Zongsheng Cao

Zongsheng Cao

Auto-generated profile, based on publicly available information

Zongsheng Cao

Chinese Academy of Sciences, Institute of Information Engineering, Beijing, China

Research Focus & Metrics

Academic Career Length

4Years (2023-Present)

(Calculated once Scilit publication data is synced: current year − year of first publication + 1)

Representative Publications

View All Publications
26 October 2023
Verified
Conference Paper
Open access
WNWenxin Ni
Wenxin Ni
QXQianqian Xu
Qianqian Xu
YJYangbangyan Jiang
Yangbangyan Jiang
ZCZongsheng Cao
Zongsheng Cao
XCXiaochun Cao
Xiaochun Cao
QHQingming Huang
Qingming Huang
Multi-modal entity alignment aims to identify entities that refer to the same concept in the real world across a plethora of multi-modal knowledge graphs (MMKGs). Most existing methods focus on reducing the embedding differences between multiple modalities while neglecting the following challenges: 1) cannot handle the heterogeneity across graphs, 2) suffer from the scarcity of pre-aligned data (a.k.a. initial seeds). To tackle these issues, we propose a Pseudo-Siamese Network for multi-modal Entity Alignment (PSNEA). It consists of two modules to extract various information and generate holistic embeddings. Specifically, the first module PSN is designed with two parallel branches to learn the representations for different MMKGs, thus effectively bridging the graph heterogeneity. On top of this, we introduce an Incremental Alignment Pool (IAP) to alleviate the scarcity of initial seeds by labeling likely alignment. IAP avoids error-prone by data swapping and sample re-weighting strategies. To the best of our knowledge, PSNEA is the first model that tackles graph heterogeneity and scarcity of initial seeds in one unified framework. The extensive experiments demonstrate that our model achieves the best performance on both cross-lingual and cross-graph datasets. The source code is available at https://github.com/idrfer/psn4ea.

24 August 2024
Verified
Conference Paper
Open access
ZCZongsheng Cao
Zongsheng Cao
Jing LiJing Li
Jing Li
ZWZigan Wang
Zigan Wang
JLJinliang Li
Jinliang Li
Graph Neural Networks (GNNs) have demonstrated powerful capabilities in reasoning within Knowledge Graphs (KGs), gathering increasing attention. Our idea stems from the observation that the prior work typically employs hand-designed or sample-designed paradigms in the process of message propagation, engaging a set of adjacent entities at each step of propagation. As a result, such methods struggle with the increasing number of entities involved as propagation steps extend. Moreover, they neglect the message interactions between adjacent entities and propagation relations in KG reasoning, leading to semantic inconsistency during the message aggregation phase. To address these issues, we introduce a novel knowledge graph embedding method through a diffusion process, termed DiffusionE. Specifically, we reformulate the message propagation in knowledge reasoning as a diffusion process, regarding the message semantics as the diffusion signal. In this sense, guided by semantic information, messages can be transmitted between nodes effectively and adaptively. Furthermore, the theoretical analysis suggests our method can leverage an optimal diffusivity for message propagation in the semantic interactions of KGs. It shows that DiffusionE effectively leverages message interactions between entities and propagation relations, ensuring semantic consistency in KG reasoning. Comprehensive experiments reveal that our method attains state-of-the-art performance compared to prior work on several well-established benchmarks.

13 May 2025 in ACM Transactions on Multimedia Computing, Communications, and Applications
Verified
Journal Article
Open access
ZCZongsheng Cao
Zongsheng Cao
QXQianqian Xu
Qianqian Xu
ZYZhiyong Yang
Zhiyong Yang
YHYuan He
Yuan He
XCXiaochun Cao
Xiaochun Cao
QHQingming Huang
Qingming Huang
Knowledge graphs have proven highly effective for learning representations of entities and relations, with hyper-relational knowledge graphs (HKGs) gaining increased attention due to their enhanced representation capabilities. Each fact in an HKG consists of a main triple supplemented by attribute-value qualifiers that provide additional contextual information. Due to the complexity of hyper-relations, HKGs typically contain complex geometric structures, such as hierarchical, ring, and chain structures, often mixed together. However, previous work mainly embeds HKGs into Euclidean space, limiting their ability to capture these complex geometric structures simultaneously. To address this challenge, we propose a novel model called Geometry Aware Hyper-relational Embedding (GAHE). Specifically, GAHE adopts a multi-curvature geometry-aware approach by modeling HKGs in Euclidean space (zero curvature), hyperbolic space (negative curvature), and hyperspherical space (positive curvature) in a unified framework. In this way, it can integrate space-invariant and space-specific features to accurately capture the diverse structures in HKGs. In addition, GAHE introduces a module termed hyper-relational subspace learning, which allocates multiple sub-relations for each hyper-relation. It enables the exploitation of abundant latent semantic interactions and facilitates the exploration of fine-grained semantics between attribute-value pairs and hyper-relations across multiple subspaces. Furthermore, we provide theoretical guarantees that GAHE is fully expressive and capable of modeling a wide range of semantic patterns for hyper-relations. Empirical evaluations demonstrate that GAHE achieves state-of-the-art results on both hyper-relational and binary-relational benchmarks.