activity
20162022
most citedAdaptive Gradient Methods with Dynamic Bound of Learning Rate

189 citations · 808 across the 51 of their papers we have counts for

collaborators
Showing 2021Show all

19 papers · 1 filter

cs.CL2021

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…

cs.LG2021

Auto-Encoding Knowledge Graph for Unsupervised Medical Report Generation

Fenglin Liu, Chenyu You, Xian Wu +3

Medical report generation, which aims to automatically generate a long and coherent report of a given medical image, has been receiving growing research interests. Existing approac…

cs.CL2021★ 1 cited

RAP: Robustness-Aware Perturbations for Defending against Backdoor Attacks on NLP Models

Wenkai Yang, Yankai Lin, Peng Li +2

Backdoor attacks, which maliciously control a well-trained model's outputs of the instances with specific triggers, are recently shown to be serious threats to the safety of reusin…

cs.LG2021★ 47 cited

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…

cs.LG2021

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…

cs.CL2021

Dynamic Knowledge Distillation for Pre-trained Language Models

Lei Li, Yankai Lin, Shuhuai Ren +3

Knowledge distillation~(KD) has been proved effective for compressing large-scale pre-trained language models. However, existing methods conduct KD statically, e.g., the student mo…