<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="jian-wang-2023-invgc">
    <titleInfo>
        <title>InvGC: Robust Cross-Modal Retrieval by Inverse Graph Convolution</title>
    </titleInfo>
    <name type="personal">
        <namePart type="given">Xiangru</namePart>
        <namePart type="family">Jian</namePart>
        <role>
            <roleTerm authority="marcrelator" type="text">author</roleTerm>
        </role>
    </name>
    <name type="personal">
        <namePart type="given">Yimu</namePart>
        <namePart type="family">Wang</namePart>
        <role>
            <roleTerm authority="marcrelator" type="text">author</roleTerm>
        </role>
    </name>
    <originInfo>
        <dateIssued>2023-12</dateIssued>
    </originInfo>
    <typeOfResource>text</typeOfResource>
    <relatedItem type="host">
        <titleInfo>
            <title>Findings of the Association for Computational Linguistics: EMNLP 2023</title>
        </titleInfo>
        <name type="personal">
            <namePart type="given">Houda</namePart>
            <namePart type="family">Bouamor</namePart>
            <role>
                <roleTerm authority="marcrelator" type="text">editor</roleTerm>
            </role>
        </name>
        <name type="personal">
            <namePart type="given">Juan</namePart>
            <namePart type="family">Pino</namePart>
            <role>
                <roleTerm authority="marcrelator" type="text">editor</roleTerm>
            </role>
        </name>
        <name type="personal">
            <namePart type="given">Kalika</namePart>
            <namePart type="family">Bali</namePart>
            <role>
                <roleTerm authority="marcrelator" type="text">editor</roleTerm>
            </role>
        </name>
        <originInfo>
            <publisher>Association for Computational Linguistics</publisher>
            <place>
                <placeTerm type="text">Singapore</placeTerm>
            </place>
        </originInfo>
        <genre authority="marcgt">conference publication</genre>
    </relatedItem>
    <abstract>Over recent decades, significant advancements in cross-modal retrieval is mainly driven by breakthroughs in visual and linguistic modeling. However, a recent study shows that multi-modal data representations tend to cluster within a limited convex cone (as representation degeneration problem), which hinders retrieval performance due to the inseparability of these representations. In our study, we first empirically validate the presence of the representation degeneration problem across multiple cross-modal benchmarks and methods. Next, to address it, we introduce a novel method, called InvGC, a post-processing technique inspired by graph convolution and average pooling. Specifically, InvGC defines the graph topology within the datasets and then applies graph convolution in a subtractive manner. This method effectively separates representations by increasing the distances between data points. To improve the efficiency and effectiveness of InvGC, we propose an advanced graph topology, LocalAdj, which only aims to increase the distances between each data point and its nearest neighbors. To understand why InvGC works, we present a detailed theoretical analysis, proving that the lower bound of recall will be improved after deploying InvGC. Extensive empirical results show that InvGC and InvGC w/LocalAdj significantly mitigate the representation degeneration problem, thereby enhancing retrieval performance.</abstract>
    <identifier type="citekey">jian-wang-2023-invgc</identifier>
    <identifier type="doi">10.18653/v1/2023.findings-emnlp.60</identifier>
    <location>
        <url>https://aclanthology.org/2023.findings-emnlp.60</url>
    </location>
    <part>
        <date>2023-12</date>
        <extent unit="page">
            <start>836</start>
            <end>865</end>
        </extent>
    </part>
</mods>
</modsCollection>

%0 Conference Proceedings
%T InvGC: Robust Cross-Modal Retrieval by Inverse Graph Convolution
%A Jian, Xiangru
%A Wang, Yimu
%Y Bouamor, Houda
%Y Pino, Juan
%Y Bali, Kalika
%S Findings of the Association for Computational Linguistics: EMNLP 2023
%D 2023
%8 December
%I Association for Computational Linguistics
%C Singapore
%F jian-wang-2023-invgc
%X Over recent decades, significant advancements in cross-modal retrieval is mainly driven by breakthroughs in visual and linguistic modeling. However, a recent study shows that multi-modal data representations tend to cluster within a limited convex cone (as representation degeneration problem), which hinders retrieval performance due to the inseparability of these representations. In our study, we first empirically validate the presence of the representation degeneration problem across multiple cross-modal benchmarks and methods. Next, to address it, we introduce a novel method, called InvGC, a post-processing technique inspired by graph convolution and average pooling. Specifically, InvGC defines the graph topology within the datasets and then applies graph convolution in a subtractive manner. This method effectively separates representations by increasing the distances between data points. To improve the efficiency and effectiveness of InvGC, we propose an advanced graph topology, LocalAdj, which only aims to increase the distances between each data point and its nearest neighbors. To understand why InvGC works, we present a detailed theoretical analysis, proving that the lower bound of recall will be improved after deploying InvGC. Extensive empirical results show that InvGC and InvGC w/LocalAdj significantly mitigate the representation degeneration problem, thereby enhancing retrieval performance.
%R 10.18653/v1/2023.findings-emnlp.60
%U https://aclanthology.org/2023.findings-emnlp.60
%U https://doi.org/10.18653/v1/2023.findings-emnlp.60
%P 836-865

Markdown (Informal)

[InvGC: Robust Cross-Modal Retrieval by Inverse Graph Convolution](https://aclanthology.org/2023.findings-emnlp.60) (Jian & Wang, Findings 2023)

• InvGC: Robust Cross-Modal Retrieval by Inverse Graph Convolution (Jian & Wang, Findings 2023)

ACL

• Xiangru Jian and Yimu Wang. 2023. InvGC: Robust Cross-Modal Retrieval by Inverse Graph Convolution. In Findings of the Association for Computational Linguistics: EMNLP 2023, pages 836–865, Singapore. Association for Computational Linguistics.