Shichao Pei
Current Organizations / Institutes
The organizations/institutes from the scholar's latest article
Previous Organizations / Institutes
The organizations / institutes from the scholar's other articles in the past ten years
Research Subjects
Shichao Pei has a total of 50 co-authors. Here are the top co-authors by number of shared publications:
- Xiangliang Zhang
University of Notre Dame
6 shared publications - Ziyi Kou
University of Notre Dame, Notre Dame, IN, USA
2 shared publications - Amin Beheshti
Macquarie University, Sydney, NSW, Australia
1 shared publication - Armin Toroghi
University of Toronto, Toronto, ON, Canada
1 shared publication - Chunhua Hu
Institute of Big Data and Internet Innovation, Hunan University of Technology and Business, Changsha, China
1 shared publication - Chuxu Zhang
University of Connecticut, Storrs, CT, USA
1 shared publication
Latest Publications
- Open Access
- 12 October 2026
- Published by Association for Computing Machinery (ACM)
- p. 563-573
Behavioral Consistency and Transparency Analysis on Large Language Model API Gateways
- 12 October 2026
- Published by Association for Computing Machinery (ACM)
- p. 563-573
Open AccessBehavioral Consistency and Transparency Analysis on Large Language Model API Gateways
- Open Access
- 12 April 2026
- Published by Association for Computing Machinery (ACM)
- p. 3788-3799
PLIKD: Prompt Learning with Instance-aware Knowledge Distillation for Web-scale Semantic Image Classification
With the rapid growth of multi-modal content on the Web, robust vision-language models are essential for semantic understanding and classification of web images under diverse and dynamic contexts, supporting Web applications such as multimedia search and recommendation. Prompt learning has proven effective for enhancing vision-language models in semantic image classification tasks. However, previous methods often suffer from poor generalization: the learned prompts tend to overfit the base classes seen during training, leading to poor performance on unseen classes and under distribution shifts. This issue is especially challenging in Web-scale data, where new classes emerge and distributions shift dynamically. To address these limitations, we propose PLIKD, a novel prompt learning method that integrates instance-aware knowledge distillation for robust Web-scale semantic image classification. Specifically, PLIKD introduces an instance-aware knowledge extraction module, which leverages multi-modal large language models through a step-by-step strategy to extract external knowledge for each image instance. To incorporate this extracted knowledge, PLIKD further introduces an instance-aware knowledge distillation module, which consists of two key steps: (1) a dual-teacher strategy for robust and informative knowledge distillation, and (2) fine-grained cross-modal alignment via Smooth and Sparse Optimal Transport. Extensive experiments demonstrate that PLIKD significantly improves generalization to both seen and unseen classes, and remains robust under distribution shifts, outperforming existing state-of-the-art methods on Web-scale semantic image classification.
- 12 April 2026
- Published by Association for Computing Machinery (ACM)
- p. 3788-3799
Open AccessPLIKD: Prompt Learning with Instance-aware Knowledge Distillation for Web-scale Semantic Image Classification
With the rapid growth of multi-modal content on the Web, robust vision-language models are essential for semantic understanding and classification of web images under diverse and dynamic contexts, supporting Web applications such as multimedia search and recommendation. Prompt learning has proven effective for enhancing vision-language models in semantic image classification tasks. However, previous methods often suffer from poor generalization: the learned prompts tend to overfit the base classes seen during training, leading to poor performance on unseen classes and under distribution shifts. This issue is especially challenging in Web-scale data, where new classes emerge and distributions shift dynamically. To address these limitations, we propose PLIKD, a novel prompt learning method that integrates instance-aware knowledge distillation for robust Web-scale semantic image classification. Specifically, PLIKD introduces an instance-aware knowledge extraction module, which leverages multi-modal large language models through a step-by-step strategy to extract external knowledge for each image instance. To incorporate this extracted knowledge, PLIKD further introduces an instance-aware knowledge distillation module, which consists of two key steps: (1) a dual-teacher strategy for robust and informative knowledge distillation, and (2) fine-grained cross-modal alignment via Smooth and Sparse Optimal Transport. Extensive experiments demonstrate that PLIKD significantly improves generalization to both seen and unseen classes, and remains robust under distribution shifts, outperforming existing state-of-the-art methods on Web-scale semantic image classification.
- Open Access
- 20 August 2025
- Published by Elsevier in Materials Science and Engineering: R: Reports
- Vol. 166
Machine learning for 2D material–based devices
- 20 August 2025
- Published by Elsevier in Materials Science and Engineering: R: Reports
- Vol. 166
Open AccessMachine learning for 2D material–based devices
- Top Cited PapersOpen Access
- 5 March 2025
- Published by Association for Computing Machinery (ACM) in ACM Computing Surveys
- Vol. 57  (8) , 1-16
Knowledge Distillation on Graphs: A Survey
Graph Neural Networks (GNNs) have received significant attention for demonstrating their capability to handle graph data. However, they are difficult to be deployed in resource-limited devices because of model sizes and scalability constraints imposed by the multi-hop data dependency. In addition, real-world graphs usually possess complex structural information and features. Therefore, to improve the applicability of GNNs and fully encode the complicated topological information, Knowledge Distillation on Graphs (KDG) has been introduced to build a smaller but effective model, leading to model compression and performance improvement. Recently, KDG has achieved considerable progress, with many studies proposed. In this survey, we systematically review these works. Specifically, we first introduce the challenges and bases of KDG, then categorize and summarize the existing work of KDG by answering the following three questions: (1) what to distillate, (2) who to whom, and (3) how to distillate. We offer in-depth comparisons and elucidate the strengths and weaknesses of each design. Finally, we share our thoughts on future research directions.
- 5 March 2025
- Published by Association for Computing Machinery (ACM) in ACM Computing Surveys
- Vol. 57  (8) , 1-16
Top Cited PapersOpen AccessKnowledge Distillation on Graphs: A Survey
Graph Neural Networks (GNNs) have received significant attention for demonstrating their capability to handle graph data. However, they are difficult to be deployed in resource-limited devices because of model sizes and scalability constraints imposed by the multi-hop data dependency. In addition, real-world graphs usually possess complex structural information and features. Therefore, to improve the applicability of GNNs and fully encode the complicated topological information, Knowledge Distillation on Graphs (KDG) has been introduced to build a smaller but effective model, leading to model compression and performance improvement. Recently, KDG has achieved considerable progress, with many studies proposed. In this survey, we systematically review these works. Specifically, we first introduce the challenges and bases of KDG, then categorize and summarize the existing work of KDG by answering the following three questions: (1) what to distillate, (2) who to whom, and (3) how to distillate. We offer in-depth comparisons and elucidate the strengths and weaknesses of each design. Finally, we share our thoughts on future research directions.
- Open Access
- 21 October 2024
- Published by Association for Computing Machinery (ACM)
- p. 1326-1335
Learning from Novel Knowledge: Continual Few-shot Knowledge Graph Completion
Knowledge graph (KG) completion has been increasingly recognized as a vital approach for uncovering missing knowledge and addressing the incompleteness issue in KGs. To enhance inference on rare relations and mitigate the impact of the long-tail distribution, the dominant strategy designs few-shot models following the meta-learning paradigm. However, these approaches typically operate under the assumption that KGs are available instantly, disregarding the newly emerging relations during KG enrichment. Thus, the emergence of these novel relations presents a need for few-shot models to continually learn from emerging knowledge. Although promising, two significant obstacles, i.e., catastrophic forgetting and the scarcity of novel relations, prevent effective learning from newly emerging relations. In this paper, we propose a novel framework designed to equip the few-shot model with the ability to learn sequentially from novel relations. Specifically, we introduce innovative strategies at both data and model levels: data-level rehearsal and model-level modulation to address catastrophic forgetting, alongside multi-view relation augmentation aimed at resolving the issue of insufficient novel relations. Extensive experiments conducted on real-world KGs validate the effectiveness of our proposed method.
- 21 October 2024
- Published by Association for Computing Machinery (ACM)
- p. 1326-1335
Open AccessLearning from Novel Knowledge: Continual Few-shot Knowledge Graph Completion
Knowledge graph (KG) completion has been increasingly recognized as a vital approach for uncovering missing knowledge and addressing the incompleteness issue in KGs. To enhance inference on rare relations and mitigate the impact of the long-tail distribution, the dominant strategy designs few-shot models following the meta-learning paradigm. However, these approaches typically operate under the assumption that KGs are available instantly, disregarding the newly emerging relations during KG enrichment. Thus, the emergence of these novel relations presents a need for few-shot models to continually learn from emerging knowledge. Although promising, two significant obstacles, i.e., catastrophic forgetting and the scarcity of novel relations, prevent effective learning from newly emerging relations. In this paper, we propose a novel framework designed to equip the few-shot model with the ability to learn sequentially from novel relations. Specifically, we introduce innovative strategies at both data and model levels: data-level rehearsal and model-level modulation to address catastrophic forgetting, alongside multi-view relation augmentation aimed at resolving the issue of insufficient novel relations. Extensive experiments conducted on real-world KGs validate the effectiveness of our proposed method.
- Open Access
- 24 August 2024
- Published by Association for Computing Machinery (ACM)
- p. 1418-1427
LeMon: Automating Portrait Generation for Zero-Shot Story Visualization with Multi-Character Interactions
Zero-Shot Story Visualization (ZSV) seeks to depict textual narratives through a sequence of images without relying on pre-existing text-image pairs for training. In this paper, we address the challenge of automated multi-character ZSV, aiming to create distinctive yet compatible character portraits for high-quality story visualization without the need of manual human interventions. Our study is motivated by the limitation of current ZSV approaches that necessitate inefficient manual collection of external images as initial character portraits and suffer from low-quality story visualization, especially with multi-character interactions, when the portraits are not well initiated. To overcome these issues, we develop LeMon, an LLM enhanced Multi-Character Zero-Shot Visualization framework that automates character portrait initialization and supports iterative portrait refinement by exploring the semantic content of the story. In particular, we design an LLM-based portrait generation strategy that matches the story characters with external movie characters, and leverage the matched resources as in-context learning (ICL) samples for LLMs to accurately initialize the character portraits. We then propose a graph-based Text2Image diffusion model that constructs a character interaction graph from the story to iteratively refine the character portraits by maximizing the distinctness of different characters while minimizing their incompatibility in the multi-character story visualization. Our evaluation results show that LeMon outperforms existing ZSV approaches in generating high-quality visualizations for stories across various types with multiple interacted characters. Our code is available at https://github.com/arxrean/LLM-LeMon.
- 24 August 2024
- Published by Association for Computing Machinery (ACM)
- p. 1418-1427
Open AccessLeMon: Automating Portrait Generation for Zero-Shot Story Visualization with Multi-Character Interactions
Zero-Shot Story Visualization (ZSV) seeks to depict textual narratives through a sequence of images without relying on pre-existing text-image pairs for training. In this paper, we address the challenge of automated multi-character ZSV, aiming to create distinctive yet compatible character portraits for high-quality story visualization without the need of manual human interventions. Our study is motivated by the limitation of current ZSV approaches that necessitate inefficient manual collection of external images as initial character portraits and suffer from low-quality story visualization, especially with multi-character interactions, when the portraits are not well initiated. To overcome these issues, we develop LeMon, an LLM enhanced Multi-Character Zero-Shot Visualization framework that automates character portrait initialization and supports iterative portrait refinement by exploring the semantic content of the story. In particular, we design an LLM-based portrait generation strategy that matches the story characters with external movie characters, and leverage the matched resources as in-context learning (ICL) samples for LLMs to accurately initialize the character portraits. We then propose a graph-based Text2Image diffusion model that constructs a character interaction graph from the story to iteratively refine the character portraits by maximizing the distinctness of different characters while minimizing their incompatibility in the multi-character story visualization. Our evaluation results show that LeMon outperforms existing ZSV approaches in generating high-quality visualizations for stories across various types with multiple interacted characters. Our code is available at https://github.com/arxrean/LLM-LeMon.
- Open Access
- 4 August 2023
- Published by Association for Computing Machinery (ACM)
- p. 1862-1871
Few-shot Low-resource Knowledge Graph Completion with Multi-view Task Representation Generation
Despite their capacity to convey knowledge, most existing knowledge graphs (KGs) are created for specific domains using low-resource data sources, especially those in non-global languages, and thus unavoidably suffer from the incompleteness problem. The automatic discovery of missing triples for KG completion is thus hindered by the challenging long-tail relations problem in low-resource KGs. Few-shot learning models trained on rich-resource KGs are unable to tackle this challenge due to a lack of generalization. To alleviate the impact of the intractable long-tail problem on low-resource KG completion, in this paper, we propose a novel few-shot learning framework empowered by multi-view task representation generation. The framework consists of four components, i.e., few-shot learner, perturbed few-shot learner, relation knowledge distiller, and pairwise contrastive distiller. The key idea is to utilize the different views of each few-shot task to improve and regulate the training of the few-shot learner. For each few-shot task, instead of augmenting it by complicated task designs, we generate its representation of different views using the relation knowledge distiller and perturbed few-shot learner, which are obtained by distilling knowledge from a KG encoder and perturbing the few-shot learner. Then, the generated representation of different views is utilized by the pairwise contrastive distiller based on a teacher-student framework to distill the knowledge of how to represent relations from different views into the few-shot learner and facilitate few-shot learning. Extensive experiments conducted on several real-world low-resource KGs validate the effectiveness of our proposed method.
- 4 August 2023
- Published by Association for Computing Machinery (ACM)
- p. 1862-1871
Open AccessFew-shot Low-resource Knowledge Graph Completion with Multi-view Task Representation Generation
Despite their capacity to convey knowledge, most existing knowledge graphs (KGs) are created for specific domains using low-resource data sources, especially those in non-global languages, and thus unavoidably suffer from the incompleteness problem. The automatic discovery of missing triples for KG completion is thus hindered by the challenging long-tail relations problem in low-resource KGs. Few-shot learning models trained on rich-resource KGs are unable to tackle this challenge due to a lack of generalization. To alleviate the impact of the intractable long-tail problem on low-resource KG completion, in this paper, we propose a novel few-shot learning framework empowered by multi-view task representation generation. The framework consists of four components, i.e., few-shot learner, perturbed few-shot learner, relation knowledge distiller, and pairwise contrastive distiller. The key idea is to utilize the different views of each few-shot task to improve and regulate the training of the few-shot learner. For each few-shot task, instead of augmenting it by complicated task designs, we generate its representation of different views using the relation knowledge distiller and perturbed few-shot learner, which are obtained by distilling knowledge from a KG encoder and perturbing the few-shot learner. Then, the generated representation of different views is utilized by the pairwise contrastive distiller based on a teacher-student framework to distill the knowledge of how to represent relations from different views into the few-shot learner and facilitate few-shot learning. Extensive experiments conducted on several real-world low-resource KGs validate the effectiveness of our proposed method.
- Open Access
- 18 July 2023
- Published by Association for Computing Machinery (ACM)
- p. 2129-2133
LogicRec: Recommendation with Users' Logical Requirements
Users may demand recommendations with highly personalized requirements involving logical operations, e.g., the intersection of two requirements, where such requirements naturally form structured logical queries on knowledge graphs (KGs). To date, existing recommender systems lack the capability to tackle users' complex logical requirements. In this work, we formulate the problem of recommendation with users' logical requirements (LogicRec) and construct benchmark datasets for LogicRec. Furthermore, we propose an initial solution for LogicRec based on logical requirement retrieval and user preference retrieval, where we face two challenges. First, KGs are incomplete in nature. Therefore, there are always missing true facts, which entails that the answers to logical requirements can not be completely found in KGs. In this case, item selection based on the answers to logical queries is not applicable. We thus resort to logical query embedding (LQE) to jointly infer missing facts and retrieve items based on logical requirements. Second, answer sets are under-exploited. Existing LQE methods can only deal with query-answer pairs, where queries in our case are the intersected user preferences and logical requirements. However, the logical requirements and user preferences have different answer sets, offering us richer knowledge about the requirements and preferences by providing requirement-item and preference-item pairs. Thus, we design a multi-task knowledge-sharing mechanism to exploit these answer sets collectively. Extensive experimental results demonstrate the significance of the LogicRec task and the effectiveness of our proposed method.
- 18 July 2023
- Published by Association for Computing Machinery (ACM)
- p. 2129-2133
Open AccessLogicRec: Recommendation with Users' Logical Requirements
Users may demand recommendations with highly personalized requirements involving logical operations, e.g., the intersection of two requirements, where such requirements naturally form structured logical queries on knowledge graphs (KGs). To date, existing recommender systems lack the capability to tackle users' complex logical requirements. In this work, we formulate the problem of recommendation with users' logical requirements (LogicRec) and construct benchmark datasets for LogicRec. Furthermore, we propose an initial solution for LogicRec based on logical requirement retrieval and user preference retrieval, where we face two challenges. First, KGs are incomplete in nature. Therefore, there are always missing true facts, which entails that the answers to logical requirements can not be completely found in KGs. In this case, item selection based on the answers to logical queries is not applicable. We thus resort to logical query embedding (LQE) to jointly infer missing facts and retrieve items based on logical requirements. Second, answer sets are under-exploited. Existing LQE methods can only deal with query-answer pairs, where queries in our case are the intersected user preferences and logical requirements. However, the logical requirements and user preferences have different answer sets, offering us richer knowledge about the requirements and preferences by providing requirement-item and preference-item pairs. Thus, we design a multi-task knowledge-sharing mechanism to exploit these answer sets collectively. Extensive experimental results demonstrate the significance of the LogicRec task and the effectiveness of our proposed method.
- Open Access
TAR: Neural Logical Reasoning across TBox and ABox
Many ontologies, i.e., Description Logic (DL) knowledge bases, have been developed to provide rich knowledge about various domains. An ontology consists of an ABox, i.e., assertion axioms between two entities or between a concept and an entity, and a TBox, i.e., terminology axioms between two concepts. Neural logical reasoning (NLR) is a fundamental task to explore such knowledge bases, which aims at answering multi-hop queries with logical operations based on distributed representations of queries and answers. While previous NLR methods can give specific entity-level answers, i.e., ABox answers, they are not able to provide descriptive concept-level answers, i.e., TBox answers, where each concept is a description of a set of entities. In other words, previous NLR methods only reason over the ABox of an ontology while ignoring the TBox. In particular, providing TBox answers enables inferring the explanations of each query with descriptive concepts, which make answers comprehensible to users and are of great usefulness in the field of applied ontology. In this work, we formulate the problem of neural logical reasoning across TBox and ABox (TA-NLR), solving which needs to address challenges in incorporating, representing, and operating on concepts. We propose an original solution named TAR for TA-NLR. Firstly, we incorporate description logic based ontological axioms to provide the source of concepts. Then, we represent concepts and queries as fuzzy sets, i.e., sets whose elements have degrees of membership, to bridge concepts and queries with entities. Moreover, we design operators involving concepts on top of fuzzy set representation of concepts and queries for optimization and inference. Extensive experimental results on two real-world datasets demonstrate the effectiveness of TAR for TA-NLR.
Open AccessTAR: Neural Logical Reasoning across TBox and ABox
Many ontologies, i.e., Description Logic (DL) knowledge bases, have been developed to provide rich knowledge about various domains. An ontology consists of an ABox, i.e., assertion axioms between two entities or between a concept and an entity, and a TBox, i.e., terminology axioms between two concepts. Neural logical reasoning (NLR) is a fundamental task to explore such knowledge bases, which aims at answering multi-hop queries with logical operations based on distributed representations of queries and answers. While previous NLR methods can give specific entity-level answers, i.e., ABox answers, they are not able to provide descriptive concept-level answers, i.e., TBox answers, where each concept is a description of a set of entities. In other words, previous NLR methods only reason over the ABox of an ontology while ignoring the TBox. In particular, providing TBox answers enables inferring the explanations of each query with descriptive concepts, which make answers comprehensible to users and are of great usefulness in the field of applied ontology. In this work, we formulate the problem of neural logical reasoning across TBox and ABox (TA-NLR), solving which needs to address challenges in incorporating, representing, and operating on concepts. We propose an original solution named TAR for TA-NLR. Firstly, we incorporate description logic based ontological axioms to provide the source of concepts. Then, we represent concepts and queries as fuzzy sets, i.e., sets whose elements have degrees of membership, to bridge concepts and queries with entities. Moreover, we design operators involving concepts on top of fuzzy set representation of concepts and queries for optimization and inference. Extensive experimental results on two real-world datasets demonstrate the effectiveness of TAR for TA-NLR.
- Open Access
- 29 November 2021
- Published by Association for Computing Machinery (ACM)
- p. 462-466
A Generic Knowledge Based Medical Diagnosis Expert System
In this paper, we design and implement a generic medical knowledge based system (MKBS) for identifying diseases from several symptoms. In this system, some important aspects like knowledge bases system, knowledge representation, inference engine have been addressed. The system asks users different questions and inference engines will use the certainty factor to prune out low possible solutions. The proposed disease diagnosis system also uses a graphical user interface (GUI) to facilitate users to interact with the expert system. Our expert system is generic and flexible, which can be integrated with any rule bases system in disease diagnosis.
- 29 November 2021
- Published by Association for Computing Machinery (ACM)
- p. 462-466
Open AccessA Generic Knowledge Based Medical Diagnosis Expert System
In this paper, we design and implement a generic medical knowledge based system (MKBS) for identifying diseases from several symptoms. In this system, some important aspects like knowledge bases system, knowledge representation, inference engine have been addressed. The system asks users different questions and inference engines will use the certainty factor to prune out low possible solutions. The proposed disease diagnosis system also uses a graphical user interface (GUI) to facilitate users to interact with the expert system. Our expert system is generic and flexible, which can be integrated with any rule bases system in disease diagnosis.