• Publications
  • Influence
Learning Entity and Relation Embeddings for Knowledge Graph Completion
TLDR
TransR is proposed to build entity and relation embeddings in separate entity space and relation spaces to build translations between projected entities and to evaluate the models on three tasks including link prediction, triple classification and relational fact extraction. Expand
A Storage Solution for Massive IoT Data Based on NoSQL
TLDR
A storage management solution called IOTMDB based on NoSQL as current storage solutions are not well support storing massive and heterogeneous IoT data. Expand
A Performance-Sensitive Malware Detection System Using Deep Learning on Mobile Devices
TLDR
This paper proposes an effective Android malware detection system, MobiTive, leveraging customized deep neural networks to provide a real-time and responsive detection environment on mobile devices and investigates the performance of different feature extraction methods based on source code or binary code and the potential based on the evolution of mobile devices’ specifications. Expand
FedPD: A Federated Learning Framework with Optimal Rates and Adaptivity to Non-IID Data
TLDR
This paper first explicitly characterize the behavior of the FedAvg algorithm, and shows that without strong and unrealistic assumptions on the problem structure, the algorithm can behave erratically for non-convex problems (e.g., diverge to infinity). Expand
Backdoor attacks and defenses in feature-partitioned collaborative learning
TLDR
This paper shows that even parties with no access to labels can successfully inject backdoor attacks, achieving high accuracy on both main and backdoor tasks and is the first systematical study to deal with backdoor attacks in the feature-partitioned collaborative learning framework. Expand
A Communication Efficient Collaborative Learning Framework for Distributed Features
TLDR
A Federated Stochastic Block Coordinate Descent (FedBCD) algorithm is proposed, in which each party conducts multiple local updates before each communication to effectively reduce the number of communication rounds among parties, a principal bottleneck for collaborative learning problems. Expand
Clusterability as an Alternative to Anchor Points When Learning with Noisy Labels
TLDR
This paper discovers an efficient estimation procedure based on a clusterability condition and proves that with clusterable representations of features, using up to third-order consensuses of noisy labels among neighbor representations is sufficient to estimate a unique transition matrix. Expand
FedMVT: Semi-supervised Vertical Federated Learning with MultiView Training
TLDR
Experimental results demonstrate that FedMVT significantly outperforms vanilla VFL that only utilizes overlapping samples, and improves the performance of the local model in the party that owns labels, thus preserving data privacy. Expand
Automatic Code Summarization via Multi-dimensional Semantic Fusing in GNN
TLDR
This paper proposes a retrieval-augmented mechanism to augment source code semantics with external knowledge to better learn semantics from the joint graph, and proposes a novel attention-based dynamic graph to capture global interactions among nodes in the static graph. Expand
Watch out! Motion is Blurring the Vision of Your Deep Neural Networks
TLDR
A novel adversarial attack method that can generate visually natural motion-blurred adversarial examples, named motion-based adversarial blur attack (ABBA), which shows more effective penetrating capability to the state-of-the-art GAN-based deblurring mechanisms compared with other blurring methods. Expand
...
1
2
3
4
5
...