Minhua Lin
Current Organizations / Institutes
The organizations/institutes from the scholar's latest article
Research Subjects
Research Interests
Minhua Lin has a total of 36 co-authors. Here are the top co-authors by number of shared publications:
- Suhang Wang
The Pennsylvania State University, State College, USA
8 shared publications - Enyan Dai
Hong Kong University of Science and Technology (Guangzhou)
7 shared publications - Xiang Zhang
The Pennsylvania State University, USA
4 shared publications - Bin Ma
The Hong Kong University of Science and Technology (Guangzhou), Guangzhou, China
2 shared publications - Hui Liu
Amazon, Palo Alto, CA, USA
2 shared publications - Xianfeng Tang
Amazon, Palo Alto, CA, USA
2 shared publications
Latest Publications
- Open Access
- 12 August 2026
- Published by Association for Computing Machinery (ACM) in ACM Transactions on Knowledge Discovery From Data
How Far Are LLMs from Real Search: Rethinking the Complementary Roles of Search and Learning
Search plays a fundamental role in problem-solving across various domains, with most real-world decision-making problems being solvable through systematic search. Drawing inspiration from recent discussions on search and learning, we systematically explore the complementary relationship between search and Large Language Models (LLMs) from three perspectives. First, we analyze how learning can enhance search efficiency and propose Se arch vi a L earning ( SeaL ), a framework that leverages LLMs for effective and efficient search. Second, we further extend SeaL to SeaL-C to ensure rigorous completeness during search. Our evaluation across three real-world planning tasks demonstrates that SeaL achieves near-perfect accuracy while reducing search spaces by up to 99.1% compared to traditional approaches. Finally, we explore how far LLMs are from real search by investigating whether they can develop search capabilities independently. Our analysis reveals that while current LLMs struggle with efficient search in complex problems, incorporating systematic search strategies significantly enhances their problem-solving capabilities. These findings not only validate the effectiveness of our approach but also highlight the need for improving LLMs’ search abilities for real-world applications. Our code is available at https://github.com/ventr1c/SeaL .
- 12 August 2026
- Published by Association for Computing Machinery (ACM) in ACM Transactions on Knowledge Discovery From Data
Open AccessHow Far Are LLMs from Real Search: Rethinking the Complementary Roles of Search and Learning
Search plays a fundamental role in problem-solving across various domains, with most real-world decision-making problems being solvable through systematic search. Drawing inspiration from recent discussions on search and learning, we systematically explore the complementary relationship between search and Large Language Models (LLMs) from three perspectives. First, we analyze how learning can enhance search efficiency and propose Se arch vi a L earning ( SeaL ), a framework that leverages LLMs for effective and efficient search. Second, we further extend SeaL to SeaL-C to ensure rigorous completeness during search. Our evaluation across three real-world planning tasks demonstrates that SeaL achieves near-perfect accuracy while reducing search spaces by up to 99.1% compared to traditional approaches. Finally, we explore how far LLMs are from real search by investigating whether they can develop search capabilities independently. Our analysis reveals that while current LLMs struggle with efficient search in complex problems, incorporating systematic search strategies significantly enhances their problem-solving capabilities. These findings not only validate the effectiveness of our approach but also highlight the need for improving LLMs’ search abilities for real-world applications. Our code is available at https://github.com/ventr1c/SeaL .
- Open Access
- 8 August 2026
- Published by Association for Computing Machinery (ACM)
- p. 3573-3584
Do Explanations Increase the Risk of Decision Logic Leakage? Explanation-Guided Stealing of Graph Models
- 8 August 2026
- Published by Association for Computing Machinery (ACM)
- p. 3573-3584
Open AccessDo Explanations Increase the Risk of Decision Logic Leakage? Explanation-Guided Stealing of Graph Models
- Open Access
- 8 August 2026
- Published by Association for Computing Machinery (ACM)
- p. 10150-10161
General Protein Pretraining or Domain-Specific Designs? Benchmarking Protein Modeling on Realistic Applications
- 8 August 2026
- Published by Association for Computing Machinery (ACM)
- p. 10150-10161
Open AccessGeneral Protein Pretraining or Domain-Specific Designs? Benchmarking Protein Modeling on Realistic Applications
- Open Access
- 3 August 2025
- Published by Association for Computing Machinery (ACM)
- p. 1729-1740
Are You Using Reliable Graph Prompts? Trojan Prompt Attacks on Graph Neural Networks
- 3 August 2025
- Published by Association for Computing Machinery (ACM)
- p. 1729-1740
Open AccessAre You Using Reliable Graph Prompts? Trojan Prompt Attacks on Graph Neural Networks
- Open Access
- 3 August 2025
- Published by Association for Computing Machinery (ACM)
- p. 6173-6183
A Survey on Small Language Models in the Era of Large Language Models: Architecture, Capabilities, and Trustworthiness
- 3 August 2025
- Published by Association for Computing Machinery (ACM)
- p. 6173-6183
Open AccessA Survey on Small Language Models in the Era of Large Language Models: Architecture, Capabilities, and Trustworthiness
- Open Access
- 3 August 2025
- Published by Association for Computing Machinery (ACM)
- p. 415-426
PreGIP: Watermarking the Pretraining of Graph Neural Networks for Deep IP Protection
- 3 August 2025
- Published by Association for Computing Machinery (ACM)
- p. 415-426
Open AccessPreGIP: Watermarking the Pretraining of Graph Neural Networks for Deep IP Protection
- Open Access
- 20 July 2025
- Published by Association for Computing Machinery (ACM)
- p. 777-788
Stealing Training Graphs from Graph Neural Networks
- 20 July 2025
- Published by Association for Computing Machinery (ACM)
- p. 777-788
Open AccessStealing Training Graphs from Graph Neural Networks
- Open Access
- 22 April 2025
- Published by Association for Computing Machinery (ACM)
- p. 3586-3597
Fairness-aware Prompt Tuning for Graph Neural Networks
- 22 April 2025
- Published by Association for Computing Machinery (ACM)
- p. 3586-3597
Open AccessFairness-aware Prompt Tuning for Graph Neural Networks
- Open Access
- 24 August 2024
- Published by Association for Computing Machinery (ACM)
- p. 4386-4397
Rethinking Graph Backdoor Attacks: A Distribution-Preserving Perspective
Graph Neural Networks (GNNs) have shown remarkable performance in various tasks. However, recent works reveal that GNNs are vulnerable to backdoor attacks. Generally, backdoor attack poisons the graph by attaching backdoor triggers and the target class label to a set of nodes in the training graph. A GNN trained on the poisoned graph will then be misled to predict test nodes attached with trigger to the target class. Despite their effectiveness, our empirical analysis shows that triggers generated by existing methods tend to be out-of-distribution (OOD), which significantly differ from the clean data. Hence, these injected triggers can be easily detected and pruned with widely used outlier detection methods in real-world applications. Therefore, in this paper, we study a novel problem of unnoticeable graph backdoor attacks with in-distribution (ID) triggers. To generate ID triggers, we introduce an OOD detector in conjunction with an adversarial learning strategy to generate the attributes of the triggers within distribution. To ensure a high attack success rate with ID triggers, we introduce novel modules designed to enhance trigger memorization by the victim model trained on poisoned graph. Extensive experiments on real-world datasets demonstrate the effectiveness of the proposed method in generating in distribution triggers that can bypass various defense strategies while maintaining a high attack success rate.
- 24 August 2024
- Published by Association for Computing Machinery (ACM)
- p. 4386-4397
Open AccessRethinking Graph Backdoor Attacks: A Distribution-Preserving Perspective
Graph Neural Networks (GNNs) have shown remarkable performance in various tasks. However, recent works reveal that GNNs are vulnerable to backdoor attacks. Generally, backdoor attack poisons the graph by attaching backdoor triggers and the target class label to a set of nodes in the training graph. A GNN trained on the poisoned graph will then be misled to predict test nodes attached with trigger to the target class. Despite their effectiveness, our empirical analysis shows that triggers generated by existing methods tend to be out-of-distribution (OOD), which significantly differ from the clean data. Hence, these injected triggers can be easily detected and pruned with widely used outlier detection methods in real-world applications. Therefore, in this paper, we study a novel problem of unnoticeable graph backdoor attacks with in-distribution (ID) triggers. To generate ID triggers, we introduce an OOD detector in conjunction with an adversarial learning strategy to generate the attributes of the triggers within distribution. To ensure a high attack success rate with ID triggers, we introduce novel modules designed to enhance trigger memorization by the victim model trained on poisoned graph. Extensive experiments on real-world datasets demonstrate the effectiveness of the proposed method in generating in distribution triggers that can bypass various defense strategies while maintaining a high attack success rate.
- Open Access
- 4 March 2024
- Published by Association for Computing Machinery (ACM)
- p. 693-701
Efficient, Direct, and Restricted Black-Box Graph Evasion Attacks to Any-Layer Graph Neural Networks via Influence Function
- 4 March 2024
- Published by Association for Computing Machinery (ACM)
- p. 693-701
Open AccessEfficient, Direct, and Restricted Black-Box Graph Evasion Attacks to Any-Layer Graph Neural Networks via Influence Function