Jian Kang
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
Jian Kang has a total of 52 co-authors. Here are the top co-authors by number of shared publications:
- Dawei Zhou
Virginia Tech, Blacksburg, VA, USA
4 shared publications - Hanghang Tong
University of Illinois Urbana-Champaign, Urbana, IL, USA
3 shared publications - Fei Wang
Amazon, Sunnyvale, CA, USA
2 shared publications - Haohui Wang
Virginia Polytechnic Institute and State University, Blacksbug, USA
2 shared publications - Hyunsik Yoo
University of Illinois Urbana-Champaign, Urbana, IL, USA
2 shared publications - Ruizhong Qiu
University of Illinois Urbana-Champaign, Urbana, IL, USA
2 shared publications
Latest Publications
- Open Access
- 6 November 2026
- Published by Association for Computing Machinery (ACM)
- p. 2503-2513
Beyond Observed Auxiliary Relations: Environment-Conditioned Modeling for Multi-Behavior Recommendation
- 6 November 2026
- Published by Association for Computing Machinery (ACM)
- p. 2503-2513
Open AccessBeyond Observed Auxiliary Relations: Environment-Conditioned Modeling for Multi-Behavior Recommendation
- Open Access
- 7 October 2026
- Published by Association for Computing Machinery (ACM)
- p. 3655-3659
AIALIB: A Threat Library for AI-Generated Code
- 7 October 2026
- Published by Association for Computing Machinery (ACM)
- p. 3655-3659
Open AccessAIALIB: A Threat Library for AI-Generated Code
- Open Access
- 8 August 2026
- Published by Association for Computing Machinery (ACM)
- p. 13419-13420
The 2nd SeT-LLM Workshop on Secure and Trustworthy Large Language Models
- 8 August 2026
- Published by Association for Computing Machinery (ACM)
- p. 13419-13420
Open AccessThe 2nd SeT-LLM Workshop on Secure and Trustworthy Large Language Models
- Open Access
- 3 August 2025
- Published by Association for Computing Machinery (ACM)
- p. 3031-3042
Non-exchangeable Conformal Prediction for Temporal Graph Neural Networks
- 3 August 2025
- Published by Association for Computing Machinery (ACM)
- p. 3031-3042
Open AccessNon-exchangeable Conformal Prediction for Temporal Graph Neural Networks
- Open Access
- 3 August 2025
- Published by Association for Computing Machinery (ACM)
- p. 709-720
EVI N ET: Towards Open-World Graph Learning via Evidential Reasoning Network
- 3 August 2025
- Published by Association for Computing Machinery (ACM)
- p. 709-720
Open AccessEVI N ET: Towards Open-World Graph Learning via Evidential Reasoning Network
- Open Access
- 23 June 2025
- Published by Association for Computing Machinery (ACM)
- p. 2815-2846
Characterizing Bias: Benchmarking Large Language Models in Simplified versus Traditional Chinese
- 23 June 2025
- Published by Association for Computing Machinery (ACM)
- p. 2815-2846
Open AccessCharacterizing Bias: Benchmarking Large Language Models in Simplified versus Traditional Chinese
- Open Access
- 22 April 2025
- Published by Association for Computing Machinery (ACM)
- p. 4625-4634
Bridging Fairness and Uncertainty: Theoretical Insights and Practical Strategies for Equalized Coverage in GNNs
- 22 April 2025
- Published by Association for Computing Machinery (ACM)
- p. 4625-4634
Open AccessBridging Fairness and Uncertainty: Theoretical Insights and Practical Strategies for Equalized Coverage in GNNs
- Open Access
- 21 October 2024
- Published by Association for Computing Machinery (ACM)
- p. 829-838
On the Sensitivity of Individual Fairness: Measures and Robust Algorithms
Algorithmic fairness has been receiving increasing attention in recent years. Among others, individual fairness, with its root in the dictionary definition of fairness, offers a fine-grained fairness notion. At the algorithmic level, individual fairness can often be operationalized as a convex regularization term with respect to a similarity matrix. Appealing as it might be, a notorious challenge of individual fairness lies in how to find appropriate distance or similarity measure, which largely remains open to date. Consequently, the similarity or distance measure used in almost any individually fair algorithm is likely to be imperfect due to various reasons such as imprecise prior/domain knowledge, noise, or even adversaries. In this paper, we take an important step towards resolving this fundamental challenge and ask: how sensitive is the individually fair learning algorithm with respect to the given similarities? How can we make the learning results robust with respect to the imperfection of the given similarity measure? First (Soul-M), we develop a sensitivity measure to characterize how the learning outcomes of an individually fair learning algorithm change in response to the change of the given similarity measure. Second (Soul-A ), based on the proposed sensitive measure, we further develop a robust individually fair algorithm by adversarial learning that optimizes the similarity matrix to defend against L_∞ attack. A unique advantage of our sensitivity measure and robust algorithm lies in that they are applicable to a broad range of learning models as long as the objective function is twice differentiable. We conduct extensive experiments to demonstrate the efficacy of our methods.
- 21 October 2024
- Published by Association for Computing Machinery (ACM)
- p. 829-838
Open AccessOn the Sensitivity of Individual Fairness: Measures and Robust Algorithms
Algorithmic fairness has been receiving increasing attention in recent years. Among others, individual fairness, with its root in the dictionary definition of fairness, offers a fine-grained fairness notion. At the algorithmic level, individual fairness can often be operationalized as a convex regularization term with respect to a similarity matrix. Appealing as it might be, a notorious challenge of individual fairness lies in how to find appropriate distance or similarity measure, which largely remains open to date. Consequently, the similarity or distance measure used in almost any individually fair algorithm is likely to be imperfect due to various reasons such as imprecise prior/domain knowledge, noise, or even adversaries. In this paper, we take an important step towards resolving this fundamental challenge and ask: how sensitive is the individually fair learning algorithm with respect to the given similarities? How can we make the learning results robust with respect to the imperfection of the given similarity measure? First (Soul-M), we develop a sensitivity measure to characterize how the learning outcomes of an individually fair learning algorithm change in response to the change of the given similarity measure. Second (Soul-A ), based on the proposed sensitive measure, we further develop a robust individually fair algorithm by adversarial learning that optimizes the similarity matrix to defend against L_∞ attack. A unique advantage of our sensitivity measure and robust algorithm lies in that they are applicable to a broad range of learning models as long as the objective function is twice differentiable. We conduct extensive experiments to demonstrate the efficacy of our methods.
- Open Access
- 21 October 2024
- Published by Association for Computing Machinery (ACM)
- p. 5534-5537
Data Quality-aware Graph Machine Learning
Recent years have seen a significant shift in Artificial Intelligence from model-centric to data-centric approaches, highlighted by the success of large foundational models. Following this trend, despite numerous innovations in graph machine learning model design, graph-structured data often suffers from data quality issues, jeopardizing the progress of Data-centric AI in graph-structured applications. Our proposed tutorial addresses this gap by raising awareness about data quality issues within the graph machine-learning community. We provide an overview of existing topology, imbalance, bias, limited data, and abnormality issues in graph data. Additionally, we highlight recent developments in foundational graph models that focus on identifying, investigating, mitigating, and resolving these issues.
- 21 October 2024
- Published by Association for Computing Machinery (ACM)
- p. 5534-5537
Open AccessData Quality-aware Graph Machine Learning
Recent years have seen a significant shift in Artificial Intelligence from model-centric to data-centric approaches, highlighted by the success of large foundational models. Following this trend, despite numerous innovations in graph machine learning model design, graph-structured data often suffers from data quality issues, jeopardizing the progress of Data-centric AI in graph-structured applications. Our proposed tutorial addresses this gap by raising awareness about data quality issues within the graph machine-learning community. We provide an overview of existing topology, imbalance, bias, limited data, and abnormality issues in graph data. Additionally, we highlight recent developments in foundational graph models that focus on identifying, investigating, mitigating, and resolving these issues.
- Open Access
- 24 August 2024
- Published by Association for Computing Machinery (ACM)
- p. 2524-2535
LARP: Language Audio Relational Pre-training for Cold-Start Playlist Continuation
As online music consumption increasingly shifts towards playlist-based listening, the task of playlist continuation, in which an algorithm suggests songs to extend a playlist in a personalized and musically cohesive manner, has become vital to the success of music streaming services. Currently, many existing playlist continuation approaches rely on collaborative filtering methods to perform their recommendations. However, such methods will struggle to recommend songs that lack interaction data, an issue known as the cold-start problem. Current approaches to this challenge design complex mechanisms for extracting relational signals from sparse collaborative signals and integrating them into content representations. However, these approaches leave content representation learning out of scope and utilize frozen, pre-trained content models that may not be aligned with the distribution or format of a specific musical setting. Furthermore, even the musical state-of-the-art content modules are either (1) incompatible with the cold-start setting or (2) unable to effectively integrate cross-modal and relational signals. In this paper, we introduce LARP, a multi-modal cold-start playlist continuation model, to effectively overcome these limitations. LARP is a three-stage contrastive learning framework that integrates both multi-modal and relational signals into its learned representations. Our framework uses increasing stages of task-specific abstraction: within-track (language-audio) contrastive loss, track-track contrastive loss, and track-playlist contrastive loss. Experimental results on two publicly available datasets demonstrate the efficacy of LARP over uni-modal and multi-modal models for playlist continuation in a cold-start setting. Finally, this work pioneers the perspective of addressing cold-start recommendation via relational representation learning. Code and dataset are released at: https://github.com/Rsalganik1123/LARP/
- 24 August 2024
- Published by Association for Computing Machinery (ACM)
- p. 2524-2535
Open AccessLARP: Language Audio Relational Pre-training for Cold-Start Playlist Continuation
As online music consumption increasingly shifts towards playlist-based listening, the task of playlist continuation, in which an algorithm suggests songs to extend a playlist in a personalized and musically cohesive manner, has become vital to the success of music streaming services. Currently, many existing playlist continuation approaches rely on collaborative filtering methods to perform their recommendations. However, such methods will struggle to recommend songs that lack interaction data, an issue known as the cold-start problem. Current approaches to this challenge design complex mechanisms for extracting relational signals from sparse collaborative signals and integrating them into content representations. However, these approaches leave content representation learning out of scope and utilize frozen, pre-trained content models that may not be aligned with the distribution or format of a specific musical setting. Furthermore, even the musical state-of-the-art content modules are either (1) incompatible with the cold-start setting or (2) unable to effectively integrate cross-modal and relational signals. In this paper, we introduce LARP, a multi-modal cold-start playlist continuation model, to effectively overcome these limitations. LARP is a three-stage contrastive learning framework that integrates both multi-modal and relational signals into its learned representations. Our framework uses increasing stages of task-specific abstraction: within-track (language-audio) contrastive loss, track-track contrastive loss, and track-playlist contrastive loss. Experimental results on two publicly available datasets demonstrate the efficacy of LARP over uni-modal and multi-modal models for playlist continuation in a cold-start setting. Finally, this work pioneers the perspective of addressing cold-start recommendation via relational representation learning. Code and dataset are released at: https://github.com/Rsalganik1123/LARP/