Is Architectural Complexity Overrated? Competitive and Interpretable Knowledge Graph Completion with RelatE
Fuente:
arXiv
Salvato in:
| Autori principali: | , , , , |
|---|---|
| Natura: | Preprint |
| Pubblicazione: |
2025
|
| Soggetti: | |
| Accesso online: | |
| Tags: |
Aggiungi Tag
Nessun Tag, puoi essere il primo ad aggiungerne!!
|
| _version_ | 1866915303905034240 |
|---|---|
| author | Chakraborty, Abhijit Dahal, Chahana Balasubramaniam, Ashutosh Anvekar, Tejas Gupta, Vivek |
| author_facet | Chakraborty, Abhijit Dahal, Chahana Balasubramaniam, Ashutosh Anvekar, Tejas Gupta, Vivek |
| contents | We revisit the efficacy of simple, real-valued embedding models for knowledge graph completion and introduce RelatE, an interpretable and modular method that efficiently integrates dual representations for entities and relations. RelatE employs a real-valued phase-modulus decomposition, leveraging sinusoidal phase alignments to encode relational patterns such as symmetry, inversion, and composition. In contrast to recent approaches based on complex-valued embeddings or deep neural architectures, RelatE preserves architectural simplicity while achieving competitive or superior performance on standard benchmarks. Empirically, RelatE outperforms prior methods across several datasets: on YAGO3-10, it achieves an MRR of 0.521 and Hit@10 of 0.680, surpassing all baselines. Additionally, RelatE offers significant efficiency gains, reducing training time by 24%, inference latency by 31%, and peak GPU memory usage by 22% compared to RotatE. Perturbation studies demonstrate improved robustness, with MRR degradation reduced by up to 61% relative to TransE and by up to 19% compared to RotatE under structural edits such as edge removals and relation swaps. Formal analysis further establishes the model's full expressiveness and its capacity to represent essential first-order logical inference patterns. These results position RelatE as a scalable and interpretable alternative to more complex architectures for knowledge graph completion. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2505_18971 |
| institution | arXiv |
| publishDate | 2025 |
| record_format | arxiv |
| spellingShingle | Is Architectural Complexity Overrated? Competitive and Interpretable Knowledge Graph Completion with RelatE Chakraborty, Abhijit Dahal, Chahana Balasubramaniam, Ashutosh Anvekar, Tejas Gupta, Vivek Computation and Language Information Retrieval We revisit the efficacy of simple, real-valued embedding models for knowledge graph completion and introduce RelatE, an interpretable and modular method that efficiently integrates dual representations for entities and relations. RelatE employs a real-valued phase-modulus decomposition, leveraging sinusoidal phase alignments to encode relational patterns such as symmetry, inversion, and composition. In contrast to recent approaches based on complex-valued embeddings or deep neural architectures, RelatE preserves architectural simplicity while achieving competitive or superior performance on standard benchmarks. Empirically, RelatE outperforms prior methods across several datasets: on YAGO3-10, it achieves an MRR of 0.521 and Hit@10 of 0.680, surpassing all baselines. Additionally, RelatE offers significant efficiency gains, reducing training time by 24%, inference latency by 31%, and peak GPU memory usage by 22% compared to RotatE. Perturbation studies demonstrate improved robustness, with MRR degradation reduced by up to 61% relative to TransE and by up to 19% compared to RotatE under structural edits such as edge removals and relation swaps. Formal analysis further establishes the model's full expressiveness and its capacity to represent essential first-order logical inference patterns. These results position RelatE as a scalable and interpretable alternative to more complex architectures for knowledge graph completion. |
| title | Is Architectural Complexity Overrated? Competitive and Interpretable Knowledge Graph Completion with RelatE |
| topic | Computation and Language Information Retrieval |
| url | https://arxiv.org/abs/2505.18971 |