110 citations · 867 across the 51 of their papers we have counts for
8 papers · 1 filter
Model Uncertainty-Aware Knowledge Amalgamation for Pre-Trained Language Models
Lei Li, Yankai Lin, Xuancheng Ren +4
As many fine-tuned pre-trained language models~(PLMs) with promising performance are generously released, investigating better ways to reuse these models is vital as it can greatly…
Topology-Imbalance Learning for Semi-Supervised Node Classification
Deli Chen, Yankai Lin, Guangxiang Zhao +4
The class imbalance problem, as an important issue in learning node representations, has drawn increasing attention from the community. Although the imbalance considered by existin…
Well-classified Examples are Underestimated in Classification with Deep Neural Networks
Guangxiang Zhao, Wenkai Yang, Xuancheng Ren +3
The conventional wisdom behind learning deep classification models is to focus on bad-classified examples and ignore well-classified examples that are far from the decision boundar…
Adversarial Parameter Defense by Multi-Step Risk Minimization
Zhiyuan Zhang, Ruixuan Luo, Xuancheng Ren +3
Previous studies demonstrate DNNs' vulnerability to adversarial examples and adversarial training can establish a defense to adversarial examples. In addition, recent studies show…
O2NA: An Object-Oriented Non-Autoregressive Approach for Controllable Video Captioning
Fenglin Liu, Xuancheng Ren, Xian Wu +4
Video captioning combines video understanding and language generation. Different from image captioning that describes a static image with details of almost every object, video capt…
Rethinking Skip Connection with Layer Normalization in Transformers and ResNets
Fenglin Liu, Xuancheng Ren, Zhiyuan Zhang +2
Skip connection, is a widely-used technique to improve the performance and the convergence of deep neural networks, which is believed to relieve the difficulty in optimization due…
Be Careful about Poisoned Word Embeddings: Exploring the Vulnerability of the Embedding Layers in NLP Models
Wenkai Yang, Lei Li, Zhiyuan Zhang +3
Recent studies have revealed a security threat to natural language processing (NLP) models, called the Backdoor Attack. Victim models can maintain competitive performance on clean…
Multi-View Feature Representation for Dialogue Generation with Bidirectional Distillation
Shaoxiong Feng, Xuancheng Ren, Kan Li +1
Neural dialogue models suffer from low-quality responses when interacted in practice, demonstrating difficulty in generalization beyond training data. Recently, knowledge distillat…