arXiv subjects

Cheng Ji

Publications and source records attributed to Cheng Ji.

44 records · Page 3Linked to original sources

arXiv2021

HADFL: Heterogeneity-aware Decentralized Federated Learning Framework

Federated learning (FL) supports training models on geographically distributed devices. However, traditional FL systems adopt a centralized synchronous strategy, putting high communication pressure and model generalization challenge. Existing optimizations on FL either fail to speedup training on heterogeneous devices or suffer from poor communication efficiency. In this paper, we propose HADFL, a framework that supports decentralized asynchronous training on heterogeneous devices. The devices train model locally with heterogeneity-aware local steps using local data. In each aggregation cycle, they are selected based on probability to perform model synchronization and aggregation. Compared with the traditional FL system, HADFL can relieve the central server's communication pressure, efficiently utilize heterogeneous computing power, and can achieve a maximum speedup of 3.15x than decentralized-FedAvg and 4.68x than Pytorch distributed training scheme, respectively, with almost no loss of convergence accuracy.

cs.LG↗

arXiv2021

Abnormal behavior of Cs polyoxides under high pressure

High-pressure can transform the structures and compositions of materials either by changing the relative strengths of bonds or by altering the oxidation states of atoms. Both effects cause unconventional compositions in novel compounds that have been synthesized or predicted in large numbers in the past decade. What naturally follows is a question: what if pressure imposes strong effects on both chemical bonds and atomic orbitals in the same material. A systematic DFT and crystal structure search study of Cs polyoxides under high pressure shows a striking transition of chemistry due to the activation of the Cs 5p core electrons. Opposing to the general trend of polyoxides, the O-O bonds disappear in Cs polyoxides and Cs and O atoms form molecules and monolayers with strong Cs-O covalent bonds. Especially, the abnormal transition of structure and chemical bonds happens to CsO, a solid peroxide that is stable under ambient pressure, at 221 GPa, which can be accessed by current high-pressure experiments.

cond-mat.mtrl-sci↗

arXiv2021

ACE-HGNN: Adaptive Curvature Exploration Hyperbolic Graph Neural Network

Graph Neural Networks (GNNs) have been widely studied in various graph data mining tasks. Most existingGNNs embed graph data into Euclidean space and thus are less effective to capture the ubiquitous hierarchical structures in real-world networks. Hyperbolic Graph Neural Networks(HGNNs) extend GNNs to hyperbolic space and thus are more effective to capture the hierarchical structures of graphs in node representation learning. In hyperbolic geometry, the graph hierarchical structure can be reflected by the curvatures of the hyperbolic space, and different curvatures can model different hierarchical structures of a graph. However, most existing HGNNs manually set the curvature to a fixed value for simplicity, which achieves a suboptimal performance of graph learning due to the complex and diverse hierarchical structures of the graphs. To resolve this problem, we propose an Adaptive Curvature Exploration Hyperbolic Graph NeuralNetwork named ACE-HGNN to adaptively learn the optimal curvature according to the input graph and downstream tasks. Specifically, ACE-HGNN exploits a multi-agent reinforcement learning framework and contains two agents, ACE-Agent andHGNN-Agent for learning the curvature and node representations, respectively. The two agents are updated by a NashQ-leaning algorithm collaboratively, seeking the optimal hyperbolic space indexed by the curvature. Extensive experiments on multiple real-world graph datasets demonstrate a significant and consistent performance improvement in model quality with competitive performance and good generalization ability.

cs.LG↗

arXiv2021

RWNE: A Scalable Random-Walk-Based Network Embedding Framework with Personalized Higher-Order Proximity Preserved

Higher-order proximity preserved network embedding has attracted increasing attention. In particular, due to the superior scalability, random-walk-based network embedding has also been well developed, which could efficiently explore higher-order neighborhoods via multi-hop random walks. However, despite the success of current random-walk-based methods, most of them are usually not expressive enough to preserve the personalized higher-order proximity and lack a straightforward objective to theoretically articulate what and how network proximity is preserved. In this paper, to address the above issues, we present a general scalable random-walk-based network embedding framework, in which random walk is explicitly incorporated into a sound objective designed theoretically to preserve arbitrary higher-order proximity. Further, we introduce the random walk with restart process into the framework to naturally and effectively achieve personalized-weighted preservation of proximities of different orders. We conduct extensive experiments on several real-world networks and demonstrate that our proposed method consistently and substantially outperforms the state-of-the-art network embedding methods.

cs.LG↗

arXiv2019

HeteSpaceyWalk: A Heterogeneous Spacey Random Walk for Heterogeneous Information Network Embedding

Heterogeneous information network (HIN) embedding has gained increasing interests recently. However, the current way of random-walk based HIN embedding methods have paid few attention to the higher-order Markov chain nature of meta-path guided random walks, especially to the stationarity issue. In this paper, we systematically formalize the meta-path guided random walk as a higher-order Markov chain process, and present a heterogeneous personalized spacey random walk to efficiently and effectively attain the expected stationary distribution among nodes. Then we propose a generalized scalable framework to leverage the heterogeneous personalized spacey random walk to learn embeddings for multiple types of nodes in an HIN guided by a meta-path, a meta-graph, and a meta-schema respectively. We conduct extensive experiments in several heterogeneous networks and demonstrate that our methods substantially outperform the existing state-of-the-art network embedding algorithms.

cs.LG↗

arXiv2019

Intermolecular coupling and fluxional behavior of hydrogen in phase IV

We performed Raman and infrared (IR) spectroscopy measurements of hydrogen at 295 K up to 280 GPa at an IR synchrotron facility of SSRF. To reach the highest pressure, hydrogen was loaded into toroidal diamond anvils with 40 micrometers central culet. The intermolecular coupling has been determined by concomitant measurements of the IR and Raman vibron modes. In phase IV, we find that the intermolecular coupling is much stronger in the graphene (G) like layer of elongated molecules compared to the Br2 like layer of shortened molecules and it increases with pressure much faster in the G layer compared to the Br2 layer. These heterogeneous lattice dynamical properties are unique features of highly fluxional hydrogen phase IV.

cond-mat.mtrl-sci↗

arXiv2018

On the Reactivity of Hydrogen-Helium and Hydrogen-Nitrogen at High Pressures

Through a series of Raman spectroscopy studies, we investigate the behaviour of hydrogen-helium and hydrogen-nitrogen mixtures at high pressure across wide ranging concentrations. We find that there is no evidence of chemical association, miscibility, nor any demixing of hydrogen and helium in the solid state up to pressures of 250 GPa at 300 K. In contrast, we observe the formation of concentration-dependent N$_2$-H$_2$ van der Waals solids, which react to form N-H bonded compounds above 50 GPa. Through this combined study, we can demonstrate that the recently claimed chemical association of H$_2$-He can be attributed to significant N$_2$ contamination and subsequent formation of N$_2$-H$_2$ compounds.

cond-mat.mtrl-sci↗

arXiv2015

Pressure-induced semimetal to superconductor transition in a three-dimensional topological material ZrTe5

As a new type of topological materials, ZrTe5 shows many exotic properties under extreme conditions. Utilizing resistance and ac magnetic susceptibility measurements under high pressure, while the resistance anomaly near 128 K is completely suppressed at 6.2 GPa, a fully superconducting transition emerges surprisingly. The superconducting transition temperature Tc increases with applied pressure, and reaches a maximum of 4.0 K at 14.6 GPa, followed by a slight drop but remaining almost constant value up to 68.5 GPa. At pressures above 21.2 GPa, a second superconducting phase with the maximum Tc of about 6.0 K appears and coexists with the original one to the maximum pressure studied in this work. In situ high-pressure synchrotron X-ray diffraction and Raman spectroscopy combined with theoretical calculations indicate the observed two-stage superconducting behavior is correlated to the structural phase transition from ambient Cmcm phase to high-pressure C2/m phase around 6 GPa, and to a mixture of two high-pressure phases of C2/m and P-1 above 20 GPa. The combination of structure, transport measurement and theoretical calculations enable a complete understanding of the emerging exotic properties in three-dimensional topological materials happened under extreme environments.

cond-mat.supr-con↗