems’ responsibility, and a human-centered approach is vital. We introduce the recommender system, assistant, and human (RAH) framework, an innovative solution with large language model (LLM)-based agents such as perceive, learn, act, critic, and reflect, emphasizing the alignment with user personalities. The framework utilizes the learn-act-critic loop and a reflection mechanism for improving user alignment. Using the real-world data, our experiments demonstrate the RAH framework’s efficacy in various recommendation domains, from reducing human burden to mitigating biases and enhancing user control. Notably, our contributions provide a human-centered recommendation framework that partners effectively with various recommendation models.

Operation anomalies are common phenomena in large-scale solar farms. Effective anomaly detection and classification is essential for improving operation reliability and electricity generation. However, this is a challenging task due to the high complexity and wide variety of frequently occurring anomalies. Furthermore, existing pre-installed supervisory control and data acquisition systems (SCADA) can only provide a limited amount of information regarding the healthy condition of solar farms, making accurate anomaly detection and classification difficult. This paper presents a data-driven anomaly detection and classification solution, which can accurately detect and classify diverse photovoltaic system anomalies. The proposed solution does not require additional equipment or non-SCADA data collection. More specifically, the proposed work consists of two methods: (1) a hierarchical context-aware anomaly detection method using unsupervised learning, and (2) a multimodal anomaly classification method. The proposed solution has been deployed in two large-scale solar farms (39.36 MWp and 21.62 MWp). Multi-month operation demonstrates the effectiveness, robustness, as well as cost- and computation-efficiency of the proposed solution.