Dynamic Encoding Selection: Adaptive Mamba and LLM Fusion for Temporal Knowledge Graph Reasoning Article Swipe
This paper introduces Dynamic Encoding Selection DES , a novel framework for temporal knowledge graph reasoning that adaptively fuses representations from state space models and large language models LLMs . While recent advancements in sequence modeling have improved temporal pattern recognition, they often lack the semantic understanding necessary for comprehensive reasoning. Similarly, large language models possess rich semantic knowledge but struggle with structured temporal dependencies. Our approach leverages the complementary strengths of both paradigms—employing Mamba's state space architecture to efficiently capture sequential patterns with linear complexity, while utilizing LLMs' pre-trained knowledge for semantic understanding. The key innovation lies in our adaptive fusion mechanism, which dynamically selects between sequential, semantic, or combined representations for each query based on contextual factors like temporal proximity and entity connectivity.
Related Topics
Concepts
No concepts available.
Metadata
- Type
- article
- Landing Page
- https://doi.org/10.65286/icic.v21i2.54944
- http://poster-openaccess.com/files/ICIC2025/3677.pdf
- OA Status
- gold
- OpenAlex ID
- https://openalex.org/W4416058091
All OpenAlex metadata
Raw OpenAlex JSON
- OpenAlex ID
-
https://openalex.org/W4416058091Canonical identifier for this work in OpenAlex
- DOI
-
https://doi.org/10.65286/icic.v21i2.54944Digital Object Identifier
- Title
-
Dynamic Encoding Selection: Adaptive Mamba and LLM Fusion for Temporal Knowledge Graph ReasoningWork title
- Type
-
articleOpenAlex work type
- Publication year
-
2025Year of publication
- Publication date
-
2025-01-01Full publication date if available
- Authors
-
Shuchong WeiList of authors in order
- Landing page
-
https://doi.org/10.65286/icic.v21i2.54944Publisher landing page
- PDF URL
-
https://poster-openaccess.com/files/ICIC2025/3677.pdfDirect link to full text PDF
- Open access
-
YesWhether a free full text is available
- OA status
-
goldOpen access status per OpenAlex
- OA URL
-
https://poster-openaccess.com/files/ICIC2025/3677.pdfDirect OA link when available
- Cited by
-
0Total citation count in OpenAlex
Full payload
| id | https://openalex.org/W4416058091 |
|---|---|
| doi | https://doi.org/10.65286/icic.v21i2.54944 |
| ids.doi | https://doi.org/10.65286/icic.v21i2.54944 |
| ids.openalex | https://openalex.org/W4416058091 |
| fwci | |
| type | article |
| title | Dynamic Encoding Selection: Adaptive Mamba and LLM Fusion for Temporal Knowledge Graph Reasoning |
| biblio.issue | |
| biblio.volume | |
| biblio.last_page | 2332 |
| biblio.first_page | 2315 |
| is_xpac | False |
| apc_list | |
| apc_paid | |
| language | |
| locations[0].id | doi:10.65286/icic.v21i2.54944 |
| locations[0].is_oa | True |
| locations[0].source | |
| locations[0].license | |
| locations[0].pdf_url | http://poster-openaccess.com/files/ICIC2025/3677.pdf |
| locations[0].version | publishedVersion |
| locations[0].raw_type | proceedings-article |
| locations[0].license_id | |
| locations[0].is_accepted | True |
| locations[0].is_published | True |
| locations[0].raw_source_name | Poster Volume Ⅱ The 2025 Twenty-First International Conference on Intelligent Computing July 26-29, 2025 Ningbo, China |
| locations[0].landing_page_url | https://doi.org/10.65286/icic.v21i2.54944 |
| indexed_in | crossref |
| authorships[0].author.id | https://openalex.org/A5067481838 |
| authorships[0].author.orcid | https://orcid.org/0000-0003-1449-0672 |
| authorships[0].author.display_name | Shuchong Wei |
| authorships[0].author_position | first |
| authorships[0].raw_author_name | Shuchong Wei |
| authorships[0].is_corresponding | True |
| has_content.pdf | True |
| has_content.grobid_xml | False |
| is_paratext | False |
| open_access.is_oa | True |
| open_access.oa_url | http://poster-openaccess.com/files/ICIC2025/3677.pdf |
| open_access.oa_status | gold |
| open_access.any_repository_has_fulltext | False |
| created_date | 2025-11-10T00:00:00 |
| display_name | Dynamic Encoding Selection: Adaptive Mamba and LLM Fusion for Temporal Knowledge Graph Reasoning |
| has_fulltext | False |
| is_retracted | False |
| updated_date | 2025-11-28T10:36:07.986616 |
| primary_topic | |
| cited_by_count | 0 |
| locations_count | 1 |
| best_oa_location.id | doi:10.65286/icic.v21i2.54944 |
| best_oa_location.is_oa | True |
| best_oa_location.source | |
| best_oa_location.license | |
| best_oa_location.pdf_url | http://poster-openaccess.com/files/ICIC2025/3677.pdf |
| best_oa_location.version | publishedVersion |
| best_oa_location.raw_type | proceedings-article |
| best_oa_location.license_id | |
| best_oa_location.is_accepted | True |
| best_oa_location.is_published | True |
| best_oa_location.raw_source_name | Poster Volume Ⅱ The 2025 Twenty-First International Conference on Intelligent Computing July 26-29, 2025 Ningbo, China |
| best_oa_location.landing_page_url | https://doi.org/10.65286/icic.v21i2.54944 |
| primary_location.id | doi:10.65286/icic.v21i2.54944 |
| primary_location.is_oa | True |
| primary_location.source | |
| primary_location.license | |
| primary_location.pdf_url | http://poster-openaccess.com/files/ICIC2025/3677.pdf |
| primary_location.version | publishedVersion |
| primary_location.raw_type | proceedings-article |
| primary_location.license_id | |
| primary_location.is_accepted | True |
| primary_location.is_published | True |
| primary_location.raw_source_name | Poster Volume Ⅱ The 2025 Twenty-First International Conference on Intelligent Computing July 26-29, 2025 Ningbo, China |
| primary_location.landing_page_url | https://doi.org/10.65286/icic.v21i2.54944 |
| publication_date | 2025-01-01 |
| publication_year | 2025 |
| referenced_works_count | 0 |
| abstract_inverted_index., | 7 |
| abstract_inverted_index.. | 29 |
| abstract_inverted_index.a | 8 |
| abstract_inverted_index.in | 33, 98 |
| abstract_inverted_index.of | 71 |
| abstract_inverted_index.on | 116 |
| abstract_inverted_index.or | 109 |
| abstract_inverted_index.to | 78 |
| abstract_inverted_index.DES | 6 |
| abstract_inverted_index.Our | 65 |
| abstract_inverted_index.The | 94 |
| abstract_inverted_index.and | 24, 122 |
| abstract_inverted_index.but | 59 |
| abstract_inverted_index.for | 11, 48, 91, 112 |
| abstract_inverted_index.key | 95 |
| abstract_inverted_index.our | 99 |
| abstract_inverted_index.the | 44, 68 |
| abstract_inverted_index.LLMs | 28 |
| abstract_inverted_index.This | 0 |
| abstract_inverted_index.both | 72 |
| abstract_inverted_index.each | 113 |
| abstract_inverted_index.from | 20 |
| abstract_inverted_index.have | 36 |
| abstract_inverted_index.lack | 43 |
| abstract_inverted_index.lies | 97 |
| abstract_inverted_index.like | 119 |
| abstract_inverted_index.rich | 56 |
| abstract_inverted_index.that | 16 |
| abstract_inverted_index.they | 41 |
| abstract_inverted_index.with | 61, 83 |
| abstract_inverted_index.LLMs' | 88 |
| abstract_inverted_index.While | 30 |
| abstract_inverted_index.based | 115 |
| abstract_inverted_index.fuses | 18 |
| abstract_inverted_index.graph | 14 |
| abstract_inverted_index.large | 25, 52 |
| abstract_inverted_index.novel | 9 |
| abstract_inverted_index.often | 42 |
| abstract_inverted_index.paper | 1 |
| abstract_inverted_index.query | 114 |
| abstract_inverted_index.space | 22, 76 |
| abstract_inverted_index.state | 21, 75 |
| abstract_inverted_index.which | 103 |
| abstract_inverted_index.while | 86 |
| abstract_inverted_index.entity | 123 |
| abstract_inverted_index.fusion | 101 |
| abstract_inverted_index.linear | 84 |
| abstract_inverted_index.models | 23, 27, 54 |
| abstract_inverted_index.recent | 31 |
| abstract_inverted_index.Dynamic | 3 |
| abstract_inverted_index.Mamba's | 74 |
| abstract_inverted_index.between | 106 |
| abstract_inverted_index.capture | 80 |
| abstract_inverted_index.factors | 118 |
| abstract_inverted_index.pattern | 39 |
| abstract_inverted_index.possess | 55 |
| abstract_inverted_index.selects | 105 |
| abstract_inverted_index.Encoding | 4 |
| abstract_inverted_index.adaptive | 100 |
| abstract_inverted_index.approach | 66 |
| abstract_inverted_index.combined | 110 |
| abstract_inverted_index.improved | 37 |
| abstract_inverted_index.language | 26, 53 |
| abstract_inverted_index.modeling | 35 |
| abstract_inverted_index.patterns | 82 |
| abstract_inverted_index.semantic | 45, 57, 92 |
| abstract_inverted_index.sequence | 34 |
| abstract_inverted_index.struggle | 60 |
| abstract_inverted_index.temporal | 12, 38, 63, 120 |
| abstract_inverted_index.Selection | 5 |
| abstract_inverted_index.framework | 10 |
| abstract_inverted_index.knowledge | 13, 58, 90 |
| abstract_inverted_index.leverages | 67 |
| abstract_inverted_index.necessary | 47 |
| abstract_inverted_index.proximity | 121 |
| abstract_inverted_index.reasoning | 15 |
| abstract_inverted_index.semantic, | 108 |
| abstract_inverted_index.strengths | 70 |
| abstract_inverted_index.utilizing | 87 |
| abstract_inverted_index.Similarly, | 51 |
| abstract_inverted_index.adaptively | 17 |
| abstract_inverted_index.contextual | 117 |
| abstract_inverted_index.innovation | 96 |
| abstract_inverted_index.introduces | 2 |
| abstract_inverted_index.mechanism, | 102 |
| abstract_inverted_index.reasoning. | 50 |
| abstract_inverted_index.sequential | 81 |
| abstract_inverted_index.structured | 62 |
| abstract_inverted_index.complexity, | 85 |
| abstract_inverted_index.dynamically | 104 |
| abstract_inverted_index.efficiently | 79 |
| abstract_inverted_index.pre-trained | 89 |
| abstract_inverted_index.sequential, | 107 |
| abstract_inverted_index.advancements | 32 |
| abstract_inverted_index.architecture | 77 |
| abstract_inverted_index.recognition, | 40 |
| abstract_inverted_index.complementary | 69 |
| abstract_inverted_index.comprehensive | 49 |
| abstract_inverted_index.connectivity. | 124 |
| abstract_inverted_index.dependencies. | 64 |
| abstract_inverted_index.understanding | 46 |
| abstract_inverted_index.understanding. | 93 |
| abstract_inverted_index.representations | 19, 111 |
| abstract_inverted_index.paradigms—employing | 73 |
| cited_by_percentile_year | |
| corresponding_author_ids | https://openalex.org/A5067481838 |
| countries_distinct_count | 0 |
| institutions_distinct_count | 1 |
| citation_normalized_percentile |