Publications (12)
Federated Skewed Label Learning with Logits Fusion
Yuwei Wang, Runhan Li, Hao Tan +5
Federated learning (FL) aims to collaboratively train a shared model across multiple clients without transmitting their local data. Data heterogeneity is a critical challenge in re…
Topology-engineered orbital Hall effect in two-dimensional ferromagnets
Zhiqi Chen, Runhan Li, Yingxi Bai +7
Recent advances in manipulation of orbital angular momentum (OAM) within the paradigm of orbitronics present a promising avenue for the design of future electronic devices. In this…
Ferroelectric higher-order topological insulator in two dimensions
Ning Mao, Runhan Li, Xiaorong Zou +3
The interplay between ferroelectricity and band topology can give rise to a wide range of both fundamental and applied research. Here, we map out the emergence of nontrivial corner…
Tackling Noisy Clients in Federated Learning with End-to-end Label Correction
Xuefeng Jiang, Sheng Sun, Jia Li +6
Recently, federated learning (FL) has achieved wide successes for diverse privacy-sensitive applications without sacrificing the sensitive private information of clients. However,…
Chiral Weyl-Kondo semimetals and hexagonal heavy fermion systems
Kuan-Sen Lin, Yuan Fang, Henrique Fabrelli +7
Strong correlation, in concert with symmetry and topology, engenders novel gapless phases of matter, though only a tip of the iceberg has been seen. An exemplary framework is provi…
Tight-binding and density-functional study of the Raman tensor in two-dimensional massive Dirac fermion systems
Selçuk Parlak, Abhishek Kumar, Runhan Li +2
Recently, two unusual features were theoretically predicted for the Raman response of out-of-plane phonons in magnetic two-dimensional materials hosting massive Dirac fermions. Fir…
Altermagnetism from a Cu-Fe Lieb Lattice in FeSe/Cuprate Heterostructures
Ying Li, Augustin Davignon, Peng Rao +4
The paper proposes that FeSe/cuprate heterostructures with a twisted Cu-Fe arrangement can host altermagnetism, producing spin‑split electronic bands without net magnetization, and…
Knowledge Distillation in Federated Edge Learning: A Survey
Zhiyuan Wu, Sheng Sun, Yuwei Wang +4
The increasing demand for intelligent services and privacy protection of mobile and Internet of Things (IoT) devices motivates the wide application of Federated Edge Learning (FEL)…
Orbital shift-induced boundary obstructed topological materials with a large energy gap
Ning Mao, Runhan Li, Ying Dai +3
We propose boundary obstructed topological phases caused by Wannier orbital shift between ordinary atomic sites, which, however, cannot be indicated by symmetry eigenvalues at high…
SMES: Towards Scalable Multi-Task Recommendation via Expert Sparsity
Yukun Zhang, Si Dong, Xu Wang +11
Industrial recommender systems typically rely on multi-task learning to estimate diverse user feedback signals and aggregate them for ranking. Recent advances in model scaling have…
Managed Geo-Distributed Feature Store: Architecture and System Design
Anya Li, Bhala Ranganathan, Feng Pan +6
Companies are using machine learning to solve real-world problems and are developing hundreds to thousands of features in the process. They are building feature engineering pipelin…
Doubled Quantum Spin Hall Effect with High-Spin Chern Number in -Antimonene and -Bismuthene
Yingxi Bai, Linke Cai, Ning Mao +4
The discovery of quantum spin Hall effect has ignited the field of topological physics with vast variety of exotic properties. Here, we present the emergence of doubled quantum spi…