@inproceedings{zhang-etal-2026-graphs,
title = "When Graphs Whisper: Graph Structure Serialization for Embedding Alignment in Cold-Start Recommendation",
author = "Zhang, Yujing and
Zhou, Huachi and
Liu, Ruochen and
Zhang, Qinggang and
Zhuang, Luyao and
Chen, Hao and
Hong, Zijin and
Yang, Chang and
Huang, Xiao",
editor = "Lee, Hung-Yi and
Dev, Sunipa and
Li, Jessy and
Elliott, Desmond",
booktitle = "Proceedings of the 2026 Conference on Empirical Methods in Natural Language Processing",
month = oct,
year = "2026",
address = "Budapest, Hungary",
publisher = "Association for Computational Linguistics",
url = "https://aclanthology.org/2026.emnlp-main.1470/",
pages = "33642--33660",
ISBN = "979-8-89176-459-0",
abstract = "Cold-start item recommendation remains challenging as new items lack interaction signals beyond textual descriptions. Existing methods either fine-tune large language models (LLMs) on descriptions or map item content into collaborative spaces learned from user-warm item interactions. However, text-only prompts struggle to capture higher-order graph structures, while distributional differences between behavior and content embeddings weaken alignment based solely on predicted probabilities. To address these issues, we propose Graph Structure Serialization for Embedding Alignment (GraphSEA), an LLM-based framework inspired by the observation that graphs contain sequential structures similar to language and can be serialized as inputs for LLMs. GraphSEA first serializes interaction graphs into structured token sequences for an LLM to learn behavior embeddings that encode collaborative patterns, while the LLM separately generates content embeddings from item descriptions. An embedding alignment module then aligns behavior and content embeddings across multiple facets, including interaction probability, preference order, and item distinction. Extensive experiments demonstrate that GraphSEA improves recommendation performance across warm and cold recommendation tasks, while achieving higher efficiency than LLM-based methods."
}<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="zhang-etal-2026-graphs">
<titleInfo>
<title>When Graphs Whisper: Graph Structure Serialization for Embedding Alignment in Cold-Start Recommendation</title>
</titleInfo>
<name type="personal">
<namePart type="given">Yujing</namePart>
<namePart type="family">Zhang</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Huachi</namePart>
<namePart type="family">Zhou</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Ruochen</namePart>
<namePart type="family">Liu</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Qinggang</namePart>
<namePart type="family">Zhang</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Luyao</namePart>
<namePart type="family">Zhuang</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Hao</namePart>
<namePart type="family">Chen</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Zijin</namePart>
<namePart type="family">Hong</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Chang</namePart>
<namePart type="family">Yang</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Xiao</namePart>
<namePart type="family">Huang</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<originInfo>
<dateIssued>2026-10</dateIssued>
</originInfo>
<typeOfResource>text</typeOfResource>
<relatedItem type="host">
<titleInfo>
<title>Proceedings of the 2026 Conference on Empirical Methods in Natural Language Processing</title>
</titleInfo>
<name type="personal">
<namePart type="given">Hung-Yi</namePart>
<namePart type="family">Lee</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Sunipa</namePart>
<namePart type="family">Dev</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Jessy</namePart>
<namePart type="family">Li</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Desmond</namePart>
<namePart type="family">Elliott</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<originInfo>
<publisher>Association for Computational Linguistics</publisher>
<place>
<placeTerm type="text">Budapest, Hungary</placeTerm>
</place>
</originInfo>
<genre authority="marcgt">conference publication</genre>
<identifier type="isbn">979-8-89176-459-0</identifier>
</relatedItem>
<abstract>Cold-start item recommendation remains challenging as new items lack interaction signals beyond textual descriptions. Existing methods either fine-tune large language models (LLMs) on descriptions or map item content into collaborative spaces learned from user-warm item interactions. However, text-only prompts struggle to capture higher-order graph structures, while distributional differences between behavior and content embeddings weaken alignment based solely on predicted probabilities. To address these issues, we propose Graph Structure Serialization for Embedding Alignment (GraphSEA), an LLM-based framework inspired by the observation that graphs contain sequential structures similar to language and can be serialized as inputs for LLMs. GraphSEA first serializes interaction graphs into structured token sequences for an LLM to learn behavior embeddings that encode collaborative patterns, while the LLM separately generates content embeddings from item descriptions. An embedding alignment module then aligns behavior and content embeddings across multiple facets, including interaction probability, preference order, and item distinction. Extensive experiments demonstrate that GraphSEA improves recommendation performance across warm and cold recommendation tasks, while achieving higher efficiency than LLM-based methods.</abstract>
<identifier type="citekey">zhang-etal-2026-graphs</identifier>
<location>
<url>https://aclanthology.org/2026.emnlp-main.1470/</url>
</location>
<part>
<date>2026-10</date>
<extent unit="page">
<start>33642</start>
<end>33660</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T When Graphs Whisper: Graph Structure Serialization for Embedding Alignment in Cold-Start Recommendation
%A Zhang, Yujing
%A Zhou, Huachi
%A Liu, Ruochen
%A Zhang, Qinggang
%A Zhuang, Luyao
%A Chen, Hao
%A Hong, Zijin
%A Yang, Chang
%A Huang, Xiao
%Y Lee, Hung-Yi
%Y Dev, Sunipa
%Y Li, Jessy
%Y Elliott, Desmond
%S Proceedings of the 2026 Conference on Empirical Methods in Natural Language Processing
%D 2026
%8 October
%I Association for Computational Linguistics
%C Budapest, Hungary
%@ 979-8-89176-459-0
%F zhang-etal-2026-graphs
%X Cold-start item recommendation remains challenging as new items lack interaction signals beyond textual descriptions. Existing methods either fine-tune large language models (LLMs) on descriptions or map item content into collaborative spaces learned from user-warm item interactions. However, text-only prompts struggle to capture higher-order graph structures, while distributional differences between behavior and content embeddings weaken alignment based solely on predicted probabilities. To address these issues, we propose Graph Structure Serialization for Embedding Alignment (GraphSEA), an LLM-based framework inspired by the observation that graphs contain sequential structures similar to language and can be serialized as inputs for LLMs. GraphSEA first serializes interaction graphs into structured token sequences for an LLM to learn behavior embeddings that encode collaborative patterns, while the LLM separately generates content embeddings from item descriptions. An embedding alignment module then aligns behavior and content embeddings across multiple facets, including interaction probability, preference order, and item distinction. Extensive experiments demonstrate that GraphSEA improves recommendation performance across warm and cold recommendation tasks, while achieving higher efficiency than LLM-based methods.
%U https://aclanthology.org/2026.emnlp-main.1470/
%P 33642-33660
Markdown (Informal)
[When Graphs Whisper: Graph Structure Serialization for Embedding Alignment in Cold-Start Recommendation](https://aclanthology.org/2026.emnlp-main.1470/) (Zhang et al., EMNLP 2026)
ACL
- Yujing Zhang, Huachi Zhou, Ruochen Liu, Qinggang Zhang, Luyao Zhuang, Hao Chen, Zijin Hong, Chang Yang, and Xiao Huang. 2026. When Graphs Whisper: Graph Structure Serialization for Embedding Alignment in Cold-Start Recommendation. In Proceedings of the 2026 Conference on Empirical Methods in Natural Language Processing, pages 33642–33660, Budapest, Hungary. Association for Computational Linguistics.