Publications (21)
AutoSND: From Execution Evidence to Structural Policies for Automated Network Dismantling Heuristic Discovery
Zhijing Hu, Changjun Fan, Yufan Deng +1
Network dismantling is fundamental to analyzing the robustness and vulnerability of complex systems, yet practical heuristics must balance effectiveness and computational efficienc…
A Comprehensive Survey on Underwater Acoustic Target Positioning and Tracking: Progress, Challenges, and Perspectives
Zhong Yang, Zhengqiu Zhu, Yong Zhao +16
Underwater target tracking technology plays a pivotal role in marine resource exploration, environmental monitoring, and national defense security. Given that acoustic waves repres…
Learning to Identify High Betweenness Centrality Nodes from Scratch: A Novel Graph Neural Network Approach
Changjun Fan, Li Zeng, Yuhui Ding +3
Betweenness centrality (BC) is one of the most used centrality measures for network analysis, which seeks to describe the importance of nodes in a network in terms of the fraction…
Reply to: Deep reinforced learning heuristic tested on spin-glass ground states: The larger picture
Changjun Fan, Mutian Shen, Zohar Nussinov +3
We wish to thank Stefan Boettcher for prompting us to further check and highlight the accuracy and scaling of our results. Here we provide a comprehensive response to the Comment w…
Transform then Explore: a Simple and Effective Technique for Exploratory Combinatorial Optimization with Reinforcement Learning
Tianle Pu, Changjun Fan, Mutian Shen +5
Many complex problems encountered in both production and daily life can be conceptualized as combinatorial optimization problems (COPs) over graphs. Recent years, reinforcement lea…
Finding spin glass ground states through deep reinforcement learning
Changjun Fan, Mutian Shen, Zohar Nussinov +3
Spin glasses are disordered magnets with random interactions that are, generally, in conflict with each other. Finding the ground states of spin glasses is not only essential for t…
The Expressive Power of Graph Neural Networks: A Survey
Bingxu Zhang, Changjun Fan, Shixuan Liu +4
Graph neural networks (GNNs) are effective machine learning models for many graph-related applications. Despite their empirical success, many research efforts focus on the theoreti…
On Disjoint Golomb Rulers
Xiu Baoxin, Changjun Fan, Meilian Liang
A set of non-negative integers is a Golomb ruler if differences , for any , are all distinct. A set of disjoint Golomb rulers (…
Optimizing p-spin models through hypergraph neural networks and deep reinforcement learning
Li Zeng, Mutian Shen, Tianle Pu +5
p-spin glasses, characterized by frustrated many-body interactions beyond the conventional pairwise case (p>2), are prototypical disordered systems whose ground-state search is NP-…
Machine Learning for the Multi-Dimensional Bin Packing Problem: Literature Review and Empirical Evaluation
Wenjie Wu, Changjun Fan, Jincai Huang +2
The Bin Packing Problem (BPP) is a well-established combinatorial optimization (CO) problem. Since it has many applications in our daily life, e.g. logistics and resource allocatio…
RoME: Domain-Robust Mixture-of-Experts for MILP Solution Prediction across Domains
Tianle Pu, Zijie Geng, Haoyang Liu +5
Mixed-Integer Linear Programming (MILP) is a fundamental and powerful framework for modeling complex optimization problems across diverse domains. Recently, learning-based methods…
Multilingual Knowledge Graph Completion via Ensemble Knowledge Transfer
Xuelu Chen, Muhao Chen, Changjun Fan +3
Predicting missing facts in a knowledge graph (KG) is a crucial task in knowledge base construction and reasoning, and it has been the subject of much research in recent works usin…
Generating Graph-Like Logical Rules for Knowledge Graph Reasoning via Diffusion Models
Haoxiang Cheng, Yunfei Wang, Chao Chen +5
Logical rules constitute a cornerstone of knowledge graph (KG) reasoning, valued for their interpretability and ability to model relational patterns. However, existing rule mining…
EvoPath: Evolutionary Meta-path Discovery with Large Language Models for Complex Heterogeneous Information Networks
Shixuan Liu, Haoxiang Cheng, Yunfei Wang +3
Heterogeneous Information Networks (HINs) encapsulate diverse entity and relation types, with meta-paths providing essential meta-level semantics for knowledge reasoning, although…
CoCo-MILP: Inter-Variable Contrastive and Intra-Constraint Competitive MILP Solution Prediction
Tianle Pu, Jianing Li, Yingying Gao +5
Mixed-Integer Linear Programming (MILP) is a cornerstone of combinatorial optimization, yet solving large-scale instances remains a significant computational challenge. Recently, G…
Learning from History: Modeling Temporal Knowledge Graphs with Sequential Copy-Generation Networks
Cunchao Zhu, Muhao Chen, Changjun Fan +2
Large knowledge graphs often grow to store temporal facts that model the dynamic relations or interactions of entities along the timeline. Since such temporal knowledge graphs ofte…
Pre-Training Graph Neural Networks for Generic Structural Feature Extraction
Ziniu Hu, Changjun Fan, Ting Chen +2
Graph neural networks (GNNs) are shown to be successful in modeling applications with graph structures. However, training an accurate GNN model requires a large collection of label…
Inductive Meta-path Learning for Schema-complex Heterogeneous Information Networks
Shixuan Liu, Changjun Fan, Kewei Cheng +4
Heterogeneous Information Networks (HINs) are information networks with multiple types of nodes and edges. The concept of meta-path, i.e., a sequence of entity types and relation t…
NED-Tree: Bridging the Semantic Gap with Nonlinear Element Decomposition Tree for LLM Nonlinear Optimization Modeling
Zhijing Hu, Yufan Deng, Haoyang Liu +1
Automating the translation of Operations Research (OR) problems from natural language to executable models is a critical challenge. While Large Language Models (LLMs) have shown pr…
Finding Influencers in Complex Networks: An Effective Deep Reinforcement Learning Approach
Changan Liu, Changjun Fan, Zhongzhi Zhang
Maximizing influences in complex networks is a practically important but computationally challenging task for social network analysis, due to its NP- hard nature. Most current appr…
Some constructive results on Disjoint Golomb Rulers
Xiaodong Xu, Baoxin Xiu, Changjun Fan +1
A set of non-negative integers is a Golomb ruler if differences , for any , are all distinct.All finite Sidon sets are Golomb ruler…