activity
20222026
most citedTopology-aware Generalization of Decentralized SGD

7 citations · 11 across the 11 of their papers we have counts for

collaborators

11 papers

cs.MA2026

Distributed Team Orchestration via Supervisor Networks: Convergence, Optimality, and Resilience

Juntian Zhu, Guanpu Chen, Tongtian Zhu +3

In this paper, we study zero-sum potential team games with a supervisor network, where agents rely on supervisor-provided belief information rather than accurate common beliefs. Th…

cs.LG2026

Mobius Learning: Cyclic Depth Folding in Transformers

Tongtian Zhu

Transformer-based language models organize computation along an ordered depth axis, where shallow and deep blocks often develop distinct representational roles. We challenge the co…

cs.LG2025

DICE: Data Influence Cascade in Decentralized Learning

Tongtian Zhu, Wenhao Li, Can Wang +1

Decentralized learning offers a promising approach to crowdsource data consumptions and computational workloads across geographically distributed compute interconnected through pee…

cs.LG2025

On the Surprising Effectiveness of a Single Global Merging in Decentralized Learning

Tongtian Zhu, Tianyu Zhang, Mingze Wang +2

Decentralized learning provides a scalable alternative to parameter-server-based training, yet its performance is often hindered by limited peer-to-peer communication. In this pape…

math.AP2024

Lie Symmetry Net: Preserving Conservation Laws in Modelling Financial Market Dynamics via Differential Equations

Xuelian Jiang, Tongtian Zhu, Yingxiang Xu +3

This paper employs a novel Lie symmetries-based framework to model the intrinsic symmetries within financial market. Specifically, we introduce Lie symmetry net (LSN), which charac…

cs.LG2023

Adversarial Erasing with Pruned Elements: Towards Better Graph Lottery Ticket

Yuwen Wang, Shunyu Liu, Kaixuan Chen +5

Graph Lottery Ticket (GLT), a combination of core subgraph and sparse subnetwork, has been proposed to mitigate the computational cost of deep Graph Neural Networks (GNNs) on large…