Liangsi Lu

Liangsi Lu

Auto-generated profile, based on publicly available information

Liangsi Lu

Guangdong University of Technology, Guangzhou, China

Research Focus & Metrics

Academic Career Length

2Years (2025-Present)

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

Representative Publications

View All Publications
20 August 2025 in Neurocomputing
Verified
Journal Article
Closed access
RHRuixin He
Ruixin He
YSYang Shi
Yang Shi
MHMingxuan Huang
Mingxuan Huang
LLLiangsi Lu
Liangsi Lu
ZDZhaorong Dai
Zhaorong Dai
ZXZhuoming Xie
Zhuoming Xie

12 April 2026
Verified
Conference Paper
Open access
LLLiangsi Lu
Liangsi Lu
JWJingchao Wang
Jingchao Wang
ZDZhaorong Dai
Zhaorong Dai
HLHanqian Liu
Hanqian Liu
YSYang Shi
Yang Shi
Liquid Time-Constant networks (LTCs), a type of continuous-time graph neural network, excel at modeling irregularly-sampled dynamics but are fundamentally confined to Euclidean space. This limitation introduces significant geometric distortion when representing real-world graphs with inherent non-Euclidean structures (e.g., hierarchies and cycles), degrading representation quality. To overcome this limitation, we introduce the Riemannian Liquid Spatio-Temporal Graph Network (RLSTG), a framework that unifies continuous-time liquid dynamics with the geometric inductive biases of Riemannian manifolds. RLSTG models graph evolution through an Ordinary Differential Equation (ODE) formulated directly on a curved manifold, enabling it to faithfully capture the intrinsic geometry of both structurally static and dynamic spatio-temporal graphs. Moreover, we provide rigorous theoretical guarantees for RLSTG, extending stability theorems of LTCs to the Riemannian domain and quantifying its expressive power via state trajectory analysis. Extensive experiments on real-world benchmarks demonstrate that, by combining advanced temporal dynamics with a Riemannian spatial representation, RLSTG achieves superior performance on graphs with complex structures. Project Page: https://rlstg.github.io

5 September 2026 in ACM Transactions on Knowledge Discovery From Data
Verified
Journal Article
Open access
YSYang Shi
Yang Shi
JWJingchao Wang
Jingchao Wang
LLLiangsi Lu
Liangsi Lu
HHHaiying Huang
Haiying Huang
SXSutong Xiao
Sutong Xiao
BXBoyan Xu
Boyan Xu
Non-Euclidean spaces inherently enable high-fidelity embeddings for hierarchical and cyclical data due to their geometric properties. Existing approaches unify hyperbolic and spherical embeddings within the framework of constant curvature spaces. However, current methods for Lipschitz regularization remain limited to non-positive curvature geometries, such as hyperbolic and Euclidean spaces, and cannot be naturally extended to the general constant curvature setting. In this article, we present a rigorous Lipschitz analysis for constant curvature graph convolutional networks ( \(\kappa\) -GCNs) and enhance their robustness through Lipschitz regularization. We derive upper bounds for the Lipschitz constants across constant curvature spaces, thereby standardizing the Lipschitz limits of the \(\kappa\) -stereographic model. Furthermore, we incorporate these bounds into a regularization framework for \(\kappa\) -GCNs to improve stability and robustness. Experimental results demonstrate that the proposed regularization method often strengthens the robustness of \(\kappa\) -GCNs across various curvature regimes, particularly under Gaussian feature noise.

8 August 2026
Verified
Conference Paper
Open access
YSYang Shi
Yang Shi
LCLixian Chen
Lixian Chen
JWJingchao Wang
Jingchao Wang
MGMinzhe Guo
Minzhe Guo
MHMingxuan Huang
Mingxuan Huang
LLLiangsi Lu
Liangsi Lu
Message-passing graph neural networks (MP-GNNs) are widely used for learning on relational data. However, their performance drops on tasks requiring long-range interactions due to over-squash­ing, where exponential information compression overwhelms fixed-width embeddings. While existing analyses often attribute this to geometric bottlenecks under linear diffusion assumptions, thresholded nonlinearities in GNNs motivate a load-release view akin to Abelian sandpiles. Using the discrete sandpile model as a structural proxy, we show that graph bottlenecks force large stabilization cost, effectively creating zones of high transport congestion. We characterize stabilization-invariant equivalence classes induced by the reduced Laplacian and derive cut-based lower bounds linking bottlenecks to unavoidable stabilization effort. The resulting theory is discrete, whereas our implementation is a continuous vector-valued surrogate. The theory identifies the relevant design factors, namely capacity and cut size. Guided by these insights, we propose a differentiable Sandpile Stabilization Layer (SSL) and congestion-aware objectives designed to redistribute excess load and manage stabilization costs. Experiments on long-range benchmarks, together with congestion and collision diagnostics, show that targeting sandpile-identified bottlenecks mitigates representation collapse and improves over standard baselines. Project Page: https://sandpile-gnn.github.io/