9 papers
ISO-RAG: Isoperimetric Noise Control for Retrieval-Augmented Generation
Siyuan Zhang, Hanchen Wang, Dong Wen +2
Retrieval-Augmented Generation (RAG) mitigates large language models (LLMs) hallucinations, yet conventional dense retrieval struggles with the complex reasoning paths of multi-hop…
GCCM: Enhancing Generative Graph Prediction via Contrastive Consistency Model
Shaozhen Ma, Wei Huang, Hanchen Wang +2
Conditional generative models, particularly diffusion-based methods, have recently been applied to graph prediction by modeling the target as a conditional distribution given the i…
RLMiner: Finding the Most Frequent k-sized Subgraph via Reinforcement Learning
Wei Huang, Hanchen Wang, Dong Wen +4
Identifying the most frequent induced subgraph of size in a target graph is a fundamental graph mining problem with direct implications for Web-related data mining and social n…
Small Shifts, Large Gains: Unlocking Traditional TSP Heuristic Guided-Sampling via Unsupervised Neural Instance Modification
Wei Huang, Hanchen Wang, Dong Wen +1
The Traveling Salesman Problem (TSP) is one of the most representative NP-hard problems in route planning and a long-standing benchmark in combinatorial optimization. Traditional h…
Accelerating Historical K-Core Search in Temporal Graphs
Zhuo Ma, Dong Wen, Kaiyu Chen +3
We study the temporal k-core component search (TCCS), which outputs the k-core containing the query vertex in the snapshot over an arbitrary query time window in a temporal graph.…
Accelerating K-Core Computation in Temporal Graphs
Zhuo Ma, Dong Wen, Hanchen Wang +3
We address the problem of enumerating all temporal k-cores given a query time range and a temporal graph, which suffers from poor efficiency and scalability in the state-of-the-art…
WOCD: A Semi-Supervised Method for Overlapping Community Detection Using Weak Cliques
Shaozhen Ma, Hanchen Wang, Dong Wen +3
Overlapping community detection (OCD) is a fundamental graph data analysis task for extracting graph patterns. Traditional OCD methods can be broadly divided into node clustering a…
Towards Unsupervised Training of Matching-based Graph Edit Distance Solver via Preference-aware GAN
Wei Huang, Hanchen Wang, Dong Wen +3
Graph Edit Distance (GED) is a fundamental graph similarity metric widely used in various applications. However, computing GED is an NP-hard problem. Recent state-of-the-art hybrid…
DiffGED: Computing Graph Edit Distance via Diffusion-based Graph Matching
Wei Huang, Hanchen Wang, Dong Wen +3
The Graph Edit Distance (GED) problem, which aims to compute the minimum number of edit operations required to transform one graph into another, is a fundamental challenge in graph…