Zhijin Guo

Zhijin Guo

PhD student in university of Bristol

Publications

EXTRACT: Explainable Transparent Control of Bias in Embeddings

Published in AEQUITAS 2023: AEQUITAS 2023 First AEQUITAS Workshop on Fairness and Bias in AI | co-located with ECAI 2023, 2023

Knowledge Graphs are a widely used method to represent relations between entities in various AI applications, and Graph Embedding has rapidly become a standard technique to represent Knowledge Graphs in such a way as to facilitate inferences and decisions. As this representation is obtained from behavioural data, and is not in a form readable by humans, there is a concern that it might incorporate unintended information that could lead to biases. We propose EXTRACT: a suite of Explainable and Transparent methods to ConTrol bias in knowledge graph embeddings, so as to assess and decrease the implicit presence of protected information. Our method uses Canonical Correlation Analysis (CCA) to investigate the presence, extent and origins of information leaks during training, then decomposes embeddings into a sum of their private attributes by solving a linear system. Our experiments, performed on the MovieLens-1M dataset, show that a range of personal attributes can be inferred from a user’s viewing behaviour and preferences, including gender, age and occupation. Further experiments, per- formed on the KG20C citation dataset, show that the information about the conference in which a paper was published can be inferred from the citation network of that article. We propose four transparent methods to maintain the capability of the embedding to make the intended predictions without retaining unwanted information. A trade-off between these two goals is observed.

Recommended citation: Your Name, You. (2010). "Paper Title Number 2." Journal 1. 1(2). http://academicpages.github.io/files/paper2.pdf

On Compositionality in Data Embedding

Published in Journal 1, 2023

Representing data items as vectors in a space is a common practice in machine learning, where it often goes under the name of “data embedding”. This representation is typically learnt from known relations that exist in the original data, such as co-occurrence of words, or connections in graphs. A property of these embeddings is known as compositionality, whereby the vector representation of an item can be decomposed into different parts, which can be understood separately. This property, first observed in the case of word embeddings, could help with various challenges of modern AI: detection of unwanted bias in the representation, explainability of AI decisions based on these representations, and the possibility of performing analogical reasoning or counterfactual question answering. One important direction of research is to understand the origins, properties and limitations of compositional data embeddings, with the idea of going beyond word embeddings. In this paper, we propose two methods to test for this property, demonstrating their use in the case of sentence embedding and knowledge graph embedding.

Recommended citation: Your Name, You. (2009). "Paper Title Number 1." Journal 1. 1(1). https://link.springer.com/chapter/10.1007/978-3-031-30047-9_38