Existing Quantization-Aware Training (QAT) methods intensively depend on the
complete labeled dataset or knowledge distillation to guarantee the
performances toward Full Precision (FP) accuracies. However, empirical results
show that QAT still has inferior results compared to its FP counterpart. One
question is how to push QAT toward or even surpass FP performances. In this
paper, we address this issue from a new perspective by injecting the vicinal
data distribution information to improve the generalization performances of QAT
effectively. We present a simple, novel, yet powerful method introducing an
Consistency Regularization (CR) for QAT. Concretely, CR assumes that augmented
samples should be consistent in the latent feature space. Our method
generalizes well to different network architectures and various QAT methods.
Extensive experiments demonstrate that our approach significantly outperforms
the current state-of-the-art QAT methods and even FP counterparts.

该论文介绍了一种新颖的方法 ——Consistency Regularization（CR），通过将邻近数据分布信息注入到 Quantization-Aware Training（QAT）中，有效提高了 QAT 的泛化性能，实验证明该方法显著优于当前最先进的 QAT 方法和 Full Precision（FP）对照组。

通过一致性规则将量化感知训练推向全精度性能

Push Quantization-Aware Training Toward Full Precision Performances via  Consistency Regularization

We consider the problem of ranking n experts based on their performances on d
tasks. We make a monotonicity assumption stating that for each pair of experts,
one outperforms the other on all tasks. We consider the sequential setting
where in each round, the learner has access to noisy evaluations of actively
chosen pair of expert-task, given the information available up to the actual
round. Given a confidence parameter $\delta$ $\in$ (0, 1), we provide
strategies allowing to recover the correct ranking of experts and develop a
bound on the total number of queries made by our algorithm that hold with
probability at least 1 -- $\delta$. We show that our strategy is adaptive to
the complexity of the problem (our bounds are instance dependent), and develop
matching lower bounds up to a poly-logarithmic factor. Finally, we adapt our
strategy to the relaxed problem of best expert identification and provide
numerical simulation consistent with our theoretical results.

针对评估专家在多项任务上表现的问题，提出了一种策略，使得能够通过接收含噪声的反馈信息，实现对专家排名的正确恢复，并且该策略适应问题的复杂程度，并提供了与理论结果一致的数值模拟。

基于多任务表现的专家活跃排名

Active Ranking of Experts Based on their Performances in Many Tasks

Keyphrase generation is the task consisting in generating a set of words or
phrases that highlight the main topics of a document. There are few datasets
for keyphrase generation in the biomedical domain and they do not meet the
expectations in terms of size for training generative models. In this paper, we
introduce kp-biomed, the first large-scale biomedical keyphrase generation
dataset with more than 5M documents collected from PubMed abstracts. We train
and release several generative models and conduct a series of experiments
showing that using large scale datasets improves significantly the performances
for present and absent keyphrase generation. The dataset is available under
CC-BY-NC v4.0 license at this https URL datasets/taln-ls2n/kpbiomed.

本文介绍了 kp-biomed 数据集，这是第一个从 PubMed 摘要中收集了超过 5M 篇文献的大规模生物医学关键词生成数据集，并训练发布了几个生成模型，并进行了一系列实验，表明使用大规模数据集显著提高了生成模型的性能。