Enhancing Small Language Models for Graph Tasks Through Graph Encoder Integration
Identification
- Clé publique
- radar:r-94016c2cb1b306d922c56177a87b6dda
- Auteurs
- Dongryul Oh · Sujin Kang · Hee-Jin Kim · Dongsuk Oh
- Année déclarée
- 2025
- Langue déclarée
- en
- Type source
- article
- Première détection
- 2026-11-13T12:38:25.174830+00:00
- Dernière observation des métadonnées
- 2026-11-13T12:38:25.174830+00:00
- Dernière vérification HTTP
- Non effectuée
Institutions déclarées par la source
Kyungpook National University · Hyundai Motors (South Korea)
Pays d’affiliation déclarés
KR
Résumé documentaire — langue originale
Small language models (SLMs) are increasingly utilized for on-device applications due to their ability to ensure user privacy, reduce inference latency, and operate independently of cloud infrastructure. However, their performance is often limited when processing complex data structures such as graphs, which are ubiquitous in real-world datasets like social networks and system interactions. Graphs inherently encode intricate structural dependencies, requiring models to effectively capture both local and global relationships. Traditional language models, designed primarily for text data, struggle to address these requirements, leading to suboptimal performance in graph-related tasks. To overcome this limitation, we propose a novel graph encoder-based prompt tuning framework which integrates a graph convolutional network (GCN) with a graph transformer. By leveraging the complementary strengths of the GCN for local structural modeling and the graph transformer for capturing global relationships, our method enables SLMs to effectively process graph data. This integration significantly enhances the ability of SLMs to handle graph-centric tasks while maintaining the efficiency required for resource-constrained devices. The experimental results show that our approach not only improves the performance of SLMs on various graph benchmarks but also achieves results which closely approach the performance of a large language model (LLM). This work highlights the potential of extending SLMs for graph-based applications and advancing the capabilities of on-device artificial intelligence.
Identifiants
- OPENALEX
- https://openalex.org/W4407903641
- DOI
- 10.3390/app15052418
Repères documentaires
- Famille documentaire
- article
- Types déclarés par les sources
- article
- Éditeurs
- Multidisciplinary Digital Publishing Institute
Les mentions d’entités ne constituent pas une preuve de reconnaissance juridique. La juridiction étudiée est distincte du pays d’affiliation des auteurs.
Sources
OpenAlex · Document 1
Citer cette référence
Dongryul Oh; Sujin Kang; Hee-Jin Kim; Dongsuk Oh. Enhancing Small Language Models for Graph Tasks Through Graph Encoder Integration. 2025. https://doi.org/10.3390/app15052418
JSON · CSL-JSON · BibTeX · RIS · CSV · JSON-LD ·
APA, Chicago, ISO 690 : formats bibliographiques fondés sur les champs disponibles. OSCOLA / Bluebook : données structurées uniquement ; aucune conformité juridique complète n’est revendiquée sans vérification des éléments nécessaires.
- APA
- Dongryul Oh; Sujin Kang; Hee-Jin Kim; Dongsuk Oh. (2025). Enhancing Small Language Models for Graph Tasks Through Graph Encoder Integration. https://doi.org/10.3390/app15052418
- Chicago
- Dongryul Oh; Sujin Kang; Hee-Jin Kim; Dongsuk Oh. Enhancing Small Language Models for Graph Tasks Through Graph Encoder Integration. 2025. https://doi.org/10.3390/app15052418
- ISO 690
- Dongryul Oh; Sujin Kang; Hee-Jin Kim; Dongsuk Oh. Enhancing Small Language Models for Graph Tasks Through Graph Encoder Integration. 2025. https://doi.org/10.3390/app15052418
Warning: Undefined array key "last_link_verified" in /home/clients/e27d81e12f04d2bfd747aa264540ac56/sites/_UDTR_APP/legal_library_reference.php on line 31
UDTR — Bibliothèque juridique mondiale des droits de la Nature. Enhancing Small Language Models for Graph Tasks Through Graph Encoder Integration. Notice documentaire: https://www.declarationuniverselledesdroitsdelarbre.org/global-rights-of-nature-radar/reference/r-94016c2cb1b306d922c56177a87b6dda/ · Dernière vérification HTTP : non effectuée
Données de cette version figée
Dossiers et relations documentaires
Rôles des sources
Source bibliographique / publication d’origine · https://doi.org/10.3390/app15052418
Un lien vers une autorité ne prouve pas à lui seul une affirmation juridique. Les résumés et les textes intégraux restent soumis aux conditions de leur source.
Statut documentaire
Pertinence à examiner
Bibliothèque
Cette identité n’est pas encore intégrée à la Bibliothèque juridique.