Jing Du
Current Organizations / Institutes
The organizations/institutes from the scholar's latest article
Research Subjects
Jing Du has a total of 39 co-authors. Here are the top co-authors by number of shared publications:
- Lina Yao
University of New South Wales, Sydney, Australia
4 shared publications - Zesheng Ye
School of Computer Science and Engineering, University of New South Wales, Sydney, Kensington 2052, Australia
4 shared publications - Bin Guo
Northwestern Polytechnical University
3 shared publications - Zhiwen Yu
Harbin Engineering University
3 shared publications - Flora Dilys Salim
University of New South Wales, Sydney, Australia
2 shared publications - Jia Wu
Macquarie University, Sydney, Australia
2 shared publications
Latest Publications
- 24 September 2026
- Published by Wiley in International Journal of Eating Disorders
Toward Zeitgeist‐Aware Multimodal ( ZAM ) Datasets of Pro‐Eating Disorder Short‐Form Videos
Objective: Reliable identification of pro‐eating disorder (pro‐ED) content online suffers from two pervasive problems: (1) existing methods predominantly rely on text‐based signals, failing to capture the inherently multimodal nature of multimedia content; and (2) these methods struggle to keep pace with the rapid evolution of references, memes, terminology, and contextual cues that underlie this content. Together, these limitations point to a gap: the absence of expert‐annotated reference standards capable of supporting real‐time research and robust multimodal detection model training for pro‐ED content on short‐form video (SFV) platforms. Method: To address this, we propose the development of zeitgeist‐aware multimodal (ZAM) datasets, which are continuously curated collections of annotated multimodal pro‐ED content with inclusion criteria that evolve alongside the memetic zeitgeist: the variable essence of what is considered pro‐ED as new media and references come into the cultural zeitgeist and are absorbed and interpreted in online spaces. Results: We present a rationale for such datasets, outline approaches for their curation, and describe our progress toward that end. Discussion: This ZAM curation method may benefit stakeholders across several fields who are interested in how pro‐ED sentiment is encoded and transmitted through SFV content across time, including for the purpose of responsive moderation efforts.
- 24 September 2026
- Published by Wiley in International Journal of Eating Disorders
Toward Zeitgeist‐Aware Multimodal ( ZAM ) Datasets of Pro‐Eating Disorder Short‐Form Videos
Objective: Reliable identification of pro‐eating disorder (pro‐ED) content online suffers from two pervasive problems: (1) existing methods predominantly rely on text‐based signals, failing to capture the inherently multimodal nature of multimedia content; and (2) these methods struggle to keep pace with the rapid evolution of references, memes, terminology, and contextual cues that underlie this content. Together, these limitations point to a gap: the absence of expert‐annotated reference standards capable of supporting real‐time research and robust multimodal detection model training for pro‐ED content on short‐form video (SFV) platforms. Method: To address this, we propose the development of zeitgeist‐aware multimodal (ZAM) datasets, which are continuously curated collections of annotated multimodal pro‐ED content with inclusion criteria that evolve alongside the memetic zeitgeist: the variable essence of what is considered pro‐ED as new media and references come into the cultural zeitgeist and are absorbed and interpreted in online spaces. Results: We present a rationale for such datasets, outline approaches for their curation, and describe our progress toward that end. Discussion: This ZAM curation method may benefit stakeholders across several fields who are interested in how pro‐ED sentiment is encoded and transmitted through SFV content across time, including for the purpose of responsive moderation efforts.
- Open Access
- 3 November 2025
- Published by Association for Computing Machinery (ACM)
- p. 646-655
A Probabilistic Framework for Imputing Genetic Distances in Spatiotemporal Pathogen Models
- 3 November 2025
- Published by Association for Computing Machinery (ACM)
- p. 646-655
Open AccessA Probabilistic Framework for Imputing Genetic Distances in Spatiotemporal Pathogen Models
- Open Access
- 27 October 2025
- Published by Association for Computing Machinery (ACM)
- p. 2556-2565
Joint Test-time Adaptation with Refined Pseudo-labels and Latent Score Matching
- 27 October 2025
- Published by Association for Computing Machinery (ACM)
- p. 2556-2565
Open AccessJoint Test-time Adaptation with Refined Pseudo-labels and Latent Score Matching
- 29 August 2025
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Transactions on Artificial Intelligence
- Vol. 7 (3) , 1455-1465
Community-Structure Enhanced Brain Graph Mining
Brain neuroimaging technology has become increasingly valuable in diagnosing brain disorders, with brain graphs constructed from neuroimaging data providing critical insights into the properties of the human brain. Although functional connectivity-based brain graph construction methods have proven effective in diagnostic tasks, they often fail to incorporate prior knowledge from neuroscience, such as the existence of distinct functional modules that govern various aspects of brain function. In this work, we define these functional modules as different communities of brain graphs and propose a community-structure enhanced brain graph mining framework. Specifically, we design community-constrained node identity vectors as part of node features to adaptively capture the community structure in the process of model optimization toward downstream tasks. Importantly, since common community variations are identified across subjects with the same disorder, these identity vectors are shared among all subjects within a specific brain disorder diagnostic task. Additionally, to improve the interpretability of our model, we generate attention scores solely from the identity vectors, enabling the model to constantly focus on specific brain regions and communities associated with a particular disorder. Finally, we conduct extensive experiments on three real-world datasets. The analysis results demonstrate the effectiveness of our approach and provide valuable insights for identifying biomarkers associated with corresponding brain disorders.
- 29 August 2025
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Transactions on Artificial Intelligence
- Vol. 7 (3) , 1455-1465
Community-Structure Enhanced Brain Graph Mining
Brain neuroimaging technology has become increasingly valuable in diagnosing brain disorders, with brain graphs constructed from neuroimaging data providing critical insights into the properties of the human brain. Although functional connectivity-based brain graph construction methods have proven effective in diagnostic tasks, they often fail to incorporate prior knowledge from neuroscience, such as the existence of distinct functional modules that govern various aspects of brain function. In this work, we define these functional modules as different communities of brain graphs and propose a community-structure enhanced brain graph mining framework. Specifically, we design community-constrained node identity vectors as part of node features to adaptively capture the community structure in the process of model optimization toward downstream tasks. Importantly, since common community variations are identified across subjects with the same disorder, these identity vectors are shared among all subjects within a specific brain disorder diagnostic task. Additionally, to improve the interpretability of our model, we generate attention scores solely from the identity vectors, enabling the model to constantly focus on specific brain regions and communities associated with a particular disorder. Finally, we conduct extensive experiments on three real-world datasets. The analysis results demonstrate the effectiveness of our approach and provide valuable insights for identifying biomarkers associated with corresponding brain disorders.
- Open Access
- 8 May 2025
- Published by Association for Computing Machinery (ACM)
- p. 1184-1188
Enhanced Social Event Detection through Dynamically Weighted Meta-Paths Modeling
- 8 May 2025
- Published by Association for Computing Machinery (ACM)
- p. 1184-1188
Open AccessEnhanced Social Event Detection through Dynamically Weighted Meta-Paths Modeling
- Open Access
- 10 July 2024
- Published by Association for Computing Machinery (ACM)
- p. 2091-2101
Identifiability of Cross-Domain Recommendation via Causal Subspace Disentanglement
Cross-Domain Recommendation~(CDR) seeks to enable effective knowledge transfer across domains. Most existing works rely on either representation alignment or transformation bridges, but they come with shortcomings regarding identifiability of domain-shared and domain-specific latent factors. Specifically, while CDR describes user representations as a joint distribution over two domains, these methods fail to account for its joint identifiability as they primarily fixate on the marginal distribution within a particular domain. Such a failure may overlook the conditionality between two domains and how it contributes to latent factor disentanglement, leading to negative transfer when domains are weakly correlated. In this study, we explore what should and should not be transferred in cross-domain user representations from a causality perspective. We propose a Hierarchical causal subspace disentanglement approach to explore the Joint IDentifiability of cross-domain joint distribution, termed HJID, to preserve domain-specific behaviors from domain-shared factors. HJID abides by the feature hierarchy and divides user representations into generic shallow subspace and domain-oriented deep subspaces. We first encode the generic pattern in the shallow subspace by minimizing the Maximum Mean Discrepancy of initial layer activation. Then, to dissect how domain-oriented latent factors are encoded in deeper layers activation, we construct a cross-domain causality-based data generation graph, which identifies cross-domain consistent and domain-specific components, adhering to the Minimal Change principle. This allows HJID to maintain stability whilst discovering unique factors for different domains, all within a generative framework of invertible transformations that guarantee the joint identifiability. With experiments on real-world datasets, we show that HJID outperforms SOTA methods on both strong- and weak-correlation CDR tasks.
- 10 July 2024
- Published by Association for Computing Machinery (ACM)
- p. 2091-2101
Open AccessIdentifiability of Cross-Domain Recommendation via Causal Subspace Disentanglement
Cross-Domain Recommendation~(CDR) seeks to enable effective knowledge transfer across domains. Most existing works rely on either representation alignment or transformation bridges, but they come with shortcomings regarding identifiability of domain-shared and domain-specific latent factors. Specifically, while CDR describes user representations as a joint distribution over two domains, these methods fail to account for its joint identifiability as they primarily fixate on the marginal distribution within a particular domain. Such a failure may overlook the conditionality between two domains and how it contributes to latent factor disentanglement, leading to negative transfer when domains are weakly correlated. In this study, we explore what should and should not be transferred in cross-domain user representations from a causality perspective. We propose a Hierarchical causal subspace disentanglement approach to explore the Joint IDentifiability of cross-domain joint distribution, termed HJID, to preserve domain-specific behaviors from domain-shared factors. HJID abides by the feature hierarchy and divides user representations into generic shallow subspace and domain-oriented deep subspaces. We first encode the generic pattern in the shallow subspace by minimizing the Maximum Mean Discrepancy of initial layer activation. Then, to dissect how domain-oriented latent factors are encoded in deeper layers activation, we construct a cross-domain causality-based data generation graph, which identifies cross-domain consistent and domain-specific components, adhering to the Minimal Change principle. This allows HJID to maintain stability whilst discovering unique factors for different domains, all within a generative framework of invertible transformations that guarantee the joint identifiability. With experiments on real-world datasets, we show that HJID outperforms SOTA methods on both strong- and weak-correlation CDR tasks.
- Open Access
- 21 October 2023
- Published by Association for Computing Machinery (ACM)
- p. 5123-5127
NP-SSL: A Modular and Extensible Self-supervised Learning Library with Neural Processes
Neural Processes (NPs) are a family of supervised density estimators devoted to probabilistic function approximation with meta-learning. Despite extensive research on the subject, the absence of a unified framework for NPs leads to varied architectural solutions across diverse studies. This non-consensus poses challenges to reproducing and benchmarking different NPs. Moreover, existing codebases mainly prioritize generative density estimation, yet rarely consider expanding the capability of NPs to self-supervised representation learning, which however has gained growing importance in data mining applications. To this end, we present NP-SSL, a modular and configurable framework with built-in support, requiring minimal effort to 1) implement classical NPs architectures; 2) customize specific components; 3) integrate hybrid training scheme (e.g., contrastive); and 4) extend NPs to act as a self-supervised learning toolkit, producing latent representations of data, and facilitating diverse downstream predictive tasks. To illustrate, we discuss a case study that applies NP-SSL to model time-series data. We interpret that NP-SSL can handle different predictive tasks such as imputation and forecasting, by a simple switch in data samplings, without significant change to the underlying structure. We hope this study can reduce the workload of future research on leveraging NPs to tackle more a broader range of real-world data mining applications. Code and documentation are at https://github.com/zyecs/NP-SSL.
- 21 October 2023
- Published by Association for Computing Machinery (ACM)
- p. 5123-5127
Open AccessNP-SSL: A Modular and Extensible Self-supervised Learning Library with Neural Processes
Neural Processes (NPs) are a family of supervised density estimators devoted to probabilistic function approximation with meta-learning. Despite extensive research on the subject, the absence of a unified framework for NPs leads to varied architectural solutions across diverse studies. This non-consensus poses challenges to reproducing and benchmarking different NPs. Moreover, existing codebases mainly prioritize generative density estimation, yet rarely consider expanding the capability of NPs to self-supervised representation learning, which however has gained growing importance in data mining applications. To this end, we present NP-SSL, a modular and configurable framework with built-in support, requiring minimal effort to 1) implement classical NPs architectures; 2) customize specific components; 3) integrate hybrid training scheme (e.g., contrastive); and 4) extend NPs to act as a self-supervised learning toolkit, producing latent representations of data, and facilitating diverse downstream predictive tasks. To illustrate, we discuss a case study that applies NP-SSL to model time-series data. We interpret that NP-SSL can handle different predictive tasks such as imputation and forecasting, by a simple switch in data samplings, without significant change to the underlying structure. We hope this study can reduce the workload of future research on leveraging NPs to tackle more a broader range of real-world data mining applications. Code and documentation are at https://github.com/zyecs/NP-SSL.
- Open Access
- 27 February 2023
- Published by Association for Computing Machinery (ACM)
- p. 481-489
IDNP: Interest Dynamics Modeling Using Generative Neural Processes for Sequential Recommendation
Recent sequential recommendation models rely increasingly on consecutive short-term user-item interaction sequences to model user interests. These approaches have, however, raised concerns about both short- and long-term interests. (1) short-term: interaction sequences may not result from a monolithic interest, but rather from several intertwined interests, even within a short period of time, resulting in their failures to model skip behaviors; (2) long-term: interaction sequences are primarily observed sparsely at discrete intervals, other than consecutively over the long run. This renders difficulty in inferring long-term interests, since only discrete interest representations can be derived, without taking into account interest dynamics across sequences. In this study, we address these concerns by learning (1) multi-scale representations of short-term interests; and (2) dynamics-aware representations of long-term interests. To this end, we present an Interest Dynamics modeling framework using generative Neural Processes, coined IDNP, to model user interests from a functional perspective. IDNP learns a global interest function family to define each user's long-term interest as a function instantiation, manifesting interest dynamics through function continuity. Specifically, IDNP first encodes each user's short-term interactions into multi-scale representations, which are then summarized as user context. By combining latent global interest with user context, IDNP then reconstructs long-term user interest functions and predicts interactions at upcoming query timestep. Moreover, IDNP can model such interest functions even when interaction sequences are limited and non-consecutive. Extensive experiments on four real-world datasets demonstrate that our model outperforms the state-of-the-art on various evaluation metrics.
- 27 February 2023
- Published by Association for Computing Machinery (ACM)
- p. 481-489
Open AccessIDNP: Interest Dynamics Modeling Using Generative Neural Processes for Sequential Recommendation
Recent sequential recommendation models rely increasingly on consecutive short-term user-item interaction sequences to model user interests. These approaches have, however, raised concerns about both short- and long-term interests. (1) short-term: interaction sequences may not result from a monolithic interest, but rather from several intertwined interests, even within a short period of time, resulting in their failures to model skip behaviors; (2) long-term: interaction sequences are primarily observed sparsely at discrete intervals, other than consecutively over the long run. This renders difficulty in inferring long-term interests, since only discrete interest representations can be derived, without taking into account interest dynamics across sequences. In this study, we address these concerns by learning (1) multi-scale representations of short-term interests; and (2) dynamics-aware representations of long-term interests. To this end, we present an Interest Dynamics modeling framework using generative Neural Processes, coined IDNP, to model user interests from a functional perspective. IDNP learns a global interest function family to define each user's long-term interest as a function instantiation, manifesting interest dynamics through function continuity. Specifically, IDNP first encodes each user's short-term interactions into multi-scale representations, which are then summarized as user context. By combining latent global interest with user context, IDNP then reconstructs long-term user interest functions and predicts interactions at upcoming query timestep. Moreover, IDNP can model such interest functions even when interaction sequences are limited and non-consecutive. Extensive experiments on four real-world datasets demonstrate that our model outperforms the state-of-the-art on various evaluation metrics.
- Open Access
- 6 July 2022
- Published by Association for Computing Machinery (ACM)
- p. 1927-1932
Socially-aware Dual Contrastive Learning for Cold-Start Recommendation
Social recommendation with Graph Neural Networks(GNNs) learns to represent cold users by fusing user-user social relations with user-item interactions, thereby alleviating the cold-start problem associated with recommender systems. Despite being well adapted to social relations and user-item interactions, these supervised models are still susceptible to popularity bias. Contrastive learning helps resolve this dilemma by identifying the properties that distinguish positive from negative samples. In its previous combinations with recommender systems, social relationships and cold-start cases in this context are not considered. Also, they primarily focus on collaborative features between users and items, leaving the similarity between items under-utilized. In this work, we propose socially-aware dual contrastive learning for cold-start recommendation, where cold users can be modeled in the same way as warm users. To take full advantage of social relations, we create dynamic node embeddings for each user by aggregating information from different neighbors according to each different query item, in the form of user-item pairs. We further design a dual-branch self-supervised contrastive objective to account for user-item collaborative features and item-item mutual information, respectively. On one hand, our framework eliminates popularity bias with proper negative sampling in contrastive learning, without extra ground-truth supervision. On the other hand, we extend previous contrastive learning methods to provide a solution to cold-start problem with social relations included. Extensive experiments on two real-world social recommendation datasets demonstrate its effectiveness.
- 6 July 2022
- Published by Association for Computing Machinery (ACM)
- p. 1927-1932
Open AccessSocially-aware Dual Contrastive Learning for Cold-Start Recommendation
Social recommendation with Graph Neural Networks(GNNs) learns to represent cold users by fusing user-user social relations with user-item interactions, thereby alleviating the cold-start problem associated with recommender systems. Despite being well adapted to social relations and user-item interactions, these supervised models are still susceptible to popularity bias. Contrastive learning helps resolve this dilemma by identifying the properties that distinguish positive from negative samples. In its previous combinations with recommender systems, social relationships and cold-start cases in this context are not considered. Also, they primarily focus on collaborative features between users and items, leaving the similarity between items under-utilized. In this work, we propose socially-aware dual contrastive learning for cold-start recommendation, where cold users can be modeled in the same way as warm users. To take full advantage of social relations, we create dynamic node embeddings for each user by aggregating information from different neighbors according to each different query item, in the form of user-item pairs. We further design a dual-branch self-supervised contrastive objective to account for user-item collaborative features and item-item mutual information, respectively. On one hand, our framework eliminates popularity bias with proper negative sampling in contrastive learning, without extra ground-truth supervision. On the other hand, we extend previous contrastive learning methods to provide a solution to cold-start problem with social relations included. Extensive experiments on two real-world social recommendation datasets demonstrate its effectiveness.