Changjun Fan

Changjun Fan

Auto-generated profile, based on publicly available information

Changjun Fan

Laboratory for Big Data and Decision, College of Systems Engineering, National University of Defense Technology, Changsha, Hunan, China

Research Focus & Metrics

Academic Career Length

8Years (2019-Present)

(Calculated once Scilit publication data is synced: current year − year of first publication + 1)

Representative Publications

View All Publications
30 December 2024 in IEEE Transactions on Knowledge and Data Engineering
Verified
Journal Article
Closed access
BZBingxu Zhang
Bingxu Zhang
CFChangjun Fan
Changjun Fan
SLShixuan Liu
Shixuan Liu
KHKuihua Huang
Kuihua Huang
XZXiang Zhao
Xiang Zhao
ZLZhong Liu
Zhong Liu
Graph neural networks (GNNs) are effective machine learning models for many graph-related applications. Despite their empirical success, many research efforts focus on the theoretical limitations of GNNs, i.e., the GNNs expressive power. Early works in this domain mainly focus on studying the graph isomorphism recognition ability of GNNs, and recent works try to leverage the properties such as subgraph counting and connectivity learning to characterize the expressive power of GNNs, which are more practical and closer to real-world. However, no survey papers and open-source repositories comprehensively summarize and discuss models in this important direction. To fill the gap, we conduct a first survey for models for enhancing expressive power under different forms of definition. Concretely, the models are reviewed based on three categories, i.e., Graph feature enhancement, Graph topology enhancement, and GNNs architecture enhancement.

1 January 2024 in Mathematical Biosciences and Engineering
Verified
Journal Article
Open access
PDF file
JTJia Mian Tan
Jia Mian Tan
HLHaoran Liao
Haoran Liao
WLWei Liu
Wei Liu
CFChangjun Fan
Changjun Fan
JHJincai Huang
Jincai Huang
Junchi YanJunchi Yan
Junchi Yan
Hyperparameter optimization (HPO) has been well-developed and evolved into a well-established research topic over the decades. With the success and wide application of deep learning, HPO has garnered increased attention, particularly within the realm of machine learning model training and inference. The primary objective is to mitigate the challenges associated with manual hyperparameter tuning, which can be ad-hoc, reliant on human expertise, and consequently hinders reproducibility while inflating deployment costs. Recognizing the growing significance of HPO, this paper surveyed classical HPO methods, approaches for accelerating the optimization process, HPO in an online setting (dynamic algorithm configuration, DAC), and when there is more than one objective to optimize (multi-objective HPO). Acceleration strategies were categorized into multi-fidelity, bandit-based, and early stopping; DAC algorithms encompassed gradient-based, population-based, and reinforcement learning-based methods; multi-objective HPO can be approached via scalarization, metaheuristics, and model-based algorithms tailored for multi-objective situation. A tabulated overview of popular frameworks and tools for HPO was provided, catering to the interests of practitioners.

29 July 2024 in IEEE Transactions on Pattern Analysis and Machine Intelligence
Verified
Journal Article
Closed access
SLShixuan Liu
Shixuan Liu
CFChangjun Fan
Changjun Fan
KCKewei Cheng
Kewei Cheng
YWYunfei Wang
Yunfei Wang
Peng CuiPeng Cui
Peng Cui
ZLZhong Liu
Zhong Liu
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 types connecting two entities, is proposed to provide the meta-level explainable semantics for various HIN tasks. Traditionally, meta-paths are primarily used for schema-simple HINs, e.g., bibliographic networks with only a few entity types, where meta-paths are often enumerated with domain knowledge. However, the adoption of meta-paths for schema-complex HINs, such as knowledge bases (KBs) with hundreds of entity and relation types, has been limited due to the computational complexity associated with meta-path enumeration. Additionally, effectively assessing meta-paths requires enumerating relevant path instances, which adds further complexity to the meta-path learning process. To address these challenges, we propose SchemaWalk, an inductive meta-path learning framework for schema-complex HINs. We represent meta-paths with schema-level representations to support the learning of the scores of meta-paths for varying relations, mitigating the need of exhaustive path instance enumeration for each relation. Further, we design a reinforcement-learning based path-finding agent, which directly navigates the network schema (i.e., schema graph) to learn policies for establishing meta-paths with high coverage and confidence for multiple relations. Extensive experiments on real data sets demonstrate the effectiveness of our proposed paradigm.

30 December 2022 in The Computer Journal
Verified
Journal Article
Closed access
PDF file
CLChangan Liu
Changan Liu
CFChangjun Fan
Changjun Fan
ZZZhongzhi Zhang
Zhongzhi Zhang
Maximizing influences in complex networks is a practically important but computationally challenging task for social network analysis, due to its nondeterministic polynomial time (NP)-hard nature. Most current approximation or heuristic methods either require tremendous human design efforts or achieve unsatisfying balances between effectiveness and efficiency. Recent machine learning attempts only focus on speed but lack performance enhancement. In this paper, different from previous attempts, we propose an effective deep reinforcement learning model that achieves superior performances over traditional best influence maximization algorithms. Specifically, we design an end-to-end learning framework that combines graph neural network as the encoder and reinforcement learning as the decoder, named DREIM. Through extensive training on small synthetic graphs, DREIM outperforms the state-of-the-art baseline methods on very large synthetic and real-world networks on solution quality, and we also empirically show its linear scalability with regard to the network size, which demonstrates its superiority in solving this problem.

11 June 2025 in Knowledge-Based Systems
Verified
Journal Article
Closed access
ZHZhijing Hu
Zhijing Hu
HYHao Yan
Hao Yan
KHKuihua Huang
Kuihua Huang
JHJincai Huang
Jincai Huang
ZLZhong Liu
Zhong Liu
CFChangjun Fan
Changjun Fan

28 January 2026 in IEEE Transactions on Cognitive Communications and Networking
Verified
Journal Article
Closed access
ZYZhong Yang
Zhong Yang
ZZZhengqiu Zhu
Zhengqiu Zhu
YZYong Zhao
Yong Zhao
YTYonglin Tian
Yonglin Tian
CFChangjun Fan
Changjun Fan
Imre RudasImre Rudas
Imre Rudas
Underwater acoustic networks are evolving from static, manually-configured systems into cognitive, learning-enabled platforms that can perceive, reason, and adapt to harsh ocean dynamics in real-time. Accurate target tracking is a core service of these networks and underpins marine resource exploration, environmental monitoring, and maritime security. Existing reviews or surveys, however, rarely examine underwater acoustic target tracking through the lens of cognitive communications and networking, and often offer a narrow perspective on addressing the paradigm shifts driven by emerging technologies like deep learning. To fill this gap, this work presents a systematic survey of this field and introduces an innovative three-dimensional taxonomy framework based on the three levels of the cognitive underwater acoustic target tracking network: the target layer, the perception layer, and the processing layer.Within this framework, we comprehensively survey the literature over the period 2016-2025, spanning from the theoretical foundations to diverse algorithmic approaches in underwater acoustic target tracking. Particularly, we emphasize the transformative potential and recent advancements of machine learning techniques, including deep learning and reinforcement learning, in enhancing the performance and adaptability of cognitive underwater tracking systems. Finally, this survey concludes by identifying key challenges in the field and proposing future avenues based on emerging technologies such as data desensitization, embodied intelligence, and large models.