Publications

2026

1. ICMLW

   Discovering Mechanisms in Tokenized Graph Transformers

   Yong-Min Shin, Dae-Woong Jeong, and Sehui Han

   In ICML Workshop on Mechanistic Interpretability, Jul 2026

   HTML

   2026

2025

1. AAAI

   Faithful and Accurate Self-Attention Attribution for Message Passing Neural Networks via the Computation Tree Viewpoint

   Yong-Min Shin, Siqing Li, Xin Cao, and Won-Yong Shin

   In AAAI, Feb 2025

   HTML PDF

   2025

2024

1. IJCAIW

   On the Feasibility of Fidelity⁻ for Graph Pruning

   Yong-Min Shin, and Won-Yong Shin

   In IJCAI Workshop on Explainable Artificial Intelligence (XAI), Aug 2024

   HTML PDF

   2024
2. SIGIR

   Turbo-CF: Matrix Decomposition-Free Graph Filtering for Fast Recommendation

   Jin-Duk Park, Yong-Min Shin, and Won-Yong Shin

   In ACM SIGIR Conference on Research and Development in Information Retrieval, Apr 2024

   HTML PDF

   2024
3. PAMI

   PAGE: Prototype-Based Model-Level Explanations for Graph Neural Networks

   Yong-Min Shin, Sun-Woo Kim, and Won-Yong Shin

   Transactions on Pattern Analysis and Machine Intelligence, Apr 2024

   HTML PDF

   2024

2023

1. LoG

   Propagate & Distill: Towards Effective Graph Learners Using Propagation-Embracing MLPs

   Yong-Min Shin, and Won-Yong Shin

   In The Second Learning on Graphs Conference, Nov 2023

   HTML PDF

   2023

2022

1. AAAI

   Prototype-Based Explanations for Graph Neural Networks (Student Abstract) (selected for oral presentation)

   Yong-Min Shin, Sun-Woo Kim, Eun-Bi Yoon, and Won-Yong Shin

   In AAAI Conference on Artificial Intelligence, (AAAI), Feb 2022

   HTML PDF

   2022
2. arXiv

   Time-Series Anomaly Detection with Implicit Neural Representation

   Kyeong-Joong Jeong, and Yong-Min Shin

   arXiv preprint, Feb 2022

   HTML PDF

   2022
3. TETC

   Edgeless-GNN: Unsupervised Representation Learning for Edgeless Nodes

   Yong-Min Shin, Cong Tran, Won-Yong Shin, and Xin Cao

   IEEE Transactions on Emerging Topics in Computing, Jul 2022

   Abs HTML PDF

   We study the problem of embedding edgeless nodes such as users who newly enter the underlying network, while using graph neural networks (GNNs) widely studied for effective representation learning of graphs. Our study is motivated by the fact that GNNs cannot be straightforwardly adopted for our problem since message passing to such edgeless nodes having no connections is impossible. To tackle this challenge, we propose Edgeless-GNN, a novel inductive framework that enables GNNs to generate node embeddings even for edgeless nodes through unsupervised learning. Specifically, we start by constructing a proxy graph based on the similarity of node attributes as the GNN's computation graph defined by the underlying network. The known network structure is used to train model parameters, whereas a topology-aware loss function is established such that our model judiciously learns the network structure by encoding positive, negative, and second-order relations between nodes. For the edgeless nodes, we inductively infer embeddings by expanding the computation graph. By evaluating the performance of various downstream machine learning tasks, we empirically demonstrate that Edgeless-GNN exhibits (a) superiority over state-of-the-art inductive network embedding methods for edgeless nodes, (b) effectiveness of our topology-aware loss function, (c) robustness to incomplete node attributes, and (d) a linear scaling with the graph size.

   2022
4. PLOS ONE

   Explainable gait recognition with prototyping encoder–decoder

   Jucheol Moon, Yong-Min Shin, Jin-Duk Park, Nelson Hebert Minaya, Won-Yong Shin, and Sang-Il Choi

   PLOS ONE, Mar 2022

   Abs HTML PDF

   Human gait is a unique behavioral characteristic that can be used to recognize individuals. Collecting gait information widely by the means of wearable devices and recognizing people by the data has become a topic of research. While most prior studies collected gait information using inertial measurement units, we gather the data from 40 people using insoles, including pressure sensors, and precisely identify the gait phases from the long time series using the pressure data. In terms of recognizing people, there have been a few recent studies on neural network-based approaches for solving the open set gait recognition problem using wearable devices. Typically, these approaches determine decision boundaries in the latent space with a limited number of samples. Motivated by the fact that such methods are sensitive to the values of hyper-parameters, as our first contribution, we propose a new network model that is less sensitive to changes in the values using a new prototyping encoder–decoder network architecture. As our second contribution, to overcome the inherent limitations due to the lack of transparency and interpretability of neural networks, we propose a new module that enables us to analyze which part of the input is relevant to the overall recognition performance using explainable tools such as sensitivity analysis (SA) and layer-wise relevance propagation (LRP).

   2022