Yuan 2.0-M32: Mixture of Experts with Attention Router

Yuan 2.0-M32, with a similar base architecture as Yuan-2.0 2B, uses a mixture-of-experts architecture with 32 experts of which 2 experts are active. A new router network, Attention Router, is proposed and adopted for a more efficient selection of experts, which improves the accuracy compared to the model with classical router network. Yuan 2.0-M32 is trained with 2000B tokens from scratch, and the training computation consumption is only 9.25% of a dense model at the same parameter scale. Yuan 2.0-M32 demonstrates competitive capability on coding, math, and various domains of expertise, with only 3.7B active parameters of 40B in total, and 7.4 GFlops forward computation per token, both of which are only 1/19 of Llama3-70B. Yuan 2.0-M32 surpass Llama3-70B on MATH and ARC-Challenge benchmark, with accuracy of 55.89 and 95.8 respectively. The models and source codes of Yuan 2.0-M32 are released at Github1.

Adaptive Split Learning over Energy-Constrained Wireless Edge Networks

Split learning (SL) is a promising approach for training artificial intelligence (AI) models, in which devices collaborate with a server to train an AI model in a distributed manner, based on a same fixed split point. However, due to the device heterogeneity and variation of channel conditions, this way is not optimal in training delay and energy consumption. In this paper, we design an adaptive split learning (ASL) scheme which can dynamically select split points for devices and allocate computing resource for the server in wireless edge networks. We formulate an optimization problem to minimize the average training latency subject to long-term energy consumption constraint. The difficulties in solving this problem are the lack of future information and mixed integer programming (MIP). To solve it, we propose an online algorithm leveraging the Lyapunov theory, named OPEN, which decomposes it into a new MIP problem only with the current information. Then, a two-layer optimization method is proposed to solve the MIP problem. Extensive simulation results demonstrate that the ASL scheme can reduce the average training delay and energy consumption by 53.7% and 22.1%, respectively, as compared to the existing SL schemes.

YUAN 2.0: A Large Language Model with Localized Filtering-based Attention

In this work, we develop and release Yuan 2.0, a series of large language models with parameters ranging from 2.1 billion to 102.6 billion. The Localized Filtering-based Attention (LFA) is introduced to incorporate prior knowledge of local dependencies of natural language into Attention. A data filtering and generating system is presented to build pre-training and fine-tuning dataset in high quality. A distributed training method with non-uniform pipeline parallel, data parallel, and optimizer parallel is proposed, which greatly reduces the bandwidth requirements of intra-node communication, and achieves good performance in large-scale distributed training. Yuan 2.0 models display impressive ability in code generation, math problem-solving, and chatting compared with existing models. The latest version of YUAN 2.0, including model weights and source code, is accessible at Github.

Goal-oriented Tensor: Beyond Age of Information Towards Semantics-Empowered Goal-Oriented Communications

Optimizations premised on open-loop metrics such as Age of Information (AoI) indirectly enhance the system's decision-making utility. We therefore propose a novel closed-loop metric named Goal-oriented Tensor (GoT) to directly quantify the impact of semantic mismatches on goal-oriented decision-making utility. Leveraging the GoT, we consider a sampler & decision-maker pair that works collaboratively and distributively to achieve a shared goal of communications. We formulate a two-agent infinite-horizon Decentralized Partially Observable Markov Decision Process (Dec-POMDP) to conjointly deduce the optimal deterministic sampling policy and decision-making policy. To circumvent the curse of dimensionality in obtaining an optimal deterministic joint policy through Brute-Force-Search, a sub-optimal yet computationally efficient algorithm is developed. This algorithm is predicated on the search for a Nash Equilibrium between the sampler and the decision-maker. Simulation results reveal that the proposed sampler & decision-maker co-design surpasses the current literature on AoI and its variants in terms of both goal achievement utility and sparse sampling rate, signifying progress in the semantics-conscious, goal-driven sparse sampling design.

Deep Reinforcement Learning-Assisted Age-optimal Transmission Policy for HARQ-aided NOMA Networks

The recent interweaving of AI-6G technologies has sparked extensive research interest in further enhancing reliable and timely communications. \emph{Age of Information} (AoI), as a novel and integrated metric implying the intricate trade-offs among reliability, latency, and update frequency, has been well-researched since its conception. This paper contributes new results in this area by employing a Deep Reinforcement Learning (DRL) approach to intelligently decide how to allocate power resources and when to retransmit in a \emph{freshness-sensitive} downlink multi-user Hybrid Automatic Repeat reQuest with Chase Combining (HARQ-CC) aided Non-Orthogonal Multiple Access (NOMA) network. Specifically, an AoI minimization problem is formulated as a Markov Decision Process (MDP) problem. Then, to achieve deterministic, age-optimal, and intelligent power allocations and retransmission decisions, the Double-Dueling-Deep Q Network (DQN) is adopted. Furthermore, a more flexible retransmission scheme, referred to as Retransmit-At-Will scheme, is proposed to further facilitate the timeliness of the HARQ-aided NOMA network. Simulation results verify the superiority of the proposed intelligent scheme and demonstrate the threshold structure of the retransmission policy. Also, answers to whether user pairing is necessary are discussed by extensive simulation results.

Yuan 1.0: Large-Scale Pre-trained Language Model in Zero-Shot and Few-Shot Learning

Recent work like GPT-3 has demonstrated excellent performance of Zero-Shot and Few-Shot learning on many natural language processing (NLP) tasks by scaling up model size, dataset size and the amount of computation. However, training a model like GPT-3 requires huge amount of computational resources which makes it challengeable to researchers. In this work, we propose a method that incorporates large-scale distributed training performance into model architecture design. With this method, Yuan 1.0, the current largest singleton language model with 245B parameters, achieves excellent performance on thousands GPUs during training, and the state-of-the-art results on NLP tasks. A data processing method is designed to efficiently filter massive amount of raw data. The current largest high-quality Chinese corpus with 5TB high quality texts is built based on this method. In addition, a calibration and label expansion method is proposed to improve the Zero-Shot and Few-Shot performance, and steady improvement is observed on the accuracy of various tasks. Yuan 1.0 presents strong capacity of natural language generation, and the generated articles are difficult to distinguish from the human-written ones.

Spinal Codes Optimization: Error Probability Analysis and Transmission Scheme Design

Spinal codes are known to be capacity achieving over both the additive white Gaussian noise (AWGN) channel and the binary symmetric channel (BSC). Over wireless channels, Spinal encoding can also be regarded as an adaptive-coded-modulation (ACM) technique due to its rateless property, which fits it with mobile communications. Due to lack of tight analysis on error probability of Spinal codes, optimization of transmission scheme using Spinal codes has not been fully explored. In this work, we firstly derive new tight upper bounds of the frame error rate (FER) of Spinal codes for both the AWGN channel and the BSC in the finite block-length (FBL) regime. Based on the derived upper bounds, we then design the optimal transmission scheme. Specifically, we formulate a rate maximization problem as a nonlinear integer programming problem, and solve it by an iterative algorithm for its dual problem. As the optimal solution exhibits an incremental-tail-transmission pattern, we propose an improved transmission scheme for Spinal codes. Moreover, we develop a bubble decoding with memory (BD-M) algorithm to reduce the decoding time complexity without loss of rate performance. The improved transmission scheme at the transmitter and the BD-M algorithm at the receiver jointly constitute an "encoding-decoding" system of Spinal codes. Simulation results demonstrate that it can improve both the rate performance and the decoding throughput of Spinal codes.