REVIEW 7 cited by
Convolutional 2D Knowledge Graph Embeddings
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
Signed reviews
read the original abstract
Link prediction for knowledge graphs is the task of predicting missing relationships between entities. Previous work on link prediction has focused on shallow, fast models which can scale to large knowledge graphs. However, these models learn less expressive features than deep, multi-layer models -- which potentially limits performance. In this work, we introduce ConvE, a multi-layer convolutional network model for link prediction, and report state-of-the-art results for several established datasets. We also show that the model is highly parameter efficient, yielding the same performance as DistMult and R-GCN with 8x and 17x fewer parameters. Analysis of our model suggests that it is particularly effective at modelling nodes with high indegree -- which are common in highly-connected, complex knowledge graphs such as Freebase and YAGO3. In addition, it has been noted that the WN18 and FB15k datasets suffer from test set leakage, due to inverse relations from the training set being present in the test set -- however, the extent of this issue has so far not been quantified. We find this problem to be severe: a simple rule-based model can achieve state-of-the-art results on both WN18 and FB15k. To ensure that models are evaluated on datasets where simply exploiting inverse relations cannot yield competitive results, we investigate and validate several commonly used datasets -- deriving robust variants where necessary. We then perform experiments on these robust datasets for our own and several previously proposed models and find that ConvE achieves state-of-the-art Mean Reciprocal Rank across most datasets.
Forward citations
Cited by 7 Pith papers
-
Beyond Completion: A Foundation Model for General Knowledge Graph Reasoning
MERRY integrates graph structure and entity/relation text via multi-perspective message passing, improving zero-shot knowledge graph completion and question answering over strong baselines.
-
Transformers for Complex Query Answering over Knowledge Hypergraphs
LKHGT, a two-stage transformer with type-aware bias, achieves state-of-the-art average MRR on new knowledge-hypergraph query datasets JF17k-HCQA and M-FB15k-HCQA.
-
Distributional Negative Sampling for Knowledge Base Completion
Distributional negative sampling, which selects corrupted entities by cosine similarity to the original entity, improves several knowledge-base completion metrics for TransE and RESCAL on three benchmarks, though not ...
-
Multimodal Cultural Heritage Knowledge Graph Extension with Language and Vision Models
Authors release the multimodal WJoconde knowledge graph for French cultural heritage and a LLM-VLM pipeline that extracts and validates new triples from unstructured text and images to extend the graph.
-
GRIP: In-Parameter Graph Reasoning through Fine-Tuning Large Language Models
An LLM can memorize a knowledge graph into LoRA weights and answer relation/reasoning queries about it without graph context, but the evaluation partly trains on the test task.
-
Populating Web Scale Knowledge Graphs using Distantly Supervised Relation Extraction and Validation
A relation-extraction pipeline trains a knowledge-base completion model on its own noisy output to re-rank candidate facts, claiming large accuracy gains that the evaluation setup does not support.
-
Graph Collaborative Attention Network for Link Prediction in Knowledge Graphs
GCAT is presented as a new graph attention model for knowledge graph link prediction, but its equations are those of KBGAT and its reported benchmark numbers do not support the stated performance claims.
Discussion (0). Continue with ORCID to comment.