Congratulations to Joe Wang for passing his defense. Joe’s thesis is titled “Green Knowledge Graph Completion and Scalable Generative Content Delivery.” His Dissertation Committee includes Jay Kuo (Chair), Antonio Ortega, and Robin Jia (Outside Member). MCL News team invited Joe for a short talk on her thesis and PhD experience, and here is the summary. We thank Joe for his kind sharing, and wish her all the best in the next journey.

Knowledge graphs (KGs) and Generative AI (GenAI) models have powerful reasoning capabilities and are crucial for building advanced artificial intelligence (AI) systems. In my thesis, we focus on four fundamental research to improve the efficiency, scalability, and explainability of the existing methods. They are:
1. Improving KG Embeddings with Entity Types: Entity types describe the high-level taxonomy and categorization of entities in KGs. They are often ignored in KG embedding learning. Thus, we propose a new methodology to incorporate entity types to improve KG embeddings. Specifically, our method can represent entities and types in the same embedding space with a constant number of additional model parameters. In addition, our method has a huge advantage in computation efficiency during inference.
2. KG Completion with Classifiers: KG embeddings have limited expressiveness in modeling relations. Thus, we study using binary classifiers to represent relations in the KG completion task. There are several advantages to modeling missing links as a binary classification problem, including having access to more powerful classifiers and data augmentation.
3. Green KG Completion: KG completion methods often require higher embedding dimensions for good performance. Thus, we investigate applying feature transformation and univariate feature selection to reduce the feature dimensions in KG completion methods. The KGs are first partitioned into several groups to extract discriminant features. As a result, we can preserve 96.88% of inference memory while retaining 85.7% of performance.
4. Scalable Generative Content Delivery: GenAI models rely on deep neural networks to generate new content. Bottlenecks in the advanced models and current computing framework limit the scalability of generative content delivery. We identify the main challenges in existing systems and propose a solution to deploy GenAI models under a collaborative computing framework.

I would like to extend my sincere gratitude to Prof. C.-C. Jay Kuo for his full support and guidance throughout my PhD journey. We started the project on knowledge graphs in the summer of 2020, when I knew very little about the topic. We started by studying a survey paper together, and we finally had our first major breakthrough in the summer of 2022. It is extremely normal to have a certain frustration during this process, and it is important to stay motivated and be persistent when facing challenges. Every failure will finally be a stepping stone to your success.
MCL is also an important part of my PhD. I am grateful to every MCL member and alumni for always being willing to offer help, advice, and company. I also enjoyed the time to discuss research with other MCL members. MCL members work on a wide range of research topics. I find it beneficial to learn about others’ research and to explain your research to other lab members who are in a different research area. This actually strengthens my communication skills and interdisciplinary thinking.
To conclude, PhD is not an easy journey, but it is definitely rewarding. When I look back, I am amazed by my growth in knowledge, personality, and maturity in the past four years. I am thankful to Prof. Kuo, MCL members, and alumni. I wish everyone full success!