Knowledge boosting during low-latency inference

• URL: http://arxiv.org/abs/2407.11055v3
• Date: Thu, 25 Jul 2024 08:26:35 GMT
• Title: Knowledge boosting during low-latency inference
• Authors: Vidya Srinivas, Malek Itani, Tuochao Chen, Sefik Emre Eskimez, Takuya Yoshioka, Shyamnath Gollakota,
• Abstract summary: Models for low-latency, streaming applications could benefit from the knowledge capacity of larger models, but edge devices cannot run these models due to resource constraints. We propose knowledge boosting, a novel technique that allows a large model to operate on time-delayed input during inference, while still boosting small model performance. Our results show larger gains where the performance gap between the small and large models is wide, demonstrating a promising method for large-small model collaboration for low-latency applications.
• Score: 20.617827647115874
• License: http://creativecommons.org/licenses/by/4.0/
• Abstract: Models for low-latency, streaming applications could benefit from the knowledge capacity of larger models, but edge devices cannot run these models due to resource constraints. A possible solution is to transfer hints during inference from a large model running remotely to a small model running on-device. However, this incurs a communication delay that breaks real-time requirements and does not guarantee that both models will operate on the same data at the same time. We propose knowledge boosting, a novel technique that allows a large model to operate on time-delayed input during inference, while still boosting small model performance. Using a streaming neural network that processes 8 ms chunks, we evaluate different speech separation and enhancement tasks with communication delays of up to six chunks or 48 ms. Our results show larger gains where the performance gap between the small and large models is wide, demonstrating a promising method for large-small model collaboration for low-latency applications. Code, dataset, and audio samples available at https://knowledgeboosting.cs.washington.edu/.

Related papers

• Make Some Noise: Unlocking Language Model Parallel Inference Capability through Noisy Training [54.581599828392854]
  We propose the Make Some Noise (MSN) training framework as a replacement for the supervised fine-tuning stage of the large language model. The training method simply introduces some noise at the input for the model to learn the denoising task. Experiments in both the general and code domains have shown that MSN can improve inference speed by 2.3-2.7x times without compromising model performance.
  arXiv  Detail & Related papers  (2024-06-25T09:25:39Z)
• FlexModel: A Framework for Interpretability of Distributed Large Language Models [0.0]
  We present FlexModel, a software package providing a streamlined interface for engaging with models distributed across multi- GPU and multi-node configurations. The library is compatible with existing model distribution libraries and encapsulates PyTorch models. It exposes user-registerable HookFunctions to facilitate straightforward interaction with distributed model internals.
  arXiv  Detail & Related papers  (2023-12-05T21:19:33Z)
• Towards a Better Theoretical Understanding of Independent Subnetwork Training [56.24689348875711]
  We take a closer theoretical look at Independent Subnetwork Training (IST) IST is a recently proposed and highly effective technique for solving the aforementioned problems. We identify fundamental differences between IST and alternative approaches, such as distributed methods with compressed communication.
  arXiv  Detail & Related papers  (2023-06-28T18:14:22Z)
• Real-time Human Detection Model for Edge Devices [0.0]
  Convolutional Neural Networks (CNNs) have replaced traditional feature extraction and machine learning models in detection and classification tasks. Lightweight CNN models have been recently introduced for real-time tasks. This paper suggests a CNN-based lightweight model that can fit on a limited edge device such as Raspberry Pi.
  arXiv  Detail & Related papers  (2021-11-20T18:42:17Z)
• Communication-Efficient Separable Neural Network for Distributed Inference on Edge Devices [2.28438857884398]
  We propose a novel method of exploiting model parallelism to separate a neural network for distributed inferences. Under proper specifications of devices and configurations of models, our experiments show that the inference of large neural networks on edge clusters can be distributed and accelerated.
  arXiv  Detail & Related papers  (2021-11-03T19:30:28Z)
• Network Augmentation for Tiny Deep Learning [73.57192520534585]
  We introduce Network Augmentation (NetAug), a new training method for improving the performance of tiny neural networks. We demonstrate the effectiveness of NetAug on image classification and object detection.
  arXiv  Detail & Related papers  (2021-10-17T18:48:41Z)
• Enabling On-Device Training of Speech Recognition Models with Federated Dropout [4.165917555996752]
  Federated learning can be used to train machine learning models on the edge on local data that never leave devices. We propose using federated dropout to reduce the size of client models while training a full-size model server-side.
  arXiv  Detail & Related papers  (2021-10-07T17:22:40Z)
• Disfluency Detection with Unlabeled Data and Small BERT Models [3.04133054437883]
  We focus on the disfluency detection task, focusing on small, fast, on-device models based on the BERT architecture. We demonstrate it is possible to train disfluency detection models as small as 1.3 MiB, while retaining high performance.
  arXiv  Detail & Related papers  (2021-04-21T21:24:32Z)
• Dynamic Model Pruning with Feedback [64.019079257231]
  We propose a novel model compression method that generates a sparse trained model without additional overhead. We evaluate our method on CIFAR-10 and ImageNet, and show that the obtained sparse models can reach the state-of-the-art performance of dense models.
  arXiv  Detail & Related papers  (2020-06-12T15:07:08Z)
• When Ensembling Smaller Models is More Efficient than Single Large Models [52.38997176317532]
  We show that ensembles can outperform single models with both higher accuracy and requiring fewer total FLOPs to compute. This presents an interesting observation that output diversity in ensembling can often be more efficient than training larger models.
  arXiv  Detail & Related papers  (2020-05-01T18:56:18Z)
• A Streaming On-Device End-to-End Model Surpassing Server-Side Conventional Model Quality and Latency [88.08721721440429]
  We develop a first-pass Recurrent Neural Network Transducer (RNN-T) model and a second-pass Listen, Attend, Spell (LAS) rescorer. We find that RNN-T+LAS offers a better WER and latency tradeoff compared to a conventional model.
  arXiv  Detail & Related papers  (2020-03-28T05:00:33Z)

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.