Author name cluster

Hanyu Peng

Possible papers associated with this exact author name in Arrow. This page groups case-insensitive exact name matches and is not a full identity disambiguation profile.

5 papers

2 author rows

UAI Conference 2023 Conference Paper

Copula for Instance-wise Feature Selection and Rank

Hanyu Peng
Guanhua Fang
Ping Li 0001

Instance-wise feature selection and ranking methods can achieve a good selection of task-friendly features for each sample in the context of neural networks. However, existing approaches that assume feature subsets to be independent are imperfect when considering the dependency between features. To address this limitation, we propose to incorporate the Gaussian copula, a powerful mathematical technique for capturing correlations between variables, into the current feature selection framework with no additional changes needed. Experimental results on both synthetic and real datasets, in terms of performance comparison and interpretability, demonstrate that our method is capable of capturing meaningful correlations.

Details

ICLR Conference 2023 Conference Paper

Dataset Pruning: Reducing Training Data by Examining Generalization Influence

Shuo Yang 0006
Zeke Xie
Hanyu Peng
Min Xu 0001
Mingming Sun 0001
Ping Li 0001

The great success of deep learning heavily relies on increasingly larger training data, which comes at a price of huge computational and infrastructural costs. This poses crucial questions that, do all training data contribute to model's performance? How much does each individual training sample or a sub-training-set affect the model's generalization, and how to construct the smallest subset from the entire training data as a proxy training set without significantly sacrificing the model's performance? To answer these, we propose dataset pruning, an optimization-based sample selection method that can (1) examine the influence of removing a particular set of training samples on model's generalization ability with theoretical guarantee, and (2) construct the smallest subset of training data that yields strictly constrained generalization gap. The empirically observed generalization gap of dataset pruning is substantially consistent with our theoretical expectations. Furthermore, the proposed method prunes 40% training examples on the CIFAR-10 dataset, halves the convergence time with only 1.3% test accuracy decrease, which is superior to previous score-based sample selection methods.

Details

AAAI Conference 2023 Conference Paper

MetaTPTrans: A Meta Learning Approach for Multilingual Code Representation Learning

Weiguo Pian
Hanyu Peng
Xunzhu Tang
Tiezhu Sun
Haoye Tian
Andrew Habib
Jacques Klein
Tegawendé F. Bissyandé

Representation learning of source code is essential for applying machine learning to software engineering tasks. Learning code representation from a multilingual source code dataset has been shown to be more effective than learning from single-language datasets separately, since more training data from multilingual dataset improves the model's ability to extract language-agnostic information from source code. However, existing multilingual training overlooks the language-specific information which is crucial for modeling source code across different programming languages, while only focusing on learning a unified model with shared parameters among different languages for language-agnostic information modeling. To address this problem, we propose MetaTPTrans, a meta learning approach for multilingual code representation learning. MetaTPTrans generates different parameters for the feature extractor according to the specific programming language type of the input code snippet, enabling the model to learn both language-agnostic and language-specific information with dynamic parameters in the feature extractor. We conduct experiments on the code summarization and code completion tasks to verify the effectiveness of our approach. The results demonstrate the superiority of our approach with significant improvements on state-of-the-art baselines.

PDF Details DOI

ICLR Conference 2022 Conference Paper

Optimal Transport for Long-Tailed Recognition with Learnable Cost Matrix

Hanyu Peng
Mingming Sun 0001
Ping Li 0001

It is attracting attention to the long-tailed recognition problem, a burning issue that has become very popular recently. Distinctive from conventional recognition is that it posits that the allocation of the training set is supremely distorted. Predictably, it will pose challenges to the generalisation behaviour of the model. Approaches to these challenges revolve into two groups: firstly, training-aware methods, with the aim of enhancing the generalisability of the model by exploiting its potential in the training period; and secondly, post-hoc correction, liberally coupled with training-aware methods, which is intended to refine the predictions to the extent possible in the post-processing stage, offering the advantages of simplicity and effectiveness. This paper introduces an alternative direction to do the post-hoc correction, which goes beyond the statistical methods. Mathematically, we approach this issue from the perspective of optimal transport (OT), yet, choosing the exact cost matrix when applying OT is challenging and requires expert knowledge of various tasks. To overcome this limitation, we propose to employ linear mapping to learn the cost matrix without necessary configurations adaptively. Testing our methods in practice, along with high efficiency and excellent performance, our method surpasses all previous methods and has the best performance to date.

Details

ICML Conference 2019 Conference Paper

Collaborative Channel Pruning for Deep Networks

Hanyu Peng
Jiaxiang Wu 0001
Shifeng Chen
Junzhou Huang

Deep networks have achieved impressive performance in various domains, but their applications are largely limited by the prohibitive computational overhead. In this paper, we propose a novel algorithm, namely collaborative channel pruning (CCP), to reduce the computational overhead with negligible performance degradation. The joint impact of pruned/preserved channels on the loss function is quantitatively analyzed, and such interchannel dependency is exploited to determine which channels to be pruned. The channel selection problem is then reformulated as a constrained 0-1 quadratic optimization problem, and the Hessian matrix, which is essential in constructing the above optimization, can be efficiently approximated. Empirical evaluation on two benchmark data sets indicates that our proposed CCP algorithm achieves higher classification accuracy with similar computational complexity than other stateof-the-art channel pruning algorithms

Details