REVIEW 10 cited by
TuckER: Tensor Factorization for Knowledge Graph Completion
Not yet reviewed by Pith; the record is open.
This paper has not been read by Pith yet. Machine review is queued; the pith claim, tier, and objections will appear here once it completes.
SPECIMEN: schema-true, not a live event
T0 review · schema-true
One-sentence machine reading of the paper's core claim.
pith:XXXXXXXX · record.json · timestamp
read the original abstract
Knowledge graphs are structured representations of real world facts. However, they typically contain only a small subset of all possible facts. Link prediction is a task of inferring missing facts based on existing ones. We propose TuckER, a relatively straightforward but powerful linear model based on Tucker decomposition of the binary tensor representation of knowledge graph triples. TuckER outperforms previous state-of-the-art models across standard link prediction datasets, acting as a strong baseline for more elaborate models. We show that TuckER is a fully expressive model, derive sufficient bounds on its embedding dimensionalities and demonstrate that several previously introduced linear models can be viewed as special cases of TuckER.
Forward citations
Cited by 10 Pith papers
-
Two-dimensional Taxonomy for N-ary Knowledge Representation Learning Methods
A survey of n-ary knowledge representation learning methods proposes a two-dimensional taxonomy based on modeling technique and entity role/position awareness.
-
HERGC: Heterogeneous Experts Representation and Generative Completion for Multimodal Knowledge Graphs
HERGC combines a multimodal expert-based retriever with a fine-tuned LLM re-ranker to achieve state-of-the-art multimodal knowledge graph completion on MKG-W, MKG-Y, and DB15K.
-
MEDMKG: Benchmarking Medical Knowledge Exploitation with Multimodal Knowledge Graph
MEDMKG is a multimodal medical knowledge graph linking chest X-ray images to UMLS concepts, with a Neighbor-aware Filtering algorithm and benchmarks showing mixed but often positive downstream gains.
-
AgREE: Agentic Reasoning for Knowledge Graph Completion on Emerging Entities
A zero-training LLM agent that iteratively retrieves and reflects over search results can complete knowledge graph triples about emerging entities better than trained KGC models, the authors report.
-
Efficiently Generating Multidimensional Calorimeter Data with Tensor Decomposition Parameterization
Generating CPD tensor factors instead of full tensors inside GANs and diffusion models can cut output parameters by roughly 80-90% while keeping similar FID scores on calorimeter data.
-
Complementarity-driven Representation Learning for Multi-modal Knowledge Graph Completion
MoCME combines expert-network fusion weighted by estimated mutual information and entropy-based negative sampling, and reports state-of-the-art multi-modal knowledge graph completion on five benchmarks.
-
KG-BiLM: Knowledge Graph Embedding via Bidirectional Language Models
A bidirectional decoder with a graph-aware attention mask, knowledge-masked prediction, and contrastive sub-graph alignment achieves reported state-of-the-art link prediction on Wikidata5M and competitive results on WN18RR.
-
Rethinking Regularization Methods for Knowledge Graph Completion
A selective sparsity regularizer, SPR, nudges link prediction metrics up on standard benchmarks, but the evidence is single-run and the theoretical justification is mathematically flawed.
-
Towards Structure-aware Model for Multi-modal Knowledge Graph Completion
TSAM combines token-level fusion of visual and textual data with structure-anchored contrastive learning, outperforming prior multi-modal KGC models on DB15K, MKG-W, and MKG-Y.
-
Is Architectural Complexity Overrated? Competitive and Interpretable Knowledge Graph Completion with RelatE
RelatE, a real-valued phase-modulus embedding model, achieves the best reported MRR on YAGO3-10 (0.521) but falls far behind RotatE on WN18RR and relies on flawed formal proofs.
Discussion (0). Continue with ORCID to comment.