output
19942026
Showing 2021 · cs.LGShow all

19 papers · 2 filters

cs.LG2021

Low-bit Quantization of Recurrent Neural Network Language Models Using Alternating Direction Methods of Multipliers

Junhao Xu, Xie Chen, Shoukang Hu +3

The high memory consumption and computational costs of Recurrent neural network language models (RNNLMs) limit their wider application on resource constrained devices. In recent ye…

cs.LG2021★ 83 cited

A Survey on Epistemic (Model) Uncertainty in Supervised Learning: Recent Advances and Applications

Xinlei Zhou, Han Liu, Farhad Pourpanah +2

Quantifying the uncertainty of supervised learning models plays an important role in making more reliable predictions. Epistemic uncertainty, which usually is due to insufficient k…

cs.LG2021★ 15 cited

ProTo: Program-Guided Transformer for Program-Guided Tasks

Zelin Zhao, Karan Samel, Binghong Chen +1

Programs, consisting of semantic and structural information, play an important role in the communication between humans and agents. Towards learning general program executors to un…

cs.LG2021★ 1 cited

Inconsistent Few-Shot Relation Classification via Cross-Attentional Prototype Networks with Contrastive Learning

Hongru Wang, Zhijing Jin, Jiarun Cao +2

Standard few-shot relation classification (RC) is designed to learn a robust classifier with only few labeled data for each class. However, previous works rarely investigate the ef…

cs.LG2021★ 24 cited

Flattening Sharpness for Dynamic Gradient Projection Memory Benefits Continual Learning

Danruo Deng, Guangyong Chen, Jianye Hao +2

The backpropagation networks are notably susceptible to catastrophic forgetting, where networks tend to forget previously learned skills upon learning new ones. To address such the…

cs.LG2021★ 210 cited

Deep Reinforcement Learning for Solving the Heterogeneous Capacitated Vehicle Routing Problem

Jingwen Li, Yining Ma, Ruize Gao +4

Existing deep reinforcement learning (DRL) based methods for solving the capacitated vehicle routing problem (CVRP) intrinsically cope with homogeneous vehicle fleet, in which the…

cs.LG2021★ 6 cited

Differentiable Dynamic Quantization with Mixed Precision and Adaptive Resolution

Zhang Zhaoyang, Shao Wenqi, Gu Jinwei +2

Model quantization is challenging due to many tedious hyper-parameters such as precision (bitwidth), dynamic range (minimum and maximum discrete values) and stepsize (interval betw…

cs.LG2021★ 5 cited

Local Reweighting for Adversarial Training

Ruize Gao, Feng Liu, Kaiwen Zhou +3

Instances-reweighted adversarial training (IRAT) can significantly boost the robustness of trained models, where data being less/more vulnerable to the given attack are assigned sm…

cs.LG2021★ 3 cited

Multi-layered Network Exploration via Random Walks: From Offline Optimization to Online Learning

Xutong Liu, Jinhang Zuo, Xiaowei Chen +2

Multi-layered network exploration (MuLaNE) problem is an important problem abstracted from many applications. In MuLaNE, there are multiple network layers where each node has an im…

cs.LG2021★ 2 cited

Optimization Variance: Exploring Generalization Properties of DNNs

Xiao Zhang, Dongrui Wu, Haoyi Xiong +1

Unlike the conventional wisdom in statistical learning theory, the test error of a deep neural network (DNN) often demonstrates double descent: as the model complexity increases, i…

cs.LG2021★ 1 cited

Variance-Dependent Best Arm Identification

Pinyan Lu, Chao Tao, Xiaojin Zhang

We study the problem of identifying the best arm in a stochastic multi-armed bandit game. Given a set of arms indexed from to , each arm is associated with an unknow…

cs.LG2021★ 247 cited

SCINet: Time Series Modeling and Forecasting with Sample Convolution and Interaction

Minhao Liu, Ailing Zeng, Muxi Chen +4

One unique property of time series is that the temporal relations are largely preserved after downsampling into two sub-sequences. By taking advantage of this property, we propose…

cs.LG2021★ 2 cited

BWCP: Probabilistic Learning-to-Prune Channels for ConvNets via Batch Whitening

Wenqi Shao, Hang Yu, Zhaoyang Zhang +3

This work presents a probabilistic channel pruning method to accelerate Convolutional Neural Networks (CNNs). Previous pruning methods often zero out unimportant channels in traini…

cs.LG2021★ 16 cited

Denoising Noisy Neural Networks: A Bayesian Approach with Compensation

Yulin Shao, Soung Chang Liew, Deniz Gunduz

Deep neural networks (DNNs) with noisy weights, which we refer to as noisy neural networks (NoisyNNs), arise from the training and inference of DNNs in the presence of noise. Noisy…

cs.LG2021★ 6 cited

Distributionally Robust Graph Learning from Smooth Signals under Moment Uncertainty

Xiaolu Wang, Yuen-Man Pun, Anthony Man-Cho So

We consider the problem of learning a graph from a finite set of noisy graph signal observations, the goal of which is to find a smooth representation of the graph signal. Such a p…

cs.LG2021★ 5 cited

AppealNet: An Efficient and Highly-Accurate Edge/Cloud Collaborative Architecture for DNN Inference

Min Li, Yu Li, Ye Tian +2

This paper presents AppealNet, a novel edge/cloud collaborative architecture that runs deep learning (DL) tasks more efficiently than state-of-the-art solutions. For a given input,…

cs.LG2021★ 903 cited

A Survey on Deep Semi-supervised Learning

Xiangli Yang, Zixing Song, Irwin King +1

Deep semi-supervised learning is a fast-growing field with a range of practical applications. This paper provides a comprehensive survey on both fundamentals and recent advances in…

cs.LG2021

FeatureNorm: L2 Feature Normalization for Dynamic Graph Embedding

Menglin Yang, Ziqiao Meng, Irwin King

Dynamic graphs arise in a plethora of practical scenarios such as social networks, communication networks, and financial transaction networks. Given a dynamic graph, it is fundamen…

cs.LG2021★ 7 cited

Mask-GVAE: Blind Denoising Graphs via Partition

Jia Li, Mengzhou Liu, Honglei Zhang +4

We present Mask-GVAE, a variational generative model for blind denoising large discrete graphs, in which "blind denoising" means we don't require any supervision from clean graphs.…