56 citations · 71 across the 20 of their papers we have counts for
23 papers
Do Higher-Order Models Win for Higher-Order Reasons? Rethinking Performance Gains in Hypergraph Learning
Fanchen Bu, Fan Li, Geon Lee +4
Higher-order models (e.g., hypergraph neural networks) often outperform lower-order baselines on hypergraph learning benchmarks, and their advantages are commonly attributed to the…
Message Passing Does More with Less for In-Context Learning on Graphs
Dooho Lee, Jinmo Lee, Minho Jeong +2
Achieving strong performance with graph neural networks (GNNs) typically requires training and hyperparameter tuning for each dataset, incurring repeated costs and effort. Graph in…
SLeDGe: Semi-Supervised Learning on Data Streams with Graph Structure Learning
Heechan Moon, Kijung Shin
Semi-supervised learning (SSL) on data streams is challenging due to the continuous evolution of high-volume data and the scarcity of labels. Existing methods are limited in levera…
On the Memorization Behavior of LLMs in Generative Recommendation: Observations, Implications, and Training Strategies
Sunwoo Kim, Sunkyung Lee, Clark Mingxuan Ju +5
Generative recommendation (GR) has emerged as a promising direction for recommender systems. Recently, large language models (LLMs) have been increasingly adopted for GR, as their…
TaLK: Text-attributed Graph Dataset Distillation via Coupling Language Model with Graph-Aware Kernel
Yeongho Kim, Yeonje Choi, Kijung Shin
Text-attributed graphs (TAGs) are widely used in many real-world domains, and learning on TAGs requires jointly modeling text semantics and graph structure. A standard approach for…
A Survey on Centrality and Importance Measures in Hypergraphs: Categorization and Empirical Insights
Jaewan Chun, Fanchen Bu, Yeongho Kim +3
Identifying central entities and interactions is a fundamental problem in network science. While well-studied for graphs (pairwise relations), many biological and social systems ex…
PyTorch-based Geometric Learning with Non-CUDA Processing Units: Experiences from Intel Gaudi-v2 HPUs
Fanchen Bu, Kijung Shin
Geometric learning has emerged as a powerful paradigm for modeling non-Euclidean data, especially graph-structured ones, with applications spanning social networks, molecular struc…
On Training-Test (Mis)alignment in Unsupervised Combinatorial Optimization: Observation, Empirical Exploration, and Analysis
Fanchen Bu, Kijung Shin
In unsupervised combinatorial optimization (UCO), during training, one aims to have continuous decisions that are promising in a probabilistic sense for each training instance, whi…
Mitigating Over-Squashing in Graph Neural Networks by Spectrum-Preserving Sparsification
Langzhang Liang, Fanchen Bu, Zixing Song +3
The message-passing paradigm of Graph Neural Networks often struggles with exchanging information across distant nodes typically due to structural bottlenecks in certain graph regi…
'Hello, World!': Making GNNs Talk with LLMs
Sunwoo Kim, Soo Yong Lee, Jaemin Yoo +1
While graph neural networks (GNNs) have shown remarkable performance across diverse graph-related tasks, their high-dimensional hidden representations render them black boxes. In t…
Rethinking Reconstruction-based Graph-Level Anomaly Detection: Limitations and a Simple Remedy
Sunwoo Kim, Soo Yong Lee, Fanchen Bu +4
Graph autoencoders (Graph-AEs) learn representations of given graphs by aiming to accurately reconstruct them. A notable application of Graph-AEs is graph-level anomaly detection (…
Sign is Not a Remedy: Multiset-to-Multiset Message Passing for Learning on Heterophilic Graphs
Langzhang Liang, Sunwoo Kim, Kijung Shin +3
Graph Neural Networks (GNNs) have gained significant attention as a powerful modeling and inference method, especially for homophilic graph-structured data. To empower GNNs in hete…
Tackling Prevalent Conditions in Unsupervised Combinatorial Optimization: Cardinality, Minimum, Covering, and More
Fanchen Bu, Hyeonsoo Jo, Soo Yong Lee +2
Combinatorial optimization (CO) is naturally discrete, making machine learning based on differentiable optimization inapplicable. Karalias & Loukas (2020) adapted the probabilistic…
Edge Probability Graph Models Beyond Edge Independency: Concepts, Analyses, and Algorithms
Fanchen Bu, Ruochen Yang, Paul Bogdan +1
Desirable random graph models (RGMs) should (i) reproduce common patterns in real-world graphs (e.g., power-law degrees, small diameters, and high clustering), (ii) generate variab…
A Survey on Hypergraph Neural Networks: An In-Depth and Step-By-Step Guide
Sunwoo Kim, Soo Yong Lee, Yue Gao +3
Higher-order interactions (HOIs) are ubiquitous in real-world complex systems and applications. Investigation of deep learning for HOIs, thus, has become a valuable agenda for the…
HypeBoy: Generative Self-Supervised Representation Learning on Hypergraphs
Sunwoo Kim, Shinhwan Kang, Fanchen Bu +3
Hypergraphs are marked by complex topology, expressing higher-order interactions among multiple nodes with hyperedges, and better capturing the topology is essential for effective…
FlowerFormer: Empowering Neural Architecture Encoding using a Flow-aware Graph Transformer
Dongyeong Hwang, Hyunju Kim, Sunwoo Kim +1
The success of a specific neural network architecture is closely tied to the dataset and task it tackles; there is no one-size-fits-all solution. Thus, considerable efforts have be…
SLADE: Detecting Dynamic Anomalies in Edge Streams without Labels via Self-Supervised Learning
Jongha Lee, Sunwoo Kim, Kijung Shin
To detect anomalies in real-world graphs, such as social, email, and financial networks, various approaches have been developed. While they typically assume static input graphs, mo…
Feature Distribution on Graph Topology Mediates the Effect of Graph Convolution: Homophily Perspective
Soo Yong Lee, Sunwoo Kim, Fanchen Bu +3
How would randomly shuffling feature vectors among nodes from the same class affect graph neural networks (GNNs)? The feature shuffle, intuitively, perturbs the dependence between…
A Survey on Hypergraph Mining: Patterns, Tools, and Generators
Geon Lee, Fanchen Bu, Tina Eliassi-Rad +1
Hypergraphs, which belong to the family of higher-order networks, are a natural and powerful choice for modeling group interactions in the real world. For example, when modeling co…
Four-set Hypergraphlets for Characterization of Directed Hypergraphs
Heechan Moon, Hyunju Kim, Sunwoo Kim +1
A directed hypergraph, which consists of nodes and hyperarcs, is a higher-order data structure that naturally models directional group interactions (e.g., chemical reactions of mol…
Hypergraph Motifs and Their Extensions Beyond Binary
Geon Lee, Seokbum Yoon, Jihoon Ko +2
Hypergraphs naturally represent group interactions, which are omnipresent in many domains: collaborations of researchers, co-purchases of items, and joint interactions of proteins,…
TensorCodec: Compact Lossy Compression of Tensors without Strong Data Assumptions
Taehyung Kwon, Jihoon Ko, Jinhong Jung +1
Many real-world datasets are represented as tensors, i.e., multi-dimensional arrays of numerical values. Storing them without compression often requires substantial space, which gr…