About

C.-C. Jay Kuo is associated with the USC + Amazon Center on Secure & Trusted Machine Learning, which focuses on developing new approaches to machine learning (ML) with an emphasis on privacy, security, and trustworthiness. The center aims to unleash a new line of fundamental research on these critical aspects of AI, given its proliferation across society. While the specific details of Professor Kuo's personal research background are not provided on the page, his association with this center indicates his involvement in advancing methodologies for secure and privacy-preserving machine learning solutions.

Research topics

• Computer Science
• Artificial Intelligence
• Theoretical computer science
• Information Retrieval
• Machine Learning
• Mathematics
• Biology

Selected publications

• Knowledge Graph Embedding: An Overview

  APSIPA Transactions on Signal and Information Processing · 2024 · 40 citations

  Senior authorCorresponding
  • Computer Science
  • Computer Science
  • Information Retrieval

  Many mathematical models have been leveraged to design em-beddings for representing Knowledge Graph (KG) entities and relations for link prediction and many downstream tasks. These mathematically-inspired models are not only highly scalable for inference in large KGs, but also have many explainable advantages in modeling different relation patterns that can be validated through both formal proofs and empirical results. In this paper, we make a comprehensive overview of the current state of research in KG completion. In particular, we focus on two main branches of KG embedding (KGE) design: 1) distance-based methods and 2) semantic matching-based methods. We discover the connections between recently proposed models and present an underlying trend that might help researchers invent novel and more effective models. Next, we delve into CompoundE and CompoundE3D, which draw inspiration from 2D and 3D affine operations, respectively. They encompass a broad spectrum of distance-based embedding techniques. We will also discuss an emerging approach for KG completion which leverages pre-trained language models (PLMs) and textual descriptions of entities and relations and offer insights into the integration of KGE embedding methods with PLMs for KG completion.

  DOI

• Compounding Geometric Operations for Knowledge Graph Completion

  2023 · 25 citations

  Senior authorCorresponding
  • Computer Science
  • Computer Science
  • Artificial Intelligence

  Geometric transformations including translation, rotation, and scaling are commonly used operations in image processing. Besides, some of them are successfully used in developing effective knowledge graph embedding (KGE). Inspired by the synergy, we propose a new KGE model by leveraging all three operations in this work. Since translation, rotation, and scaling operations are cascaded to form a composite one, the new model is named CompoundE. By casting CompoundE in the framework of group theory, we show that quite a few distanced-based KGE models are special cases of CompoundE. CompoundE extends the simple distance-based scoring functions to relation-dependent compound operations on head and/or tail entities. To demonstrate the effectiveness of CompoundE, we perform three prevalent KG prediction tasks including link prediction, path query answering, and entity typing, on a range of datasets. CompoundE outperforms extant models consistently, demonstrating its effectiveness and flexibility.

  DOI

• TypeEA: Type-Associated Embedding for Knowledge Graph Entity Alignment

  APSIPA Transactions on Signal and Information Processing · 2023 · 7 citations

  Senior authorCorresponding
  • Computer Science
  • Computer Science
  • Artificial Intelligence

  Entity alignment is commonly used to link different knowledge graphs and augment facts about entities. The main objective is to identify the counterpart of a source entity in the target knowledge graph. Although the auxiliary information such as textual, visual, and temporal features was leveraged to improve the entity alignment performance in the past, the entity type information is rarely considered in existing entity alignment models. In this paper, we demonstrate that the entity type information, which is commonly available in knowledge graphs, is very helpful to knowledge graph alignment and propose a new method called the Type-associated Entity Alignment (TypeEA) accordingly. TypeEA exploits the entity type information to guide entity alignment models so that they can focus on entities with matching types. A type embedding model based on semantic matching is developed in TypeEA to capture the association between types in different knowledge graphs. Experimental results show that the proposed TypeEA consistently outperforms state-of-the-art baselines across all OpenEA entity alignment datasets with different experimental settings.

  DOI

• Green learning: Introduction, examples and outlook

  Journal of Visual Communication and Image Representation · 2022 · 89 citations

  • Computer Science
  • Artificial Intelligence
  • Computer Science

  Rapid advances in artificial intelligence (AI) in the last decade have been largely built upon the wide applications of deep learning (DL). However, the high carbon footprint yielded by larger and larger DL networks has become a concern for sustainability. Furthermore, DL decision mechanism is somewhat obscure in that it can only be verified by test data. Green learning (GL) is being proposed as an alternative paradigm to address these concerns. GL is characterized by low carbon footprints, lightweight model, low computational complexity, and logical transparency. It offers energy-efficient solutions in cloud centers as well as mobile/edge devices. GL also provides a more transparent, logical decision-making process which is essential to gaining people’s trust. Several statistical tools such as unsupervised representation learning, supervised feature learning, and supervised decision learning, have been developed to achieve this goal in recent years. We have seen a few successful GL examples with performance comparable with state-of-the-art DL solutions. This paper introduces the key characteristics of GL, its demonstrated applications, and future outlook.

  DOI

• Saak Transform-Based Machine Learning for Light-Sheet Imaging of Cardiac Trabeculation

  IEEE Transactions on Biomedical Engineering · 2020 · 27 citations

  • Artificial Intelligence
  • Computer Science
  • Artificial Intelligence

  OBJECTIVE: Recent advances in light-sheet fluorescence microscopy (LSFM) enable 3-dimensional (3-D) imaging of cardiac architecture and mechanics in toto. However, segmentation of the cardiac trabecular network to quantify cardiac injury remains a challenge. METHODS: We hereby employed "subspace approximation with augmented kernels (Saak) transform" for accurate and efficient quantification of the light-sheet image stacks following chemotherapy-treatment. We established a machine learning framework with augmented kernels based on the Karhunen-Loeve Transform (KLT) to preserve linearity and reversibility of rectification. RESULTS: The Saak transform-based machine learning enhances computational efficiency and obviates iterative optimization of cost function needed for neural networks, minimizing the number of training datasets for segmentation in our scenario. The integration of forward and inverse Saak transforms can also serve as a light-weight module to filter adversarial perturbations and reconstruct estimated images, salvaging robustness of existing classification methods. The accuracy and robustness of the Saak transform are evident following the tests of dice similarity coefficients and various adversary perturbation algorithms, respectively. The addition of edge detection further allows for quantifying the surface area to volume ratio (SVR) of the myocardium in response to chemotherapy-induced cardiac remodeling. CONCLUSION: The combination of Saak transform, random forest, and edge detection augments segmentation efficiency by 20-fold as compared to manual processing. SIGNIFICANCE: This new methodology establishes a robust framework for post light-sheet imaging processing, and creating a data-driven machine learning for automated quantification of cardiac ultra-structure.

  DOI

Frequent coauthors

• Bin Wang

  4 shared

• Xiou Ge

  University of Southern California

  4 shared

• Yun Cheng Wang

  University of Southern California

  4 shared

• Bin Wang

  2 shared

Labs

• USC + Amazon Center on Secure & Trusted MLPI

Awards & honors

• AAAS Fellow
• IEEE Fellow
• SPIE Fellow
• SPIE and IS&T Electronic Imaging Scientist of the Year Award…
• Fulbright-Nokia Distinguished Chair in Information and Commu…

Similar researchers at University of Southern California

• Norbert Schwarzh-140
• Inderbir S. Gillh-136
• Andreas Molischh-132
• David G. Armstrongh-124
• Antoine Becharah-116