Sheng Zha

Knowledge Distillation (KD) offers a natural way to reduce the latency and memory/energy usage of massive pretrained models that have come to dominate Natural Language Processing (NLP) in recent years. While numerous sophisticated variants of KD algorithms have been proposed for NLP applications, the key factors underpinning the optimal distillation performance are often confounded and remain unclear. We aim to identify how different components in the KD pipeline affect the resulting performance and how much the optimal KD pipeline varies across different datasets/tasks, such as the data augmentation policy, the loss function, and the intermediate representation for transferring the knowledge between teacher and student. To tease apart their effects, we propose Distiller, a meta KD framework that systematically combines a broad range of techniques across different stages of the KD pipeline, which enables us to quantify each component’s contribution. Within Distiller, we unify common...

With an increasing demand for training powers for deep learning algorithms and the rapid growth of computation resources in data centers, it is desirable to dynamically schedule different distributed deep learning tasks to maximize resource utilization and reduce cost. In this process, different tasks may receive varying numbers of machines at different time, a setting we call elastic distributed training. Despite the recent successes in large mini-batch distributed training, these methods are rarely tested in elastic distributed training environments and suffer degraded performance in our experiments, when we adjust the learning rate linearly immediately with respect to the batch size. One difficulty we observe is that the noise in the stochastic momentum estimation is accumulated over time and will have delayed effects when the batch size changes. We therefore propose to smoothly adjust the learning rate over time to alleviate the influence of the noisy momentum estimation. Our ex...

We present GluonCV and GluonNLP, the deep learning toolkits for computer vision and natural language processing based on Apache MXNet (incubating). These toolkits provide state-of-the-art pre-trained models, training scripts, and training logs, to facilitate rapid prototyping and promote reproducible research. We also provide modular APIs with flexible building blocks to enable efficient customization. Leveraging the MXNet ecosystem, the deep learning models in GluonCV and GluonNLP can be deployed onto a variety of platforms with different programming languages. The Apache 2.0 license has been adopted by GluonCV and GluonNLP to allow for software distribution, modification, and usage.

The goal of meta-learning is to learn to adapt to a new task with only a few labeled examples. To tackle this problem in NLP, we propose in-context tuning, which recasts adaptation and prediction as a simple sequence prediction problem: to form the input sequence, we concatenate the task instruction, the labeled examples, and the target input to predict; to meta-train the model to learn from in-context examples, we fine-tune a pre-trained language model (LM) to predict the target label from the input sequences on a collection of tasks. We benchmark our method on two collections of text classification tasks: LAMA and BinaryClfs. Compared to first-order MAML which adapts the model with gradient descent, our method better leverages the inductive bias of LMs to perform pattern matching, and outperforms MAML by an absolute 6% AUC ROC score on BinaryClfs, with increasing advantage w.r.t. model size. Compared to nonfine-tuned in-context learning (i.e. prompting a raw LM), in-context tuning...

The authors enhance pretrained language models with Securities and Exchange Commission filings data to create better language representations for features used in a predictive model. Specifically, they train RoBERTa class models with additional financial regulatory text, which they denote as a class of RoBERTa-Fin models. Using different datasets, the authors assess whether there is material improvement over models that use only text-based numerical features (e.g., sentiment, readability, polarity), which is the traditional approach adopted in academia and practice. The RoBERTa-Fin models also outperform generic bidirectional encoder representations from transformers (BERT) class models that are not trained with financial text. The improvement in classification accuracy is material, suggesting that full text and context are important in classifying financial documents and that the benefits from the use of mixed data, (i.e., enhancing numerical tabular data with text) are feasible an...

Deep learning has become the dominant approach to NLP problems, especially when applied on large scale corpora. Recent progress on unsupervised pre-training techniques such as BERT, ELMo, GPT-2, and language modeling in general, when applied on large corpora, is shown to be effective in improving a wide variety of downstream tasks. These techniques push the limits of available hardware, requiring specialized frameworks optimized for GPU, ASIC, and distributed cloud-based training.A few complexities pose challenges to scale these models and algorithms effectively. Compared to other areas where deep learning is applied, these NLP models contain a variety of moving parts: text normalization and tokenization, word representation at subword-level and word-level, variable-length models such as RNN and attention, and sequential decoder based on beam search, among others.In this hands-on tutorial, we take a closer look at the challenges from these complexities and see how with proper toolin...

Brain-computer interface system, as a new technology in controlling and monitoring, has been drawing more and more attention. Brain-computer interface systems based on EEG signals, in particular, has been more and more popular since the technology of collecting EEG data is comparatively cheap and easy. However, due to the existence of various kinds of noises (artifacts), especially those from external origins such as power supply interference, and those from inner origins such as EOG and EMG, the analysis of EEG signals would be influenced and thus the BCI systems would produce false or inaccurate results. On the other hand, BCI systems also require real-time data flow that drives the controlling or monitoring system. In order to meet these two needs, this paper digs deep into the properties of EEG signals and artifacts, and proposes a novel online artifact removal algorithm that removes artifacts from EEG data flow in real-time. This algorithm is based on independent component anal...

Batching is an essential technique to improve computation efficiency in deep learning frameworks. While batch processing for models with static feed-forward computation graphs is straightforward to implement, batching for dynamic computation graphs such as syntax trees or social network graphs is challenging due to variable computation graph structure across samples. Through simulation and analysis of a Tree-LSTM model, we show the key trade-off between graph analysis time and batching effectiveness in dynamic batching. Based on this finding, we propose a dynamic batching method as an extension to MXNet Gluon's just-in-time compilation (JIT) framework. We show empirically that our method yields up to 6.25 times speed-up on a common dynamic workload, a tree-LSTM model for the semantic relatedness task.