Revisiting SMoE Language Models by Evaluating Inefficiencies with Task Specific Expert Pruning

• URL: http://arxiv.org/abs/2409.01483v1
• Date: Mon, 2 Sep 2024 22:35:03 GMT
• Title: Revisiting SMoE Language Models by Evaluating Inefficiencies with Task Specific Expert Pruning
• Authors: Soumajyoti Sarkar, Leonard Lausen, Volkan Cevher, Sheng Zha, Thomas Brox, George Karypis,
• Abstract summary: Sparse Mixture of Expert (SMoE) models have emerged as a scalable alternative to dense models in language modeling. Our research explores task-specific model pruning to inform decisions about designing SMoE architectures. We introduce an adaptive task-aware pruning technique UNCURL to reduce the number of experts per MoE layer in an offline manner post-training.
• Score: 78.72226641279863
• License: http://creativecommons.org/licenses/by/4.0/
• Abstract: Sparse Mixture of Expert (SMoE) models have emerged as a scalable alternative to dense models in language modeling. These models use conditionally activated feedforward subnetworks in transformer blocks, allowing for a separation between total model parameters and per-example computation. However, large token-routed SMoE models face a significant challenge: during inference, the entire model must be used for a sequence or a batch, resulting in high latencies in a distributed setting that offsets the advantages of per-token sparse activation. Our research explores task-specific model pruning to inform decisions about designing SMoE architectures, mainly modulating the choice of expert counts in pretraining. We investigate whether such pruned models offer advantages over smaller SMoE models trained from scratch, when evaluating and comparing them individually on tasks. To that end, we introduce an adaptive task-aware pruning technique UNCURL to reduce the number of experts per MoE layer in an offline manner post-training. Our findings reveal a threshold pruning factor for the reduction that depends on the number of experts used in pretraining, above which, the reduction starts to degrade model performance. These insights contribute to our understanding of model design choices when pretraining with SMoE architectures, particularly useful when considering task-specific inference optimization for later stages.

Related papers

• Meta-Learning Adaptable Foundation Models [37.458141335750696]
  We introduce a meta-learning framework infused with PEFT in this intermediate retraining stage to learn a model that can be easily adapted to unseen tasks. In this setting, we demonstrate the suboptimality of standard retraining for finding an adaptable set of parameters. We then apply these theoretical insights to retraining the RoBERTa model to predict the continuation of conversations within the ConvAI2 dataset.
  arXiv  Detail & Related papers  (2024-10-29T17:24:18Z)
• SMILE: Zero-Shot Sparse Mixture of Low-Rank Experts Construction From Pre-Trained Foundation Models [85.67096251281191]
  We present an innovative approach to model fusion called zero-shot Sparse MIxture of Low-rank Experts (SMILE) construction. SMILE allows for the upscaling of source models into an MoE model without extra data or further training. We conduct extensive experiments across diverse scenarios, such as image classification and text generation tasks, using full fine-tuning and LoRA fine-tuning.
  arXiv  Detail & Related papers  (2024-08-19T17:32:15Z)
• Diversifying the Expert Knowledge for Task-Agnostic Pruning in Sparse Mixture-of-Experts [75.85448576746373]
  We propose a method of grouping and pruning similar experts to improve the model's parameter efficiency. We validate the effectiveness of our method by pruning three state-of-the-art MoE architectures. The evaluation shows that our method outperforms other model pruning methods on a range of natural language tasks.
  arXiv  Detail & Related papers  (2024-07-12T17:25:02Z)
• SEER-MoE: Sparse Expert Efficiency through Regularization for Mixture-of-Experts [49.01990048827639]
  We introduce SEER-MoE, a framework for reducing both the memory footprint and compute requirements of pre-trained MoE models. The first stage involves pruning the total number of experts using a heavy-hitters counting guidance, while the second stage employs a regularization-based fine-tuning strategy to recover accuracy loss. Our empirical studies demonstrate the effectiveness of our method, resulting in a sparse MoEs model optimized for inference efficiency with minimal accuracy trade-offs.
  arXiv  Detail & Related papers  (2024-04-07T22:13:43Z)
• On Least Square Estimation in Softmax Gating Mixture of Experts [78.3687645289918]
  We investigate the performance of the least squares estimators (LSE) under a deterministic MoE model. We establish a condition called strong identifiability to characterize the convergence behavior of various types of expert functions. Our findings have important practical implications for expert selection.
  arXiv  Detail & Related papers  (2024-02-05T12:31:18Z)
• Parameter-Efficient Sparsity Crafting from Dense to Mixture-of-Experts for Instruction Tuning on General Tasks [5.536630285985836]
  We introduce parameter-efficient sparsity crafting (PESC) PESC crafts dense models into sparse models using the mixture-of-experts (MoE) architecture. Our best sparse model outperforms other sparse and dense models and exhibits superior general capabilities compared to GP3.5.
  arXiv  Detail & Related papers  (2024-01-05T09:58:09Z)
• Earning Extra Performance from Restrictive Feedbacks [41.05874087063763]
  We set up a challenge named emphEarning eXtra PerformancE from restriCTive feEDdbacks (EXPECTED) to describe this form of model tuning problems. The goal of the model provider is to eventually deliver a satisfactory model to the local user(s) by utilizing the feedbacks. We propose to characterize the geometry of the model performance with regard to model parameters through exploring the parameters' distribution.
  arXiv  Detail & Related papers  (2023-04-28T13:16:54Z)
• Evaluating Representations with Readout Model Switching [18.475866691786695]
  In this paper, we propose to use the Minimum Description Length (MDL) principle to devise an evaluation metric. We design a hybrid discrete and continuous-valued model space for the readout models and employ a switching strategy to combine their predictions. The proposed metric can be efficiently computed with an online method and we present results for pre-trained vision encoders of various architectures.
  arXiv  Detail & Related papers  (2023-02-19T14:08:01Z)
• Models, Pixels, and Rewards: Evaluating Design Trade-offs in Visual Model-Based Reinforcement Learning [109.74041512359476]
  We study a number of design decisions for the predictive model in visual MBRL algorithms. We find that a range of design decisions that are often considered crucial, such as the use of latent spaces, have little effect on task performance. We show how this phenomenon is related to exploration and how some of the lower-scoring models on standard benchmarks will perform the same as the best-performing models when trained on the same training data.
  arXiv  Detail & Related papers  (2020-12-08T18:03:21Z)

This list is automatically generated from the titles and abstracts of the papers in this site.

This site does not guarantee the quality of this site (including all information) and is not responsible for any consequences.