<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="zhang-etal-2024-minimal">
    <titleInfo>
        <title>Minimal Distillation Schedule for Extreme Language Model Compression</title>
    </titleInfo>
    <name type="personal">
        <namePart type="given">Chen</namePart>
        <namePart type="family">Zhang</namePart>
        <role>
            <roleTerm authority="marcrelator" type="text">author</roleTerm>
        </role>
    </name>
    <name type="personal">
        <namePart type="given">Yang</namePart>
        <namePart type="family">Yang</namePart>
        <role>
            <roleTerm authority="marcrelator" type="text">author</roleTerm>
        </role>
    </name>
    <name type="personal">
        <namePart type="given">Qifan</namePart>
        <namePart type="family">Wang</namePart>
        <role>
            <roleTerm authority="marcrelator" type="text">author</roleTerm>
        </role>
    </name>
    <name type="personal">
        <namePart type="given">Jiahao</namePart>
        <namePart type="family">Liu</namePart>
        <role>
            <roleTerm authority="marcrelator" type="text">author</roleTerm>
        </role>
    </name>
    <name type="personal">
        <namePart type="given">Jingang</namePart>
        <namePart type="family">Wang</namePart>
        <role>
            <roleTerm authority="marcrelator" type="text">author</roleTerm>
        </role>
    </name>
    <name type="personal">
        <namePart type="given">Wei</namePart>
        <namePart type="family">Wu</namePart>
        <role>
            <roleTerm authority="marcrelator" type="text">author</roleTerm>
        </role>
    </name>
    <name type="personal">
        <namePart type="given">Dawei</namePart>
        <namePart type="family">Song</namePart>
        <role>
            <roleTerm authority="marcrelator" type="text">author</roleTerm>
        </role>
    </name>
    <originInfo>
        <dateIssued>2024-03</dateIssued>
    </originInfo>
    <typeOfResource>text</typeOfResource>
    <relatedItem type="host">
        <titleInfo>
            <title>Findings of the Association for Computational Linguistics: EACL 2024</title>
        </titleInfo>
        <name type="personal">
            <namePart type="given">Yvette</namePart>
            <namePart type="family">Graham</namePart>
            <role>
                <roleTerm authority="marcrelator" type="text">editor</roleTerm>
            </role>
        </name>
        <name type="personal">
            <namePart type="given">Matthew</namePart>
            <namePart type="family">Purver</namePart>
            <role>
                <roleTerm authority="marcrelator" type="text">editor</roleTerm>
            </role>
        </name>
        <originInfo>
            <publisher>Association for Computational Linguistics</publisher>
            <place>
                <placeTerm type="text">St. Julian’s, Malta</placeTerm>
            </place>
        </originInfo>
        <genre authority="marcgt">conference publication</genre>
    </relatedItem>
    <abstract>Recent studies have revealed that language model distillation can become less effective when there is a significant capacity gap between the teacher and the student models. In order to bridge the gap, teacher assistant-based distillation has been introduced, in which the selection of the teacher assistant plays a crucial role in transferring knowledge from the teacher to the student. However, existing approaches for teacher assistant-based distillation require numerous trials to find the optimal teacher assistant.In this paper, we propose a novel approach called Minimal Distillation Schedule (MiniDisc), which enables the scheduling of an optimal teacher assistant in just one trial for extreme model compression (e.g, to 5% scale). In particular, we empirically show that the performance of the student is positively correlated with the scale-performance tradeoff of the teacher assistant. We then introduce a new łambda-tradeoff metric that quantifies the optimality of the teacher assistant without the need for trial distillation to the student. By employing a sandwich framework, MiniDisc can select the optimal teacher assistant with the best łambda-tradeoff.We extensively evaluate MiniDisc through a series of experiments on the GLUE benchmark. The results demonstrate that our approach achieved an improved efficiency compared to various state-of-the-art baselines. Furthermore, we showcase the scalability of MiniDisc by applying it to a language model with billions of parameters.</abstract>
    <identifier type="citekey">zhang-etal-2024-minimal</identifier>
    <location>
        <url>https://aclanthology.org/2024.findings-eacl.93</url>
    </location>
    <part>
        <date>2024-03</date>
        <extent unit="page">
            <start>1378</start>
            <end>1394</end>
        </extent>
    </part>
</mods>
</modsCollection>

%0 Conference Proceedings
%T Minimal Distillation Schedule for Extreme Language Model Compression
%A Zhang, Chen
%A Yang, Yang
%A Wang, Qifan
%A Liu, Jiahao
%A Wang, Jingang
%A Wu, Wei
%A Song, Dawei
%Y Graham, Yvette
%Y Purver, Matthew
%S Findings of the Association for Computational Linguistics: EACL 2024
%D 2024
%8 March
%I Association for Computational Linguistics
%C St. Julian’s, Malta
%F zhang-etal-2024-minimal
%X Recent studies have revealed that language model distillation can become less effective when there is a significant capacity gap between the teacher and the student models. In order to bridge the gap, teacher assistant-based distillation has been introduced, in which the selection of the teacher assistant plays a crucial role in transferring knowledge from the teacher to the student. However, existing approaches for teacher assistant-based distillation require numerous trials to find the optimal teacher assistant.In this paper, we propose a novel approach called Minimal Distillation Schedule (MiniDisc), which enables the scheduling of an optimal teacher assistant in just one trial for extreme model compression (e.g, to 5% scale). In particular, we empirically show that the performance of the student is positively correlated with the scale-performance tradeoff of the teacher assistant. We then introduce a new łambda-tradeoff metric that quantifies the optimality of the teacher assistant without the need for trial distillation to the student. By employing a sandwich framework, MiniDisc can select the optimal teacher assistant with the best łambda-tradeoff.We extensively evaluate MiniDisc through a series of experiments on the GLUE benchmark. The results demonstrate that our approach achieved an improved efficiency compared to various state-of-the-art baselines. Furthermore, we showcase the scalability of MiniDisc by applying it to a language model with billions of parameters.
%U https://aclanthology.org/2024.findings-eacl.93
%P 1378-1394

Markdown (Informal)

[Minimal Distillation Schedule for Extreme Language Model Compression](https://aclanthology.org/2024.findings-eacl.93) (Zhang et al., Findings 2024)

• Minimal Distillation Schedule for Extreme Language Model Compression (Zhang et al., Findings 2024)

ACL

• Chen Zhang, Yang Yang, Qifan Wang, Jiahao Liu, Jingang Wang, Wei Wu, and Dawei Song. 2024. Minimal Distillation Schedule for Extreme Language Model Compression. In Findings of the Association for Computational Linguistics: EACL 2024, pages 1378–1394, St. Julian’s, Malta. Association for Computational Linguistics.