Mixture-of-Expert (MoE) presents a strong potential in enlarging the size of language model to trillions of parameters. However, training trillion-scale MoE requires algorithm and system co-design for a well-tuned high performance distributed training system. Unfortunately, the only existing platform that meets the requirements strongly depends on Google's hardware (TPU) and software (Mesh Tensorflow) stack, and is not open and available to the public, especially GPU and PyTorch communities.
In this paper, we present FastMoE, a distributed MoE training system based on PyTorch with common accelerators. The system provides a hierarchical interface for both flexible model design and easy adaption to different applications, such as Transformer-XL and Megatron-LM. Different from direct implementation of MoE models using PyTorch, the training speed is highly optimized in FastMoE by sophisticated high-performance acceleration skills. The system supports placing different experts on multiple GPUs across multiple nodes, enabling enlarging the number of experts linearly against the number of GPUs. The source of FastMoE is available at https://github.com/laekov/fastmoe under Apache-2 license.
Sparsely gated Mixture-of-Expert (MoE) has demonstrated its effectiveness in scaling up deep neural networks to an extreme scale. Despite that numerous efforts have been made to improve the performance of MoE from the model design or system optimization perspective, existing MoE dispatch patterns are still not able to fully exploit the underlying heterogeneous network environments. In this paper, we propose TA-MoE, a topology-aware routing strategy for large-scale MoE trainging, from a model-system co-design perspective, which can dynamically adjust the MoE dispatch pattern according to the ne…
We present ScatterMoE, an implementation of Sparse Mixture-of-Experts (SMoE) on GPUs. ScatterMoE builds upon existing implementations, and overcoming some of the limitations to improve inference and training speed, and memory footprint. This implementation achieves this by avoiding padding and making excessive copies of the input. We introduce ParallelLinear, the main component we use to build our implementation and the various kernels used to speed up the operation. We benchmark our implementation against Megablocks, and show that it enables a higher throughput and lower memory footprint. We …
Sparsely Mixture of Experts (MoE) has received great interest due to its promising scaling capability with affordable computational overhead. MoE converts dense layers into sparse experts, and utilizes a gated routing network to make experts conditionally activated. However, as the number of experts grows, MoE with outrageous parameters suffers from overfitting and sparse data allocation. Such problems are especially severe on tasks with limited data, thus hindering the progress for MoE models to improve performance by scaling up. In this work, we propose Mixture of Expert Clusters - a general…
ETH Zurich（苏黎世联邦理工学院）；Carnegie Mellon University（卡内基梅隆大学）
The Mixture of Experts architecture allows for outrageously large neural networks by scaling model parameter size independently from computational demand (FLOPs). However, current DNN frameworks cannot effectively support the dynamic data flow in Mixture of Experts, and implementations on top of these frameworks need to use workarounds that introduce significant overheads. To address the limitation of these frameworks, we present DynaMoE, a DNN library that uses dynamic recompilations to optimize and adapt the use of computational resources to the dynamic needs of Mixture of Experts models. Ou…
Beijing Institute of Technology（北京理工大学）；Microsoft Corporation（微软公司）；Peking University（北京大学）；Microsoft Research（微软研究院）
Sparse mixture of experts provides larger model capacity while requiring a constant computational overhead. It employs the routing mechanism to distribute input tokens to the best-matched experts according to their hidden representations. However, learning such a routing mechanism encourages token clustering around expert centroids, implying a trend toward representation collapse. In this work, we propose to estimate the routing scores between tokens and experts on a low-dimensional hypersphere. We conduct extensive experiments on cross-lingual language model pre-training and fine-tuning on do…
Mixture Compressor for Mixture-of-Experts LLMs Gains More
The University of Hong Kong（香港大学）；The Chinese University of Hong Kong（香港中文大学）；Beihang University（北京航空航天大学）；Centre for Perceptual and Interactive Intelligence（感知与交互智能中心）
Google, Inc.（谷歌公司）；Courant Institute, NYU（纽约大学库朗研究所）；Facebook AI Group（脸书人工智能团队）
Mixtures of Experts combine the outputs of several "expert" networks, each of which specializes in a different part of the input space. This is achieved by training a "gating" network that maps each input to a distribution over the experts. Such models show promise for building larger networks that are still cheap to compute at test time, and more parallelizable at training time. In this this work, we extend the Mixture of Experts to a stacked model, the Deep Mixture of Experts, with multiple sets of gating and experts. This exponentially increases the number of effective experts by associatin…
Tsinghua University（清华大学）；THiFLY Research（THiFLY研究院）；State Key Laboratory of Cognitive Intelligence（认知智能国家重点实验室）
The table-based fact verification task has recently gained widespread attention and yet remains to be a very challenging problem. It inherently requires informative reasoning over natural language together with different numerical and logical reasoning on tables (e.g., count, superlative, comparative). Considering that, we exploit mixture-of-experts and present in this paper a new method: Self-adaptive Mixture-of-Experts Network (SaMoE). Specifically, we have developed a mixture-of-experts neural network to recognize and execute different types of reasoning -- the network is composed of multip…
In this paper, we propose a novel mixture of expert architecture for learning polyhedral classifiers. We learn the parameters of the classifierusing an expectation maximization algorithm. Wederive the generalization bounds of the proposedapproach. Through an extensive simulation study, we show that the proposed method performs comparably to other state-of-the-art approaches.
We propose a novel mixture-of-experts class to optimize computer vision models in accordance with data transfer limitations at test time. Our approach postulates that the minimum acceptable amount of data allowing for highly-accurate results can vary for different input space partitions. Therefore, we consider mixtures where experts require different amounts of data, and train a sparse gating function to divide the input space for each expert. By appropriate hyperparameter selection, our approach is able to bias mixtures of experts towards selecting specific experts over others. In this way, w…
A useful strategy to deal with complex classification scenarios is the "divide and conquer" approach. The mixture of experts (MOE) technique makes use of this strategy by joinly training a set of classifiers, or experts, that are specialized in different regions of the input space. A global model, or gate function, complements the experts by learning a function that weights their relevance in different parts of the input space. Local feature selection appears as an attractive alternative to improve the specialization of experts and gate function, particularly, for the case of high dimensional …
Booth School of Business University of Chicago（芝加哥大学商学院）；Volgenau School of Engineering, George Mason University（乔治·马歇尔大学工程学院）；Department of Systems Engineering and Operations Research George Mason University（乔治·马歇尔大学系统工程与运营管理系）
Mixture-of-Clustered-Experts: Advancing Expert Specialization and Generalization in Instruction Tuning
Department of Computer Science and Engineering, Korea University, Republic of Korea（韩国大学计算机科学与工程系）；KT, Republic of Korea（韩国KT）；School of Software, Soongsil University, Republic of Korea（顺天大学软件学院）
Radboud University（拉德堡德大学）；Institute for Molecules and Materials（分子与材料研究所）
This work proposes a new data-driven model devised to integrate process knowledge into its structure to increase the human-machine synergy in the process industry. The proposed Contextual Mixture of Experts (cMoE) explicitly uses process knowledge along the model learning stage to mold the historical data to represent operators' context related to the process through possibility distributions. This model was evaluated in two real case studies for quality prediction, including a sulfur recovery unit and a polymerization process. The contextual mixture of experts was employed to represent differ…
Sparsely-activated Mixture-of-experts (MoE) models allow the number of parameters to greatly increase while keeping the amount of computation for a given token or a given sample unchanged. However, a poor expert routing strategy (e.g. one resulting in load imbalance) can cause certain experts to be under-trained, leading to an expert being under or over-specialized. Prior work allocates a fixed number of experts to each token using a top-k function regardless of the relative importance of different tokens. To address this, we propose a heterogeneous mixture-of-experts employing an expert choic…
Let the Experts Speak: Improving Survival Prediction & Calibration via Mixture-of-Experts Heads
Department of Computer Science Columbia University USA（哥伦比亚大学计算机科学系）；Department of Computer Science New York University USA（纽约大学计算机科学系）；Department of Neurology Columbia University Medical Center USA（哥伦比亚大学医学中心神经病学系）；Department of Computer Science Barnard College USA（巴纳德学院计算机科学系）；Department of Biomedical Informatics Columbia University Medical Center USA（哥伦比亚大学医学中心生物医学信息学系）；NewYork-Presbyterian Hospital at Columbia University Medical Center USA（哥伦比亚大学医学中心新英格兰-纽约 Presbyterian 医院）
Many data have an underlying dependence on spatial location; it may be weather on the Earth, a simulation on a mesh, or a registered image. Yet this feature is rarely taken advantage of, and violates common assumptions made by many neural network layers, such as translation equivariance. Further, many works that do incorporate locality fail to capture fine-grained structure. To address this, we introduce the Spatial Mixture-of-Experts (SMoE) layer, a sparsely-gated layer that learns spatial structure in the input domain and routes experts at a fine-grained level to utilize it. We also develop …
Tsinghua University（清华大学）；Institute for AI（人工智能研究院）；BNRist Center（北京信息科学与技术国家研究中心）；Tsinghua-Bosch Joint ML Center（清华-博世机器学习联合研究中心）；THBI Lab（清华脑与智能实验室）
We present Mixture of Contrastive Experts (MiCE), a unified probabilistic clustering framework that simultaneously exploits the discriminative representations learned by contrastive learning and the semantic structures captured by a latent mixture model. Motivated by the mixture of experts, MiCE employs a gating function to partition an unlabeled dataset into subsets according to the latent semantics and multiple experts to discriminate distinct subsets of instances assigned to them in a contrastive learning manner. To solve the nontrivial inference and learning problems caused by the latent v…
MC#: Mixture Compressor for Mixture-of-Experts Large Models
Department of Electrical and Electronic Engineering, The University of Hong Kong（香港大学电子与电气工程系）；School of Computing, National University of Singapore（新加坡国立大学计算机学院）；NVIDIA Research（NVIDIA研究）
