Yuguo Liu

Yuguo Liu

Auto-generated profile, based on publicly available information

Yuguo Liu

School of Computer Science and Engineering, University of Electronic Science and Technology of China, Chengdu, China

Research Focus & Metrics

Academic Career Length

6Years (2021-Present)

(Calculated once Scilit publication data is synced: current year − year of first publication + 1)

Representative Publications

View All Publications
1 August 2023
Verified
Conference Paper
Open access
PDF file
YWYuchen Wang
Yuchen Wang
KSKexin Shi
Kexin Shi
CLChengzhuo Lu
Chengzhuo Lu
YLYuguo Liu
Yuguo Liu
Malu ZhangMalu Zhang
Malu Zhang
HQHong Qu
Hong Qu
The brain-inspired spiking neural networks (SNNs) are receiving increasing attention due to their asynchronous event-driven characteristics and low power consumption. As attention mechanisms recently become an indispensable part of sequence dependence modeling, the combination of SNNs and attention mechanisms holds great potential for energy-efficient and high-performance computing paradigms. However, the existing works cannot benefit from both temporal-wise attention and the asynchronous characteristic of SNNs. To fully leverage the advantages of both SNNs and attention mechanisms, we propose an SNNs-based spatial-temporal self-attention (STSA) mechanism, which calculates the feature dependence across the time and space domains without destroying the asynchronous transmission properties of SNNs. To further improve the performance, we also propose a spatial-temporal relative position bias (STRPB) for STSA to consider the spatiotemporal position of spikes. Based on the STSA and STRPB, we construct a spatial-temporal spiking Transformer framework, named STS-Transformer, which is powerful and enables SNNs to work in an asynchronous event-driven manner. Extensive experiments are conducted on popular neuromorphic datasets and speech datasets, including DVS128 Gesture, CIFAR10-DVS, and Google Speech Commands, and our experimental results can outperform other state-of-the-art models.

4 September 2021 in Neural Computing and Applications
Verified
Journal Article
Closed access
PDF file
LHLi Huang
Li Huang
WCWenyu Chen
Wenyu Chen
YLYuguo Liu
Yuguo Liu
HZHe Zhang
He Zhang
HQHong Qu
Hong Qu

11 January 2021 in IEEE Transactions on Cybernetics
Verified
Journal Article
Closed access
LHLi Huang
Li Huang
WCWenyu Chen
Wenyu Chen
YLYuguo Liu
Yuguo Liu
SHShuai Hou
Shuai Hou
HQHong Qu
Hong Qu
In the natural language processing family, learning representations is a pioneering study, especially in sequence-to-sequence tasks where outputs are generated, totally relying on the learning representations of source sequence. Generally, classic methods infer that each word occurring in the source sequence, having more or less influence on the target sequence, should all be considered when generating outputs. As the summarization task requires the output sequence to only retain the essence, classic full consideration of the source sequence may not work well on it, which calls for more suitable methods with the ability to discard the misleading noise words. Motivated by this, with both relevance retaining and redundancy removal in mind, we propose a summarization learning model by implementing an encoder with copious contextual information represented and a decoder with a selecting mechanism integrated. Specifically, we equip the encoder with an asynchronous bi directional parallel structure, in order to obtain abundant semantic representation. The decoder, different from the classic attention-based works, employs a self-aware context selecting mechanism to generate summary in a more productive way. We evaluate the proposed methods on three benchmark summarization corpora. The experimental results demonstrate the effectiveness and applicability of the proposed framework in relation to several well-practiced and state-of-the-art summarization methods.

6 July 2023 in IEEE Transactions on Neural Networks and Learning Systems
Verified
Journal Article
Closed access
YLYuguo Liu
Yuguo Liu
WCWenyu Chen
Wenyu Chen
HLHanwen Liu
Hanwen Liu
YZYun Zhang
Yun Zhang
Malu ZhangMalu Zhang
Malu Zhang
HQHong Qu
Hong Qu
Word representations, usually derived from a large corpus and endowed with rich semantic information, have been widely applied to natural language tasks. Traditional deep language models, on the basis of dense word representations, requires large memory space and computing resource. The brain-inspired neuromorphic computing systems, with the advantages of better biological interpretability and less energy consumption, still have major difficulties in the representation of words in terms of neuronal activities, which has restricted their further application in more complicated downstream language tasks. Comprehensively exploring the diverse neuronal dynamics of both integration and resonance, we probe into three spiking neuron models to post-process the original dense word embeddings, and test the generated sparse temporal codes on several tasks concerning both word-level and sentence-level semantics. The experimental results show that our sparse binary word representations could perform on par with or even better than original word embeddings in capturing semantic information, while requiring less storage. Our methods provide a robust representation foundation of language in terms of neuronal activities, which could potentially be applied to future downstream natural language tasks under neuromorphic computing systems.

27 December 2024 in IEEE Transactions on Cognitive and Developmental Systems
Verified
Journal Article
Closed access
YLYuguo Liu
Yuguo Liu
WCWenyu Chen
Wenyu Chen
HLHanwen Liu
Hanwen Liu
YZYun Zhang
Yun Zhang
Malu ZhangMalu Zhang
Malu Zhang
HQHong Qu
Hong Qu
Language models have been undergoing rapid growth and remarkable success, while requiring massive computing resource. The brain-inspired spiking neural networks(SNNs), with advantages of better biological interpretability and less energy consumption, provides a likely alternative to process language tasks in a more sustainable way. However, there are still major difficulties in representing and processing text information with SNN-based models. Comprehensively exploring the neurodynamic diversity, we propose a spiking neural network model that could taking respective advantages from both integrator and resonator neurons to address text classification tasks. With collaborations of these two dynamically different spiking neurons, our network model outperforms previous SNN-based text classification model in an all-round way with much less time steps, and even shows some extent of potential to reach the performance of a topologically equivalent artificial neural network.