Pan Zhou

State-Clustering Based Multiple Deep Neural Networks Modeling Approach for Speech Recognition

2015 · IEEE/ACM Transactions on Audio Speech and Language Processing

The hybrid deep neural network (DNN) and hidden Markov model (HMM) has recently achieved dramatic performance gains in automatic speech recognition (ASR). The DNN-based acoustic model is very powerful but its learning process is extremely …

Privacy-Preserving Collaborative Model Learning: The Case of Word Vector Training

2018 · IEEE Transactions on Knowledge and Data Engineering

Nowadays, machine learning is becoming a new paradigm for mining hidden knowledge in big data. The collection and manipulation of big data not only create considerable values, but also raise serious privacy concerns. To protect …

Deep Adversarial Subspace Clustering

2018

Most existing subspace clustering methods hinge on self-expression of handcrafted representations and are unaware of potential clustering errors. Thus they perform unsatisfactorily on real data with complex underlying subspaces. To solve this issue, we propose …

Modulation recognition of composite modulation signal based on two-fold digital receiver and goodness of fit test

2021 · 2021 IEEE International Conference on Electronic Technology, Communication and Information (ICETCI)

Aiming at the modulation recognition problem of mixed signal set {BPSK, QPSK, BPSK-FM, QPSK-FM} with unknown parameters, this paper proposes a modulation recognition algorithm based on two-fold PLL (phase locked loop) and goodness of fit …

Mugs: A Multi-Granular Self-Supervised Learning Framework

2022 · arXiv (Cornell University)

In self-supervised learning, multi-granular features are heavily desired though rarely investigated, as different downstream tasks (e.g., general and fine-grained classification) often require different or multi-granular features, e.g.~fine- or coarse-grained one or their mixture. In this …

Multicore Federated Learning for Mobile-Edge Computing Platforms

2022 · IEEE Internet of Things Journal

With increasingly strict data privacy regulations, federated learning (FL) has become one of the most often heard machine learning techniques due to its privacy-preserving trait. To efficiently implement the FL intelligence, researchers recently resort to …

ICMC-ASR: The ICASSP 2024 In-Car Multi-Channel Automatic Speech Recognition Challenge

2024

To promote speech processing and recognition research in driving scenarios, we build on the success of the Intelligent Cockpit Speech Recognition Challenge (ICSRC) held at ISCSLP 2022 and launch the ICASSP 2024 In-Car Multi-Channel Automatic …

Grimm: A Plug-and-Play Perturbation Rectifier for Graph Neural Networks Defending against Poisoning Attacks

2024 · arXiv (Cornell University)

Recent studies have revealed the vulnerability of graph neural networks (GNNs) to adversarial poisoning attacks on node classification tasks. Current defensive methods require substituting the original GNNs with defense models, regardless of the original's type. …

Graph Agent Network: Empowering Nodes with Inference Capabilities for Adversarial Resilience

2025 · Proceedings of the AAAI Conference on Artificial Intelligence

End-to-end training with global optimization have popularized graph neural networks (GNNs) for node classification, yet inadvertently introduced vulnerabilities to adversarial edge-perturbing attacks. Adversaries can exploit the inherent opened interfaces of GNNs' input and output, perturbing …

Adversarial Category Alignment Network for Cross-domain Sentiment Classification

2019

Xiaoye Qu, Zhikang Zou, Yu Cheng, Yang Yang, Pan Zhou. Proceedings of the 2019 Conference of the North American Chapter of the Association for Computational Linguistics: Human Language Technologies, Volume 1 (Long and Short Papers). …

A Privacy-Preserving Distributed Contextual Federated Online Learning Framework with Big Data Support in Social Recommender Systems

2019 · IEEE Transactions on Knowledge and Data Engineering

Nowadays, the booming demand of big data analytics and the constraints of computational ability and network bandwidth have made it difficult for a stand-alone agent/service provider to provide suitable information for every user from the …