TWIG: Towards pre-hoc Hyperparameter Optimisation and Cross-Graph Generalisation via Simulated KGE Models

• URL: http://arxiv.org/abs/2402.06097v1
• Date: Thu, 8 Feb 2024 23:12:02 GMT
• Title: TWIG: Towards pre-hoc Hyperparameter Optimisation and Cross-Graph Generalisation via Simulated KGE Models
• Authors: Jeffrey Sardina, John D. Kelleher, Declan O'Sullivan
• Abstract summary: We introduce TWIG (Topologically-Weighted Intelligence Generation), a novel, embedding-free paradigm for simulating the output of KGEs. Experiments on the UMLS dataset show that a single TWIG neural network can predict the results of state-of-the-art ComplEx-N3 KGE model.
• Score: 2.550226198121927
• License: http://creativecommons.org/licenses/by/4.0/
• Abstract: In this paper we introduce TWIG (Topologically-Weighted Intelligence Generation), a novel, embedding-free paradigm for simulating the output of KGEs that uses a tiny fraction of the parameters. TWIG learns weights from inputs that consist of topological features of the graph data, with no coding for latent representations of entities or edges. Our experiments on the UMLS dataset show that a single TWIG neural network can predict the results of state-of-the-art ComplEx-N3 KGE model nearly exactly on across all hyperparameter configurations. To do this it uses a total of 2590 learnable parameters, but accurately predicts the results of 1215 different hyperparameter combinations with a combined cost of 29,322,000 parameters. Based on these results, we make two claims: 1) that KGEs do not learn latent semantics, but only latent representations of structural patterns; 2) that hyperparameter choice in KGEs is a deterministic function of the KGE model and graph structure. We further hypothesise that, as TWIG can simulate KGEs without embeddings, that node and edge embeddings are not needed to learn to accurately predict new facts in KGs. Finally, we formulate all of our findings under the umbrella of the ``Structural Generalisation Hypothesis", which suggests that ``twiggy" embedding-free / data-structure-based learning methods can allow a single neural network to simulate KGE performance, and perhaps solve the Link Prediction task, across many KGs from diverse domains and with different semantics.

Related papers

• Extending TWIG: Zero-Shot Predictive Hyperparameter Selection for KGEs based on Graph Structure [2.2690868277262486]
  The Topologically-Weighted Intelligence Generation (TWIG) model has been proposed as a solution to modelling how each of these elements relate. We extend the previous research on TWIG and evaluate its ability to simulate the output of the KGE model ComplEx in the cross-KG setting.
  arXiv  Detail & Related papers  (2024-12-19T12:47:21Z)
• Semi-parametric Expert Bayesian Network Learning with Gaussian Processes and Horseshoe Priors [26.530289799110562]
  This paper proposes a model learning Semi-parametric rela- tionships in an Expert Bayesian Network (SEBN) We use Gaussian Pro- cesses and a Horseshoe prior to introduce minimal nonlin- ear components. In real-world datasets with unknown truth, we gen- erate diverse graphs to accommodate user input, addressing identifiability issues and enhancing interpretability.
  arXiv  Detail & Related papers  (2024-01-29T18:57:45Z)
• A Comprehensive Study on Knowledge Graph Embedding over Relational Patterns Based on Rule Learning [49.09125100268454]
  Knowledge Graph Embedding (KGE) has proven to be an effective approach to solving the Knowledge Completion Graph (KGC) task. Relational patterns are an important factor in the performance of KGE models. We introduce a training-free method to enhance KGE models' performance over various relational patterns.
  arXiv  Detail & Related papers  (2023-08-15T17:30:57Z)
• GCondNet: A Novel Method for Improving Neural Networks on Small High-Dimensional Tabular Data [14.124731264553889]
  We propose GCondNet to enhance neural networks by leveraging implicit structures present in data. GCondNet exploits the data's high-dimensionality, and thus improves the performance of an underlying predictor network. We demonstrate GCondNet's effectiveness on 12 real-world datasets, where it outperforms 14 standard and state-of-the-art methods.
  arXiv  Detail & Related papers  (2022-11-11T16:13:34Z)
• ExpressivE: A Spatio-Functional Embedding For Knowledge Graph Completion [78.8942067357231]
  ExpressivE embeds pairs of entities as points and relations as hyper-parallelograms in the virtual triple space. We show that ExpressivE is competitive with state-of-the-art KGEs and even significantly outperforms them on W18RR.
  arXiv  Detail & Related papers  (2022-06-08T23:34:39Z)
• Sequence-to-Sequence Knowledge Graph Completion and Question Answering [8.207403859762044]
  We show that an off-the-shelf encoder-decoder Transformer model can serve as a scalable and versatile KGE model. We achieve this by posing KG link prediction as a sequence-to-sequence task and exchange the triple scoring approach taken by prior KGE methods with autoregressive decoding.
  arXiv  Detail & Related papers  (2022-03-19T13:01:49Z)
• Post-mortem on a deep learning contest: a Simpson's paradox and the complementary roles of scale metrics versus shape metrics [61.49826776409194]
  We analyze a corpus of models made publicly-available for a contest to predict the generalization accuracy of neural network (NN) models. We identify what amounts to a Simpson's paradox: where "scale" metrics perform well overall but perform poorly on sub partitions of the data. We present two novel shape metrics, one data-independent, and the other data-dependent, which can predict trends in the test accuracy of a series of NNs.
  arXiv  Detail & Related papers  (2021-06-01T19:19:49Z)
• ACDC: Weight Sharing in Atom-Coefficient Decomposed Convolution [57.635467829558664]
  We introduce a structural regularization across convolutional kernels in a CNN. We show that CNNs now maintain performance with dramatic reduction in parameters and computations.
  arXiv  Detail & Related papers  (2020-09-04T20:41:47Z)
• Learning Reasoning Strategies in End-to-End Differentiable Proving [50.9791149533921]
  Conditional Theorem Provers learn optimal rule selection strategy via gradient-based optimisation. We show that Conditional Theorem Provers are scalable and yield state-of-the-art results on the CLUTRR dataset.
  arXiv  Detail & Related papers  (2020-07-13T16:22:14Z)
• Embedding Graph Auto-Encoder for Graph Clustering [90.8576971748142]
  Graph auto-encoder (GAE) models are based on semi-supervised graph convolution networks (GCN) We design a specific GAE-based model for graph clustering to be consistent with the theory, namely Embedding Graph Auto-Encoder (EGAE) EGAE consists of one encoder and dual decoders.
  arXiv  Detail & Related papers  (2020-02-20T09:53:28Z)

This list is automatically generated from the titles and abstracts of the papers in this site.

This site does not guarantee the quality of this site (including all information) and is not responsible for any consequences.