Notice: This website is continuously updated as new conference proceedings and journal volumes are published. Consequently, the figures presented here may differ from those reported in our publications.
A brief overview of our methodology is provided on the Methods page, along with references to publications documenting our approach and links to the code and data used in each study.
The reproducibility variables underlying each score are classified using an automated LLM-based pipeline, validated against a manually labeled dataset. LLM-based classification introduces uncertainty and potential bias; scores should be interpreted as estimates.
Adversarial Explanations for Knowledge Graph Embeddings
Authors: Patrick Betz, Christian Meilicke, Heiner Stuckenschmidt
IJCAI 2022 | Venue PDF | LLM Run Details | Input Tokens: 16,935 Total number of tokens sent to the LLM as input for this paper's analysis. | Output Tokens: 5,770 Total number of tokens produced by the LLM (including reasoning/thinking tokens) for this paper's analysis.
| Reproducibility Variable | Result | LLM Response |
|---|---|---|
| Research Type | Experimental | We report results on par with state-of-the-art white-box attack methods that additionally require full access to the model architecture, the learned embeddings, and the loss functions. This is a surprising result which indicates that knowledge graph embedding models can partly be explained post hoc with the help of symbolic methods. |
| Researcher Affiliation | Academia | Patrick Betz , Christian Meilicke and Heiner Stuckenschmidt University of Mannheim, Research Group Data and Web Science EMAIL |
| Pseudocode | No | The paper does not contain structured pseudocode or algorithm blocks. It provides definitions but not algorithmic steps. |
| Open Source Code | Yes | Further details about KGE training and the code for running all experiments can be found in the supplementary material. |
| Open Datasets | Yes | We use the KGE models Compl Ex [Trouillon et al., 2016], Dist Mult [Yang et al., 2015] and Conv E [Dettmers et al., 2018] and the same datasets as [Bhardwaj et al., 2021], i.e., we use the common benchmarks WN18RR and FB15k-237. |
| Dataset Splits | Yes | Datasets are usually split into training, validation and test sets where evaluation takes place by forming queries as described above for all the triples in the test set. |
| Hardware Specification | No | The paper does not provide specific hardware details (exact GPU/CPU models, processor types with speeds, memory amounts, or detailed computer specifications) used for running its experiments. |
| Software Dependencies | No | The paper does not provide specific ancillary software details (e.g., library or solver names with version numbers) needed to replicate the experiment. |
| Experiment Setup | Yes | We have set the time available for Any BURL to learn the rule set to 100 seconds. |