Pith. sign in

REVIEW 14 cited by

Composition-based Multi-Relational Graph Convolutional Networks

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

arxiv 1911.03082 v2 pith:UTEVMXIN submitted 2019-11-08 cs.LG stat.ML

classification cs.LGstat.ML
keywords graphgraphscompgcnconvolutionalmulti-relationalbeenclassificationexisting
verification ladder T0 review T1 audit T2 compute T3 formal
0 comments
read the original abstract

Graph Convolutional Networks (GCNs) have recently been shown to be quite successful in modeling graph-structured data. However, the primary focus has been on handling simple undirected graphs. Multi-relational graphs are a more general and prevalent form of graphs where each edge has a label and direction associated with it. Most of the existing approaches to handle such graphs suffer from over-parameterization and are restricted to learning representations of nodes only. In this paper, we propose CompGCN, a novel Graph Convolutional framework which jointly embeds both nodes and relations in a relational graph. CompGCN leverages a variety of entity-relation composition operations from Knowledge Graph Embedding techniques and scales with the number of relations. It also generalizes several of the existing multi-relational GCN methods. We evaluate our proposed method on multiple tasks such as node classification, link prediction, and graph classification, and achieve demonstrably superior results. We make the source code of CompGCN available to foster reproducible research.

Discussion (0). Sign in to comment.

Forward citations

Cited by 14 Pith papers

Reviewed papers in the Pith corpus that reference this work. Sorted by Pith novelty score. Full citation record

  1. Modeling All-Atom Glycan Structures via Hierarchical Message Passing and Multi-Scale Pre-training

    cs.LG 2025-06 conditional novelty 7.0 of 10

    PreGlycanAA, a hierarchical all-atom glycan encoder with multi-scale mask pre-training, ranks first on the GlycanML benchmark, with its non-pre-trained base GlycanAA ranking second.

  2. Nonlinear Laplacians Improve Signed-Directed Graph Learning

    cs.LG 2026-08 conditional novelty 6.0 of 10

    A signed-directed nonlinear Laplacian is defined, proven positive semidefinite with bounded spectrum, and used to build a GNN that filters edges by node potentials.

  3. Enhancing Large Language Model for Knowledge Graph Completion via Structure-Aware Alignment-Tuning

    cs.CL 2025-09 reject novelty 6.0 of 10

    SAT uses hierarchical contrastive alignment and a unified graph instruction to tune a lightweight adapter for knowledge graph completion, reporting large link prediction gains.

  4. BioGraphFusion: Graph Knowledge Embedding for Biological Completion and Reasoning

    cs.AI 2025-07 conditional novelty 6.0 of 10

    A hybrid semantic-structural graph model with CP decomposition, LSTM-based relation refinement, query-guided subgraph propagation, and a blended scoring function reports state-of-the-art accuracy on three biomedical k...

  5. Context Pooling: Query-specific Graph Pooling for Generic Inductive Link Prediction in Knowledge Graphs

    cs.AI 2025-07 conditional novelty 6.0 of 10

    Context Pooling improves inductive link prediction in knowledge graphs by building a query-specific subgraph that keeps only neighbors whose relation types co-occur with the query relation.

  6. Two-dimensional Taxonomy for N-ary Knowledge Representation Learning Methods

    cs.LG 2025-06 conditional novelty 6.0 of 10

    A survey of n-ary knowledge representation learning methods proposes a two-dimensional taxonomy based on modeling technique and entity role/position awareness.

  7. HERGC: Heterogeneous Experts Representation and Generative Completion for Multimodal Knowledge Graphs

    cs.CL 2025-06 conditional novelty 6.0 of 10

    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.

  8. Beyond Completion: A Foundation Model for General Knowledge Graph Reasoning

    cs.CL 2025-05 conditional novelty 6.0 of 10

    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.

  9. Context-Driven Knowledge Graph Completion with Semantic-Aware Relational Message Passing

    cs.AI 2025-06 conditional novelty 5.0 of 10

    SARMP improves knowledge graph link prediction by selecting the Top-K semantically relevant edges per node and aggregating them with multi-head attention, beating some baselines on FB15k-237 and Kinship but not all be...

  10. Disentangled Multi-span Evolutionary Network against Temporal Knowledge Graph Reasoning

    cs.AI 2025-05 conditional novelty 5.0 of 10

    DiMNet combines multi-span cross-time message passing with disentangled active/stable node factors to set new state-of-the-art MRR on four TKG extrapolation benchmarks.

  11. Sequential Learner Modeling Using Multi-Relational Graph Convolutional Networks

    cs.AI 2026-07 reject novelty 4.0 of 10

    An unsupervised multi-relational GCN learner-modeling pipeline is described, but its own user study finds no significant benefit over the single-relation ConceptGCN baseline.

  12. KG-BiLM: Knowledge Graph Embedding via Bidirectional Language Models

    cs.CL 2025-06 conditional novelty 4.0 of 10

    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.

  13. Towards Structure-aware Model for Multi-modal Knowledge Graph Completion

    cs.MM 2025-05 conditional novelty 4.0 of 10

    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.

  14. Unifying Adversarial Perturbation for Graph Neural Networks

    cs.LG 2025-08 reject novelty 3.0 of 10

    Adding perturbations directly to every hidden embedding of a GNN is claimed to subsume existing feature-, edge-, and weight-perturbation defenses, but the claim rests on simplifications that the experiments do not act...

Pith tools