Papers › Knowledge Graphs Meet Multi-Modal Learning: A Comprehensive Survey

Knowledge Graphs Meet Multi-Modal Learning: A Comprehensive Survey

8 Feb 2024arXiv:2402.05391archive 2025-07-28

Zhuo Chen, Yichi Zhang, Yin Fang, Yuxia Geng, Lingbing Guo, Xiang Chen, Qian Li, Wen Zhang, Jiaoyan Chen, Yushan Zhu, Jiaqi Li, Xiaoze Liu, Jeff Z. Pan, Ningyu Zhang, Huajun Chen

Knowledge Graphs (KGs) play a pivotal role in advancing various AI applications, with the semantic web community's exploration into multi-modal dimensions unlocking new avenues for innovation. In this survey, we carefully review over 300 articles, focusing on KG-aware research in two principal aspects: KG-driven Multi-Modal (KG4MM) learning, where KGs support multi-modal tasks, and Multi-Modal Knowledge Graph (MM4KG), which extends KG studies into the MMKG realm. We begin by defining KGs and MMKGs, then explore their construction progress. Our review includes two primary task categories: KG-aware multi-modal learning tasks, such as Image Classification and Visual Question Answering, and intrinsic MMKG tasks like Multi-modal Knowledge Graph Completion and Entity Alignment, highlighting specific research trajectories. For most of these tasks, we provide definitions, evaluation benchmarks, and additionally outline essential insights for conducting relevant research. Finally, we discuss current challenges and identify emerging trends, such as progress in Large Language Modeling and Multi-modal Pre-training strategies. This survey aims to serve as a comprehensive reference for researchers already involved in or considering delving into KG and multi-modal learning research, offering insights into the evolving landscape of MMKG research and supporting future work.

PaperPDFCodeCode Syntology ran

In Syntology View this paper on Syntology, its page in Syntology's graph. That page adds which of its functions are also present in other papers' code Syntology holds, with dates, and its dated run record as JSON and a README badge. It also lists the repositories linked to the paper, the abstract and the calls for agents.

Open this paper in Syntology's Atlas, the map of the papers in Syntology's graph and their citations.

For agents, on Syntology's MCP service (how to connect):

Code

The archive's official repository (zjukg/kg-mm-survey) was not harvested; the 18 samples below come from 3 community repositories.

Syntology 18 code samples harvested from 3 repositories linked to this paper: 15 ran (of which 0 constructed an object rather than computing a result; 10 with no instrument failure: 0 honoured, 2 violated, 8 with no contract checked; 5 where Syntology's instrument failed) · 3 unverified. Where Syntology's instrument failed: 4 where our contract draft was wrong; 1 where the contract check could not run; failures of Syntology's instrument, not of the code.

By repository: community (archive-listed): 18 samples from 3 repositories, 15 ran (10 with no instrument failure; 5 where Syntology's instrument failed). The run record, sample by sample. “Ran” means executed on a synthesized input, not that the code is correct or reproduces the paper.

Levels written between 2026-09-22 and 2026-09-26 (UTC): the dates Syntology's graph wrote each sample's verification level, not when the code executed.

zjukg/kg-mm-survey officialmentioned in papermentioned on GitHubMITSyntology: not harvested report
China-UK-ZSL/ZS-F-VQA mentioned on GitHubpytorchMITSyntology: 2 samples, 2 ran (2 instrument-failed) · 0 unverified report
hackerchenzhuo/LaKo mentioned on GitHubpytorchMITSyntology: 10 samples, 8 ran (1 instrument-failed) · 2 unverified report
zjukg/maco mentioned on GitHubpytorchSyntology: not harvested report
zjukg/mygo mentioned on GitHubpytorchSyntology: not harvested report
zjukg/snag mentioned on GitHubpytorchMITSyntology: 6 samples, 5 ran (2 instrument-failed) · 1 unverified report

Repository list and official/mentioned flags are the archive's, frozen 2025-07-28. Reachability, where shown, is from one Syntology probe window (2026-09-16 to 2026-09-18); repositories not probed show nothing. GitHub stars are not tracked.

Code Syntology ran Syntology

18 samples harvested: 15 ran (of which 0 constructed an object rather than computing a result; 10 with no instrument failure: 0 honoured, 2 violated, 8 with no contract checked; 5 where Syntology's instrument failed) · 3 unverified. “Where Syntology's instrument failed” counts failures of Syntology's instrument, not of the code. Syntology's record for this page last changed ; when this build read Syntology's graph is in the build record. That date is not when the samples ran.

2ran · violated contract
4ran · our draft was wrong
1ran; the contract check could not run
8ran
3unverified

Licence: 4 of the 18 samples are pointer only, meaning Syntology does not serve that copy's text. For 4 of them, this paper's copy is under a permissive licence and cleared, but the stored copy of the same code that Syntology serves is not; the licence label's tooltip gives Syntology's recorded reason. This page shows no code text for any sample; each one links to its file in the repository.

Harvested from 3 repositories linked to this paper, official or community; the list below is grouped by repository, each group headed by its name and what it is to the paper. “Ran” means the sample executed on a synthesized input. It does not mean the output is correct, and nothing here reproduces the paper's results. A line beginning “fixture:” under a sample that ran gives the arguments Syntology's fixture called the sample with, each as name:type/rank/element kind (? where none was recorded), and the type of what the fixture's run returned, exactly as the harness recorded them; the arguments and the returned type were recorded by two separate runs of the same fixture. No output value is shown, and a returned type says nothing about whether the output was right. “Level recorded” gives the UTC date when Syntology's graph wrote the sample's verification level, not when the code executed; where the level was written before Syntology's graph kept that date, the row says “level recorded, date not recorded”. “Honoured” and “violated” refer to a contract Syntology drafted from the code itself. “Our draft was wrong” and “the contract check could not run” are failures of Syntology's instrument, not of the code: the sample ran on Syntology's synthesized input, and then the drafted contract did not describe it, or the check itself raised an error (RAISES), lacked a dependency (DEP_MISSING) or ran out of time (TIMEOUT); hover the label for which. A metamorphic tier, where shown, is evidence of the output's shape, not that the sample implements the method.

Each sample ends with its code_sha256. A sample's code_sha256 is Syntology's identity for that exact code. It is printed in full (16 hexadecimal characters for every sample in this build), and get_code(code_sha256="…") takes it exactly as printed. An agent calls it on Syntology's MCP service (how to connect); click an identity to copy that call.

Repository labels, per sample. official repository: The archive marks this repository official for the paper. named in the paper: The archive records that the paper mentions this repository; it is not marked official. community (archive-listed): In the archive's code links for this paper, not marked official and not recorded as mentioned in the paper. found in paper text by Syntology: Syntology found this repository in the paper's own text; whether it is the authors' implementation is not asserted. community: Not in the archive's code links for this paper; a community repository Syntology harvested. Samples are grouped by repository: a repository marked official first, then by how directly the repository is tied to the paper, then in the archive's order; never by how many ran. Licence labels name the repository's licence as recorded at harvest. “Pointer only” means Syntology does not serve that copy's text, for one of six reasons: no licence file was found; the licence was not identified; the licence is recorded as permissive but that copy's record is not marked cleared; the licence is outside the permissive list Syntology serves text under (MIT, Apache-2.0, BSD and similar); this paper's copy was not located, so its licence is not recorded; or this paper's copy is cleared, but the stored copy of the same code that Syntology serves is not. Some licences outside that list permit redistribution, such as WTFPL, and GPL-3.0 under its conditions; they are simply not on the list. Hover a licence label for the reason. File links open the file on GitHub at the default branch, which may have changed since the harvest.

A function or class name links to its page when the name occurs in the harvested code of at least 5 papers; the name is a string, not an identity. A census tag appears when Syntology's census ran implementations with that name on one shared input per bucket: it gives how many were compared, from how many papers, and how many distinct outputs they produced, and names this sample's bucket when this sample was one of them.

China-UK-ZSL/ZS-F-VQA community (archive-listed) 2 samples, 2 ran (2 instrument-failed) · 0 unverified
apply_attention in 5 papers code/model/attention.py ran · our draft was wrong fingerprinted MIT (permissive) · 745b7eb38c9d1b29 · report fixture: signature input:Tensor/4/float, attention:Tensor/4/float · returned Tensor · level recorded 2026-09-24
tile_2d_over_nd code/model/attention.py ran · our draft was wrong fingerprinted MIT (permissive) · b70265fc26e335dc · report fixture: signature feature_vector:Tensor/2/float, feature_map:Tensor/4/float · returned Tensor · level recorded 2026-09-24
hackerchenzhuo/LaKo community (archive-listed) 10 samples, 8 ran (1 instrument-failed) · 2 unverified
add_embeddings in 8 papers fact_retrieval.py ran MIT (permissive) · ac1c2010e4fa00c6 · report fixture: signature index:MockIndex/0/?, embeddings:Tensor/2/float, ids:list/1/int, indexing_batch_size:int/0/int · returned tuple · level recorded 2026-09-24
check_answer in 28 papers src/evaluation.py ran · violated contract MIT (permissive) here; the stored copy is pointer only · 637b51b8df78832a · report fixture: signature example:dict/0/?, tokenizer:SimpleTokenizer/0/? · returned list · level recorded 2026-09-25
cross_attention_forward in 14 papers src/model.py ran; the contract check could not run (RAISES) · metamorphic tier: deterministic MIT (permissive) · 6bef6bdd6eb44070 · report fixture: signature self:callable/0/?, input:Tensor/3/float, mask:Tensor/4/float, kv:Tensor/3/float, position_bias:Tensor/4/float, past_key_value_state:NoneType/0/?, head_mask:NoneType/0/?, query_length:NoneType/0/?, use_cache:bool/0/bool, output_attentions:bool/0/bool · returned tuple · level recorded 2026-09-22
encode_passages in 10 papers src/data.py ran MIT (permissive) · bc0dae797248182b · report fixture: signature batch_text_passages:list/1/list, tokenizer:StandInTokenizer/0/?, max_length:int/0/int · returned tuple · level recorded 2026-09-24
has_answer in 26 papers src/evaluation.py ran · violated contract MIT (permissive) here; the stored copy is pointer only · fa4ecbff4b9a354b · report fixture: signature answers:list/1/str, text:str/0/str, tokenizer:SimpleTokenizer/0/? · returned bool · level recorded 2026-09-25
load_data in 700 papers src/data.py ran MIT (permissive) · 0ec5a25ad1d89cc8 · report fixture: signature data_path:str/0/str, global_rank:int/0/int, world_size:int/0/int · returned list · level recorded 2026-09-24
select_examples_NQ src/preprocess.py ran MIT (permissive) · e2f8b9900fd662b1 · report fixture: signature data:dict/0/?, index:list/1/int, passages:dict/0/?, passages_index:dict/0/? · returned list · level recorded 2026-09-24
select_examples_TQA src/preprocess.py ran MIT (permissive) · e544cd4b39e5ec61 · report fixture: signature data:list/1/dict, index:list/1/int, passages:list/1/list, passages_index:dict/0/? · returned list · level recorded 2026-09-24
calculate_matches in 15 papers src/evaluation.py unverified MIT (permissive) here; the stored copy is pointer only · 7a4988952dd3a127 · report
get_options in 25 papers src/options.py unverified MIT (permissive) · b4e32355db15fe9f · report
zjukg/snag community (archive-listed) 6 samples, 5 ran (2 instrument-failed) · 1 unverified
attention in 144 papers
census: 11 implementations from 10 papers, 7 distinct outputs across 5 buckets, one shared input per bucket
SNAG_MMEA/model/EVA_tools.py ran · our draft was wrong MIT (permissive) · e7d0985e55efb9e7 · report fixture: signature q:Tensor/3/float, k:Tensor/3/float, v:Tensor/3/float, d_k:int/0/int, mask:Tensor/4/float, dropout:callable/0/? · returned Tensor · level recorded 2026-09-26
cosine_sim in 34 papers SNAG_MMEA/model/EVA_tools.py ran · our draft was wrong fingerprinted MIT (permissive) here; the stored copy is pointer only · 9b0a787b92a87023 · report fixture: signature im:Tensor/2/float, s:Tensor/2/float · returned Tensor · level recorded 2026-09-22
generate_pos_triples SNAG_MMEA/model/MSNEA_tools.py ran MIT (permissive) · 681342822f804578 · report fixture: signature triples:list/1/tuple, batch_size:int/0/int, step:int/0/int, is_fixed_size:bool/0/bool · returned list · level recorded 2026-09-24
generate_relation_triple_batch SNAG_MMEA/model/MSNEA_tools.py ran MIT (permissive) · bda2af2880f66879 · report fixture: signature triple_list1:list/1/tuple, triple_list2:list/1/tuple, triple_set1:set/0/?, triple_set2:set/0/?, entity_list1:list/1/int, entity_list2:list/1/int, batch_size:int/0/int, step:int/0/int, neg_triples_num:int/0/int · returned tuple · level recorded 2026-09-25
l2norm in 84 papers
census: 12 implementations from 20 papers, 3 distinct outputs on one shared input
SNAG_MMEA/model/EVA_tools.py ran fingerprinted MIT (permissive) · 433bcbe46a942d69 · report fixture: signature X:Tensor/2/float · returned Tensor · level recorded 2026-09-25
generate_neg_triples_fast SNAG_MMEA/model/MSNEA_tools.py unverified MIT (permissive) · b107f7a819444b4f · report

Tasks

ArticlesEntity AlignmentImage ClassificationKnowledge Graph CompletionKnowledge GraphsLanguage ModelingLanguage ModellingMulti-modal Knowledge GraphSurveyVisual Question Answeringimage-classification

Results from the paper archive 2025-07-28

No leaderboard rows for this paper in the archive.

Report a problem or propose a change · a person checks every report against the paper or source before anything changes; decisions are listed on /corrections