Self-Paced Multitask Learning with Shared Knowledge

Murugesan, Keerthiram; Carbonell, Jaime G.

doi:10.24963/ijcai.2017/351

Cited by 21 publications

(16 citation statements)

References 1 publication

Supporting

Mentioning

Contrasting

Order By: Relevance

“…These models have achieved good results in solving small-scale data problems. In addition, with the development of Self-Paced Learning (SPL) [20], many excellent self-paced multi-task Learning models have been proposed, such as SPMTL [21] and spMMTL [22]. SPL is defined as a supervised learning method which gradually adds samples to train from simplicity to difficulty, and it could typically reduce the risk of achieving local optima.…”

Section: B Multi-task Learningmentioning

confidence: 99%

See 1 more Smart Citation

The Effective Methods for Intrusion Detection With Limited Network Attack Data: Multi-Task Learning and Oversampling

et al. 2020

View full text Add to dashboard Cite

Recently, many anomaly intrusion detection algorithms have been developed and applied in network security. These algorithms achieve high detection rate on many classical datasets. However, most of them failed to address two challenges: 1) imbalanced traffic data with limited network attack, 2) multiple data sources that are distributed in different terminals. In detail, those algorithms assume that there are sufficient network traffic data to train their models for intrusion detection. Due to the network attack traffic is always scarce in the real-world network, this assumption is difficult to satisfy in most cases. In this paper, we use Multi-Task Learning (MTL) and oversampling methods to address those challenges of network intrusion detection. Firstly, we use the MTL method to treat each terminal as a single task, and then use relevant information between different terminals to help learn every single task. Meanwhile, we use the oversampling method to overcome the minority problem of attacks. Through a series of experiments on the latest UNSW-NB15 and CICIDS2018 datasets, this paper verifies the effectiveness of MTL and oversampling methods for network intrusion detection with limited network attack data, where they achieve more than 90% detection rate in different experimental settings.

show abstract

Section: B Multi-task Learningmentioning

confidence: 99%

“…2) Self-Paced Mean Regularized MTL [22] To address the unequal issue of all tasks, Self-Paced Mean Regularized MTL (spMMTL) is introduced. It is a new This work is licensed under a Creative Commons Attribution-NonCommercial-NoDerivatives 4.0 License.…”

Section: Multi-task Learning Algorithmsmentioning

confidence: 99%

The Effective Methods for Intrusion Detection With Limited Network Attack Data: Multi-Task Learning and Oversampling

et al. 2020

View full text Add to dashboard Cite

show abstract

“…Recently, self-paced multi-task learning (SPMTL) has been proposed for supervised problems. For instance, [46] proposed a self-paced task selection method for multi-task learning, and [47] proposed a novel multi-task learning framework that learns the tasks by simultaneously considering the order of both tasks and instances.…”

Section: Self-paced Learningmentioning

confidence: 99%

Self-paced multi-task clustering

et al. 2019

View full text Add to dashboard Cite

Multi-task clustering (MTC) has attracted a lot of research attentions in machine learning due to its ability in utilizing the relationship among different tasks. Despite the success of traditional MTC models, they are either easy to stuck into local optima, or sensitive to outliers and noisy data. To alleviate these problems, we propose a novel self-paced multi-task clustering (SPMTC) paradigm. In detail, SPMTC progressively selects data examples to train a series of MTC models with increasing complexity, thus highly decreases the risk of trapping into poor local optima. Furthermore, to reduce the negative influence of outliers and noisy data, we design a soft version of SPMTC to further improve the clustering performance. The corresponding SPMTC framework can be easily solved by an alternating optimization method. The proposed model is guaranteed to converge and experiments on real data sets have demonstrated its promising results compared with state-of-the-art multi-task clustering methods.

show abstract

“…Multi-task learning (MTL), the process of learning to solve multiple tasks at the same time, allows sharing information across related tasks, thereby improving model performance across all the tasks (Caruana 1993;Zamir et al 2018). Prior MTL studies can be divided into two categories, one is based on optimization (Li et al 2017;Murugesan and Carbonell 2017), and the other is based on parameter sharing approaches for deep neural networks.…”

Section: Introduction and Related Workmentioning

confidence: 99%

Adaptive Activation Network and Functional Regularization for Efficient and Flexible Deep Multi-Task Learning

Liu

Yang

Xie

et al. 2020

AAAI

View full text Add to dashboard Cite

Multi-task learning (MTL) is a common paradigm that seeks to improve the generalization performance of task learning by training related tasks simultaneously. However, it is still a challenging problem to search the flexible and accurate architecture that can be shared among multiple tasks. In this paper, we propose a novel deep learning model called Task Adaptive Activation Network (TAAN) that can automatically learn the optimal network architecture for MTL. The main principle of TAAN is to derive flexible activation functions for different tasks from the data with other parameters of the network fully shared. We further propose two functional regularization methods that improve the MTL performance of TAAN. The improved performance of both TAAN and the regularization methods is demonstrated by comprehensive experiments.

show abstract

Self-Paced Multitask Learning with Shared Knowledge

Cited by 21 publications

References 1 publication

The Effective Methods for Intrusion Detection With Limited Network Attack Data: Multi-Task Learning and Oversampling

The Effective Methods for Intrusion Detection With Limited Network Attack Data: Multi-Task Learning and Oversampling

Self-paced multi-task clustering

Adaptive Activation Network and Functional Regularization for Efficient and Flexible Deep Multi-Task Learning

Contact Info

Product

Resources

About