{"type":"ScholarlyArticle","title":"Adversarial Explanations for Knowledge Graph Embeddings","authors":[{"name":"Patrick Betz","slug":"patrick-betz","given":"Patrick","family":"Betz","affiliation":"University of Mannheim , Research Group Data and Web Science"},{"name":"Christian Meilicke","slug":"christian-meilicke","given":"Christian","family":"Meilicke","affiliation":"University of Mannheim , Research Group Data and Web Science"},{"name":"Heiner Stuckenschmidt","slug":"heiner-stuckenschmidt","given":"Heiner","family":"Stuckenschmidt","affiliation":"University of Mannheim , Research Group Data and Web Science"}],"abstract":"We propose a novel black-box approach for performing adversarial attacks against knowledge graph embedding models. An adversarial attack is a small perturbation of the data at training time to cause model failure at test time. We make use of an efficient rule learning approach and use abductive reasoning to identify triples which are logical explanations for a particular prediction. The proposed attack is then based on the simple idea to suppress or modify one of the triples in the most confident explanation. Although our attack scheme is model independent and only needs access to the training data, 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.","doi":"10.24963/ijcai.2022/391","url":"https://ijcai.org/proceedings/2022/391","pdf":"https://ijcai.org/proceedings/2022/0391.pdf","markdown":"https://ijcai.org/proceedings/2022/391.md","bibtex":"https://ijcai.org/proceedings/2022/bibtex/391","volume":{"slug":"2022","title":"Proceedings of the Thirty-First International Joint Conference on Artificial Intelligence","short_title":"IJCAI 2022","url":"https://ijcai.org/proceedings/2022/","year":2022,"location":"Vienna","dates":"23-29 July 2022","editors":"Luc De Raedt","isbn":"978-1-956792-00-3","publisher":"International Joint Conferences on Artificial Intelligence Organization","doi_prefix":"10.24963/ijcai.2022"},"section":"Machine Learning","track":"Main Track","number":391,"pages":{"first":2820,"last":2826},"keywords":["Machine Learning: Relational Learning","Knowledge Representation and Reasoning: Learning and reasoning","Machine Learning: Adversarial Machine Learning","Knowledge Representation and Reasoning: Diagnosis and Abductive Reasoning","Machine Learning: Explainable/Interpretable Machine Learning"],"videos":[{"label":"Video #1","url":"https://slideslive.com/38986765","length_sec":90,"provider":"slideslive"},{"label":"Video #2","url":"https://slideslive.com/38984908","length_sec":337,"provider":"slideslive"}],"references":[{"position":1,"raw":"[Bhardwaj et al., 2021] Peru Bhardwaj, John Kelleher, Luca Costabello, and Declan O'Sullivan. Adversarial attacks on knowledge graph embeddings via instance attribution methods. In Proceedings of the 2021 Conference on Em- pirical Methods in Natural Language Processing, pages 8225-8239. Association for Computational Linguistics, 2021.","title":"Adversarial attacks on knowledge graph embeddings via instance attribution methods","authors":"Bhardwaj","year":"2021","venue":"Proceedings of the 2021 Conference on Empirical Methods in Natural Language Processing","doi":null,"url":null,"internal_url":null},{"position":2,"raw":"[Bylander et al., 1991] Tom Bylander, Dean Allemang, Michael C. Tanner, and John R. Josephson. The compu- tational complexity of abduction. Artificial Intelligence, 49(1):25-60, 1991.","title":"The computational complexity of abduction","authors":"Tom Bylander, Dean Allemang, Michael C Tanner, John R Josephson","year":"1991","venue":"Artificial Intelligence","doi":null,"url":null,"internal_url":null},{"position":3,"raw":"[Charpiat et al., 2019] Guillaume Charpiat, Nicolas Girard, Loris Felardos, and Yuliya Tarabalka. Input similarity from the neural network perspective. In NeurIPS 2019- 33th Annual Conference on Neural Information Process- ing Systems, 2019.","title":"Input similarity from the neural network perspective","authors":"Guillaume Charpiat, Nicolas Girard, Loris Felardos, Yuliya Tarabalka","year":"2019","venue":"NeurIPS 2019-33th Annual Conference on Neural Information Processing Systems","doi":null,"url":null,"internal_url":null},{"position":4,"raw":"[Dettmers et al., 2018] Tim Dettmers, Pasquale Minervini, Pontus Stenetorp, and Sebastian Riedel. Convolutional 2d knowledge graph embeddings. In Proceedings of the AAAI Conference on Artificial Intelligence, volume 32, pages 1811-1818, 2018.","title":"Convolutional 2d knowledge graph embeddings","authors":"Tim Dettmers, Pasquale Minervini, Pontus Stenetorp, Sebastian Riedel","year":"2018","venue":"Proceedings of the AAAI Conference on Artificial Intelligence","doi":null,"url":null,"internal_url":null},{"position":5,"raw":"[Galárraga et al., 2013] Luis Antonio Galárraga, Christina Teflioudi, Katja Hose, and Fabian Suchanek. Amie: as- sociation rule mining under incomplete evidence in onto- logical knowledge bases. In Proceedings of the 22nd inter- national conference on World Wide Web, pages 413-422, 2013.","title":"Amie: association rule mining under incomplete evidence in ontological knowledge bases","authors":"Luis Antonio Galárraga, Christina Teflioudi, Katja Hose, Fabian Suchanek","year":"2013","venue":"Proceedings of the 22nd international conference on World Wide Web","doi":null,"url":null,"internal_url":null},{"position":6,"raw":"[Guo et al., 2016] Shu Guo, Quan Wang, Lihong Wang, Bin Wang, and Li Guo. Jointly embedding knowledge graphs and logical rules. In Proceedings of the 2016 confer- ence on empirical methods in natural language process- ing, pages 192-202, 2016.","title":"Jointly embedding knowledge graphs and logical rules","authors":"Shu Guo, Quan Wang, Lihong Wang, Bin Wang, Li Guo","year":"2016","venue":"Proceedings of the 2016 conference on empirical methods in natural language processing","doi":null,"url":null,"internal_url":null},{"position":7,"raw":"[Guo et al., 2018] Shu Guo, Quan Wang, Lihong Wang, Bin Wang, and Li Guo. Knowledge graph embedding with iter- ative guidance from soft rules. In Proceedings of the AAAI Conference on Artificial Intelligence, volume 32, 2018.","title":"Knowledge graph embedding with iterative guidance from soft rules","authors":"Shu Guo, Quan Wang, Lihong Wang, Bin Wang, Li Guo","year":"2018","venue":"Proceedings of the AAAI Conference on Artificial Intelligence","doi":null,"url":null,"internal_url":null},{"position":8,"raw":"[Hanawa et al., 2021] Kazuaki Hanawa, Sho Yokoi, Satoshi Hara, and Kentaro Inui. Evaluation of similarity-based ex- planations. In International Conference on Learning Rep- resentations, 2021.","title":"Evaluation of similarity-based explanations","authors":"Kazuaki Hanawa, Sho Yokoi, Satoshi Hara, Kentaro Inui","year":"2021","venue":"International Conference on Learning Representations","doi":null,"url":null,"internal_url":null},{"position":9,"raw":"[Koh and Liang, 2017] Pang Wei Koh and Percy Liang. Un- derstanding black-box predictions via influence functions. In International Conference on Machine Learning, pages 1885-1894. PMLR, 2017.","title":"Understanding black-box predictions via influence functions","authors":"Pang Wei, Koh, Percy Liang","year":"2017","venue":"International Conference on Machine Learning","doi":null,"url":null,"internal_url":null},{"position":10,"raw":"[Lawrence et al., 2021] Carolin Lawrence, Timo Sztyler, and Mathias Niepert. Explaining neural matrix factoriza- tion with gradient rollback. In Thirty-Fifth AAAI Confer- ence on Artificial Intelligence, AAAI 2021, pages 4987- 4995. AAAI Press, 2021.","title":"Explaining neural matrix factorization with gradient rollback","authors":"Carolin Lawrence, Timo Sztyler, Mathias Niepert","year":"2021","venue":"Thirty-Fifth AAAI Conference on Artificial Intelligence, AAAI 2021","doi":null,"url":null,"internal_url":null},{"position":11,"raw":"[Mayer and Pirri, 1993] Marta Cialdea Mayer and Fiora Pirri. First order abduction via tableau and sequent cal- culi. Logic Journal of the IGPL, 1(1):99-117, 1993.","title":"First order abduction via tableau and sequent calculi","authors":"Pirri Mayer, Marta Cialdea Mayer, Fiora Pirri","year":"1993","venue":"Logic Journal of the IGPL","doi":null,"url":null,"internal_url":null},{"position":12,"raw":"[Meilicke et al., 2019] Christian Meilicke, Melisachew Wudage Chekol, Daniel Ruffinelli, and Heiner Stuckenschmidt. Anytime bottom-up rule learning for knowledge graph completion. In Proceedings of the 28th International Joint Conference on Artificial Intelligence (IJCAI). IJCAI/AAAI Press, 2019.","title":"Christian Meilicke, Melisachew Wudage Chekol, Daniel Ruffinelli, and Heiner Stuckenschmidt. Anytime bottom-up rule learning for knowledge graph completion","authors":"Meilicke","year":"2019","venue":"Proceedings of the 28th International Joint Conference on Artificial Intelligence (IJCAI)","doi":null,"url":null,"internal_url":null},{"position":13,"raw":"[Meilicke et al., 2021] Christian Meilicke, Patrick Betz, and Heiner Stuckenschmidt. Why a naive way to combine symbolic and latent knowledge base completion works surprisingly well. In 3rd Conference on Automated Knowl- edge Base Construction, 2021.","title":"Why a naive way to combine symbolic and latent knowledge base completion works surprisingly well","authors":"Meilicke","year":"2021","venue":"3rd Conference on Automated Knowledge Base Construction","doi":null,"url":null,"internal_url":null},{"position":14,"raw":"[Pezeshkpour et al., 2019] Pouya Pezeshkpour, Yifan Tian, and Sameer Singh. Investigating robustness and inter- pretability of link prediction via adversarial modifications. In Proceedings of the 2019 Conference of the North Amer- ican Chapter of the Association for Computational Lin- guistics, pages 3336-3347, Minneapolis, Minnesota, June 2019. Association for Computational Linguistics.","title":"Investigating robustness and interpretability of link prediction via adversarial modifications","authors":"Pouya Pezeshkpour, Yifan Tian, Sameer Singh","year":"2019","venue":"Proceedings of the 2019 Conference of the North American Chapter of the Association for Computational Linguistics","doi":null,"url":null,"internal_url":null},{"position":15,"raw":"[Rim et al., 2021] Wiem Ben Rim, Carolin Lawrence, Kiril Gashteovski, Mathias Niepert, and Naoaki Okazaki. Be- havioral testing of knowledge graph embedding models for link prediction. In 3rd Conference on Automated Knowledge Base Construction, 2021.","title":"Behavioral testing of knowledge graph embedding models for link prediction","authors":"Wiem Ben Rim, Carolin Lawrence, Kiril Gashteovski, Mathias Niepert, Naoaki Okazaki","year":"2021","venue":"3rd Conference on Automated Knowledge Base Construction","doi":null,"url":null,"internal_url":null},{"position":16,"raw":"[Rossi et al., 2021] Andrea Rossi, Denilson Barbosa, Do- natella Firmani, Antonio Matinata, and Paolo Merialdo. Knowledge graph embedding for link prediction: A com- parative analysis. ACM Transactions on Knowledge Dis- covery from Data (TKDD), 15(2):1-49, 2021.","title":"Knowledge graph embedding for link prediction: A comparative analysis","authors":"Andrea Rossi, Denilson Barbosa, Donatella Firmani, Antonio Matinata, Paolo Merialdo","year":"2021","venue":"ACM Transactions on Knowledge Discovery from Data (TKDD)","doi":null,"url":null,"internal_url":null},{"position":17,"raw":"[Ruffinelli et al., 2020] Daniel Ruffinelli, Samuel Broscheit, and Rainer Gemulla. You CAN teach an old dog new tricks! on training knowledge graph embeddings. In Inter- national Conference on Learning Representations, 2020.","title":"You CAN teach an old dog new tricks! on training knowledge graph embeddings","authors":"Daniel Ruffinelli, Samuel Broscheit, Rainer Gemulla","year":"2020","venue":"International Conference on Learning Representations","doi":null,"url":null,"internal_url":null},{"position":18,"raw":"[Trouillon et al., 2016] Théo Trouillon, Johannes Welbl, Se- bastian Riedel, Éric Gaussier, and Guillaume Bouchard. Complex embeddings for simple link prediction. In Maria- Florina Balcan and Kilian Q. Weinberger, editors, Pro- ceedings of the 33nd International Conference on Machine Learning, volume 48 of JMLR Workshop and Conference Proceedings, pages 2071-2080. JMLR.org, 2016.","title":"Complex embeddings for simple link prediction","authors":"Théo Trouillon, Johannes Welbl, Sebastian Riedel, Éric Gaussier, Guillaume Bouchard","year":"2016","venue":"Proceedings of the 33nd International Conference on Machine Learning","doi":null,"url":null,"internal_url":null},{"position":19,"raw":"[Yang et al., 2015] Bishan Yang, Wen-tau Yih, Xiaodong He, Jianfeng Gao, and Li Deng. Embedding entities and relations for learning and inference in knowledge bases. In Yoshua Bengio and Yann LeCun, editors, 3rd Interna- tional Conference on Learning Representations, 2015.","title":"Embedding entities and relations for learning and inference in knowledge bases","authors":"Bishan Yang, Wen-Tau Yih, Xiaodong He, Jianfeng Gao, Li Deng","year":"2015","venue":"3rd International Conference on Learning Representations","doi":null,"url":null,"internal_url":null},{"position":20,"raw":"[Zhang et al., 2019a] Hengtong Zhang, Tianhang Zheng, Jing Gao, Chenglin Miao, Lu Su, Yaliang Li, and Kui Ren. Data poisoning attack against knowledge graph em- bedding. In Proceedings of the Twenty-Eighth Interna- tional Joint Conference on Artificial Intelligence, IJCAI- 19, pages 4853-4859. International Joint Conferences on Artificial Intelligence Organization, 7 2019.","title":"Data poisoning attack against knowledge graph embedding","authors":"Zhang","year":"2019","venue":"Proceedings of the Twenty-Eighth International Joint Conference on Artificial Intelligence, IJCAI-19","doi":null,"url":null,"internal_url":"/proceedings/2019/674"},{"position":21,"raw":"[Zhang et al., 2019b] Wen Zhang, Bibek Paudel, Liang Wang, Jiaoyan Chen, Hai Zhu, Wei Zhang, Abraham Bernstein, and Huajun Chen. Iteratively learning embed- dings and rules for knowledge graph reasoning. In The World Wide Web Conference, pages 2366-2377, 2019.","title":"Iteratively learning embeddings and rules for knowledge graph reasoning","authors":"Zhang","year":"2019","venue":"The World Wide Web Conference","doi":null,"url":null,"internal_url":null}],"license_note":"Copyright International Joint Conferences on Artificial Intelligence."}