C.‐C. Jay Kuo

PixelHop++: A Small Successive-Subspace-Learning-Based (SSL-based) Model for Image Classification

2020 · arXiv (Cornell University)

The successive subspace learning (SSL) principle was developed and used to design an interpretable learning model, known as the PixelHop method,for image classification in our prior work. Here, we propose an improved PixelHop method and …

Adversarial Unsupervised Domain Adaptation with Conditional and Label Shift: Infer, Align and Iterate

2021 · 2021 IEEE/CVF International Conference on Computer Vision (ICCV)

In this work, we propose an adversarial unsupervised domain adaptation (UDA) method under inherent conditional and label shifts, in which we aim to align the distributions w.r.t. both p(x|y) and p(y). Since labels are inaccessible …

L-BGNN: Layerwise Trained Bipartite Graph Neural Networks

2022 · IEEE Transactions on Neural Networks and Learning Systems

Learning low-dimensional representations of bipartite graphs enables e-commerce applications, such as recommendation, classification, and link prediction. A layerwise-trained bipartite graph neural network (L-BGNN) embedding method, which is unsupervised, efficient, and scalable, is proposed in this …

Acceleration of Subspace Learning Machine via Particle Swarm Optimization and Parallel Processing

2022 · arXiv (Cornell University)

Built upon the decision tree (DT) classification and regression idea, the subspace learning machine (SLM) has been recently proposed to offer higher performance in general classification and regression tasks. Its performance improvement is reached at …

Just Rank: Rethinking Evaluation with Word and Sentence Similarities

2022 · arXiv (Cornell University)

Word and sentence embeddings are useful feature representations in natural language processing. However, intrinsic evaluation for embeddings lags far behind, and there has been no significant update since the past decade. Word and sentence similarity …

Knowledge Graph Embedding with 3D Compound Geometric Transformations

2023 · arXiv (Cornell University)

The cascade of 2D geometric transformations were exploited to model relations between entities in a knowledge graph (KG), leading to an effective KG embedding (KGE) model, CompoundE. Furthermore, the rotation in the 3D space was …