Seungyeon Kim
Research Areas
Authored Publications
Sort By
Supervision complexity and its role in knowledge distillation
Hrayr Harutyunyan
Aditya Krishna Menon
International Conference on Learning Representations (2023) (to appear)
Preview abstract
Knowledge distillation is a popular method of compressing a large teacher model (or an ensemble of models) to a more compact student model. While empirically effective, there is limited understanding of why distillation helps, and how to improve it to transfer richer knowledge from the teacher to student. In this paper, we propose a new online distillation algorithm that applies distillation using a sequence of teacher models, corresponding to different checkpoints during teacher training. Intuitively, this gradually increases the complexity of the target functions that the student model is asked to mimic. Formally, we establish generalization bounds that explicate how the target label complexity can benefit the student. We empirically demonstrate that online distillation can significantly improve over regular offline distillation, particularly in scenarios where there is a large teacher-student capacity gap.
View details
Teacher Guided Training: An Efficient Framework for Knowledge Transfer
Chong You
Himanshu Jain
Rob Fergus
International Conference on Learning Representations (2023) (to appear)
Preview abstract
The remarkable performance gains realized by large pretrained models, e.g., GPT-3, hinge on the massive amounts of data they are exposed to during training. Analogously, distilling such large models to compact models for efficient deployment also necessitates a large amount of (labeled or unlabeled) training data. In this paper, we devise teacher-guided training (TGT) framework for training a high-quality compact model that leverages the knowledge acquired by pre-trained \emph{generative} models while obviating the need to go through a large volume of data. TGT exploits the fact that the teacher has acquired a good representation of the underlying data domain, which typically corresponds to a much lower dimensional manifold than the ambient space. Furthermore, we can use the teacher to explore the instance space more efficiently through sampling or gradient-based methods; thus, making TGT especially attractive for limited data or long-tail settings. We formally capture this benefit of proposed data-domain exploration in our generalization bounds. Among our empirical evaluations, we find that TGT can improve accuracy on ImageNet-LT by 10% compared to natural baseline and match accuracy on sentiment analysis on Amazon reviews without the need for pretraining.
View details
Efficient Training of Language Models using Few-Shot Learning
Shankar Krishnan
Satyen Kale
ICML (2023)
Preview abstract
Large deep learning models have achieved state-of-the-art performance across various natural language processing (NLP) tasks and demonstrated remarkable few-shot learning performance. However, training them is often challenging and resource-intensive. In this paper, we study an efficient approach to train language models using few-shot learners. We show that, by leveraging the fast learning nature of few-shot learners, one can train language models efficiently in a stagewise manner. Our main insight is that stacking a good few-shot learner on a good small language model provides a good initializer for a larger language model. Using this insight and building upon progressive stacking approaches, we develop novel approaches for training such networks in a stagewise manner. Furthermore, we also provide a theoretical framework and accompanying empirical studies to support our insights, thereby creating a theoretical foundation for progressive stacking. Finally, we provide empirical results to demonstrate the effectiveness of our approach in reducing the training time of few-shot learners.
View details
In defense of dual-encoders for neural ranking
Aditya Krishna Menon
Sadeep Jayasumana
International Conference on Machine Learning (ICML) (2022)
Preview abstract
Transformer-based models such as BERT have proven successful in information retrieval problem, which seek to identify relevant documents for a given query. There are two broad flavours of such models: cross-attention (CA) models, which learn a joint embedding for the query and document, and dual-encoder (DE) models, which learn separate embeddings for the query and document. Empirically, CA models are often found to be more accurate, which has motivated a series of works seeking to bridge this gap. However, a more fundamental question remains less explored: does this performance gap reflect an inherent limitation in the capacity of DE models, or a limitation in the training of such models? And does such an understanding suggest a principled means of improving DE models? In this paper, we study these questions, with three contributions. First, we establish theoretically that with a sufficiently large embedding dimension, DE models have the capacity to model a broad class of score distributions. Second, we show empirically that on real-world problems, DE models may overfit to spurious correlations in the training set, and thus under-perform on test samples. To mitigate this behaviour, we propose a novel distillation strategy that leverages confidence margins, and confirm its practical efficacy on the MSMARCO-Passage benchmark.
View details
RankDistil: Distillation for Ranking
Aditya Krishna Menon
AISTATS 2021 (2021)
Preview abstract
Knowledge distillation is an approach to improve the performance of a student model by using the knowledge of a complex teacher. Despite its success in several deep learning applications, the study of distillation is mostly confined to classification settings. In particular, the use of distillation in top-k ranking settings, where the goal is to rank k most relevant items correctly, remains largely unexplored. In this paper, we study such ranking problems through the lens of distillation. We present a framework for distillation for top-k ranking and establish connections with the existing ranking methods. The core idea of this framework is to preserve the ranking at the top by matching the k largest scores of student and teacher while penalizing large scores for items ranked low by the teacher. Building on our framework, we develop a novel distillation approach, RankDistil, specifically catered towards ranking problems with a large number of items to rank. Finally, we conduct experiments which demonstrate that RankDistil yields benefits over commonly used baselines for ranking problems.
View details
Evaluations and Methods for Explanation through Robustness Analysis
Cheng-Yu Hsieh
Chih-Kuan Yeh
Xuanqing Liu
Pradeep Ravikumar
Cho-Jui Hsieh
(2021)
Preview abstract
Among multiple ways of interpreting a machine learning model, measuring the importance of a set of features tied to a prediction is probably one of the most intuitive ways to explain a model. In this paper, we establish the link between a set of features to a prediction with a new evaluation criterion, robustness analysis, which measures the minimum distortion distance of adversarial perturbation. By measuring the tolerance level for an adversarial attack, we can extract a set of features that provides the most robust support for a prediction, and also can extract a set of features that contrasts the current prediction to a target class by setting a targeted adversarial attack. By applying this methodology to various prediction tasks across multiple domains, we observe the derived explanations are indeed capturing the significant feature set qualitatively and quantitatively.
View details
A statistical perspective on distillation
Aditya Krishna Menon
International Conference on Machine Learning (ICML) 2021 (to appear)
Preview abstract
Knowledge distillation is a technique for improving a ``student'' model by replacing its one-hot training labels with a label distribution obtained from a ``teacher'' model. Despite its broad success, several basic questions --- e.g., Why does distillation help? Why do more accurate teachers not necessarily distill better? --- have received limited formal study. In this paper, we present a statistical perspective on distillation which provides an answer to these questions. Our core observation is that a ``Bayes teacher'' providing the true class-probabilities can lower the variance of the student objective, and thus improve performance. We then establish a bias-variance tradeoff that quantifies the value of teachers that approximate the Bayes class-probabilities. This provides a formal criterion as to what constitutes a ``good'' teacher, namely, the quality of its probability estimates. Finally, we illustrate how our statistical perspective facilitates novel applications of distillation to bipartite ranking and multiclass retrieval.
View details
Preview abstract
It is generally believed that robust training of extremely large networks is critical to their success in real-world applications. However, when taken to the extreme, methods that promote robustness can hurt the model's sensitivity to rare or underrepresented patterns. In this paper, we discuss this trade-off between sensitivity and robustness to natural (non-adversarial) perturbations by introducing two notions: contextual feature utility and contextual feature sensitivity. We propose Feature Contrastive Learning (FCL) that encourages a model to be more sensitive to the features that have higher contextual utility. Empirical results demonstrate that models trained with FCL achieve a better balance of robustness and sensitivity, leading to improved generalization in the presence of noise on both vision and NLP datasets.
View details
Semantic label smoothing for sequence to sequence problems
Himanshu Jain
Aditya Krishna Menon
EMNLP (2020) (to appear)
Preview abstract
Label smoothing has been shown to be an effective regularization strategy in classification, that prevents overfitting and helps in label de-noising.
However, extending such methods directly to seq2seq settings, such as Machine Translation, has been hindered by the large target output space, making it intractable to apply label smoothing over all possible outputs. Most existing approaches for seq2seq settings either do token level smoothing, or smooth over sequences generated by randomly substituting tokens in the target sequence. Unlike these works, in this paper, we propose a technique that smooths over \emph{well formed} relevant sequences that not only have sufficient n-gram overlap with the target sequence, but are also \emph{semantically similar}. Our method shows a consistent and significant improvement over the state-of-the-art techniques on different datasets.
View details
Why are Adaptive Methods Good for Attention Models?
Jingzhao Zhang
Sai Praneeth Karimireddy
Suvrit Sra
Advances in Neural Information Processing Systems (NeurIPS) (2020)
Preview abstract
While stochastic gradient descent (SGD) is still the de facto algorithm in deep learning, adaptive methods like Clipped SGD/Adam have been observed to outperform SGD across important tasks, such as attention models. The settings under which SGD performs poorly in comparison to adaptive methods are not well understood yet. In this paper, we provide empirical and theoretical evidence that a heavy-tailed distribution of the noise in stochastic gradients is one cause of SGD's poor performance. We provide the first tight upper and lower convergence bounds for adaptive gradient methods under heavy-tailed noise. Further, we demonstrate how gradient clipping plays a key role in addressing heavy-tailed gradient noise. Subsequently, we show how clipping can be applied in practice by developing an adaptive coordinate-wise clipping algorithm (ACClip) and demonstrate its superior performance on BERT pretraining and finetuning tasks.
View details
