Kangzheng Liu
Current Organizations / Institutes
The organizations/institutes from the scholar's latest article
Kangzheng Liu has a total of 3 co-authors. Here are the top co-authors by number of shared publications:
- Feng Zhao
Natural Language Processing and Knowledge Graph Lab, School of Computer Science and Technology, Huazhong University of Science and Technology, Wuhan, China
3 shared publications - Guandong Xu
The Education University of Hong Kong
3 shared publications - Yu Yang
The Education University of Hong Kong
3 shared publications
Latest Publications
- Open Access
- 1 July 2026
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Transactions on Knowledge and Data Engineering
- Vol. 38 (7) , 4170-4184
Cog-RMH: Cognition-Based Recalling Multiview History for Event Forecasting in Temporal Knowledge Graph
- 1 July 2026
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Transactions on Knowledge and Data Engineering
- Vol. 38 (7) , 4170-4184
Open AccessCog-RMH: Cognition-Based Recalling Multiview History for Event Forecasting in Temporal Knowledge Graph
- 18 May 2026
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Transactions on Knowledge and Data Engineering
- Vol. 38 (8) , 5173-5186
Hyperbolic Dual-Attentive Evolution of Heterogeneous Deep Hierarchy for Temporal Knowledge Graph Reasoning
Temporal knowledge graphs (TKGs) are dynamic heterogeneous multirelational graphs whose topological structures evolve over time. Reasoning over TKGs involves forecasting future events based on complex historical structural information. Efficiently modeling TKGs' structural interactions at each timestamp and the evolution timelines is crucial for later reasoning. However, previous approaches simply learned shallow correlations over TKGs but ignored the heterogeneous deep hierarchy for reasoning. Furthermore, previous evolution modeling techniques for TKGs merely capture the general trends of a given chronological sequence, forgetting the fine-grained event distributions in history. To this end, we propose $\bf {H^{2}}$-$\bf {Evo}$, which learns deep $\bf{\underline{H}}$ierarchy of intra-time $\bf{\underline{H}}$eterogeneous interactions and hyperbolic $\bf{\underline{Evo}}$lution of inter-time hierarchical dependencies. Specifically, to learn the heterogeneous deep hierarchy in TKGs, we design a heterogeneous hyperbolic message-passing framework with inter-hierarchy perception, intra-hierarchy correlation, and multilayer propagation. It effectively captures the heterogeneous and hierarchical structures in TKGs. To properly capture the temporal evolution of hierarchical structures in TKGs, we devise a novel hyperbolic dual-attentive mechanism, which jointly learns the fine-grained time-varying evolution patterns of TKGs' hierarchical structure and its period-varying evolving trends for later reasoning. Extensive experiments on four public benchmarks demonstrate that $\bf {H^{2}}$-$\bf {Evo}$ has achieved state-of-the-art reasoning performance.
- 18 May 2026
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Transactions on Knowledge and Data Engineering
- Vol. 38 (8) , 5173-5186
Hyperbolic Dual-Attentive Evolution of Heterogeneous Deep Hierarchy for Temporal Knowledge Graph Reasoning
Temporal knowledge graphs (TKGs) are dynamic heterogeneous multirelational graphs whose topological structures evolve over time. Reasoning over TKGs involves forecasting future events based on complex historical structural information. Efficiently modeling TKGs' structural interactions at each timestamp and the evolution timelines is crucial for later reasoning. However, previous approaches simply learned shallow correlations over TKGs but ignored the heterogeneous deep hierarchy for reasoning. Furthermore, previous evolution modeling techniques for TKGs merely capture the general trends of a given chronological sequence, forgetting the fine-grained event distributions in history. To this end, we propose $\bf {H^{2}}$-$\bf {Evo}$, which learns deep $\bf{\underline{H}}$ierarchy of intra-time $\bf{\underline{H}}$eterogeneous interactions and hyperbolic $\bf{\underline{Evo}}$lution of inter-time hierarchical dependencies. Specifically, to learn the heterogeneous deep hierarchy in TKGs, we design a heterogeneous hyperbolic message-passing framework with inter-hierarchy perception, intra-hierarchy correlation, and multilayer propagation. It effectively captures the heterogeneous and hierarchical structures in TKGs. To properly capture the temporal evolution of hierarchical structures in TKGs, we devise a novel hyperbolic dual-attentive mechanism, which jointly learns the fine-grained time-varying evolution patterns of TKGs' hierarchical structure and its period-varying evolving trends for later reasoning. Extensive experiments on four public benchmarks demonstrate that $\bf {H^{2}}$-$\bf {Evo}$ has achieved state-of-the-art reasoning performance.
- Open Access
- 28 October 2024
- Published by Association for Computing Machinery (ACM)
- p. 8247-8256
DySarl: Dynamic Structure-Aware Representation Learning for Multimodal Knowledge Graph Reasoning
Multimodal knowledge graph (MKG) reasoning has attracted significant attention since impressive performance has been achieved by adding multimodal auxiliary information (i.e., texts and images) to the entities of traditional KGs. However, existing studies heavily rely on path-based methods for learning structural modality, failing to capture the complex structural interactions among multimodal entities beyond the reasoning path. In addition, existing studies have largely ignored the dynamic impact of different multimodal features on different decision facts for reasoning, which utilize asymmetric coattention to independently learn the static interplay between different modalities without dynamically joining the reasoning process. We propose a novel Dynamic Structure-aware representation learning method, namely DySarl, to overcome this problem and significantly improve the MKG reasoning performance. Specifically, we devise a dual-space multihop structural learning module in DySarl, aggregating the multihop structural features of multimodal entities via a novel message-passing mechanism. It integrates the message paradigms in Euclidean and hyperbolic spaces, effectively preserving the neighborhood information beyond the limited multimodal query paths. Furthermore, DySarl has an interactive symmetric attention module to explicitly learn the dynamic impacts of unimodal attention senders and multimodal attention targets on decision facts through a newly designed symmetric attention component and fact-specific gated attention unit, equipping DySarl with the dynamic associations between the multimodal feature learning and later reasoning. Extensive experiments show that DySarl achieves significantly improved reasoning performance on two public MKG datasets compared with that of the state-of-the-art baselines. Source codes are available at https://github.com/HUSTNLP-codes/DySarl.
- 28 October 2024
- Published by Association for Computing Machinery (ACM)
- p. 8247-8256
Open AccessDySarl: Dynamic Structure-Aware Representation Learning for Multimodal Knowledge Graph Reasoning
Multimodal knowledge graph (MKG) reasoning has attracted significant attention since impressive performance has been achieved by adding multimodal auxiliary information (i.e., texts and images) to the entities of traditional KGs. However, existing studies heavily rely on path-based methods for learning structural modality, failing to capture the complex structural interactions among multimodal entities beyond the reasoning path. In addition, existing studies have largely ignored the dynamic impact of different multimodal features on different decision facts for reasoning, which utilize asymmetric coattention to independently learn the static interplay between different modalities without dynamically joining the reasoning process. We propose a novel Dynamic Structure-aware representation learning method, namely DySarl, to overcome this problem and significantly improve the MKG reasoning performance. Specifically, we devise a dual-space multihop structural learning module in DySarl, aggregating the multihop structural features of multimodal entities via a novel message-passing mechanism. It integrates the message paradigms in Euclidean and hyperbolic spaces, effectively preserving the neighborhood information beyond the limited multimodal query paths. Furthermore, DySarl has an interactive symmetric attention module to explicitly learn the dynamic impacts of unimodal attention senders and multimodal attention targets on decision facts through a newly designed symmetric attention component and fact-specific gated attention unit, equipping DySarl with the dynamic associations between the multimodal feature learning and later reasoning. Extensive experiments show that DySarl achieves significantly improved reasoning performance on two public MKG datasets compared with that of the state-of-the-art baselines. Source codes are available at https://github.com/HUSTNLP-codes/DySarl.