Adversarial Curriculum

Adversarial curriculum learning aims to improve model robustness and generalization by progressively increasing the difficulty of training data, often using contrastive learning methods to enhance feature representation. Current research focuses on applying this technique across diverse domains, including graph representation learning, indoor localization, and image processing, with various model architectures and algorithms being adapted to incorporate this strategy. This approach shows promise in improving the performance and resilience of machine learning models in challenging or adversarial environments, leading to more robust and reliable applications in various fields.

Papers

August 22, 2024

Multi-Task Curriculum Graph Contrastive Learning with Clustering Entropy Guidance
Chusheng Zeng, Bocheng Wang, Jinghui Yuan, Rong Wang, Mulin Chen
Contrastive Learning Graph Contrastive Learning Deep Graph Clustering Adversarial Curriculum

February 16, 2024

Adversarial Curriculum Graph Contrastive Learning with Pair-wise Augmentation
Xinjian Zhao, Liang Zhang, Yang Liu, Ruocheng Guo, Xiangyu Zhao
Contrastive Learning Graph Representation Learning Graph Contrastive Learning Adversarial Curriculum

November 10, 2023

CALLOC: Curriculum Adversarial Learning for Secure and Robust Indoor Localization
Danish Gufran, Sudeep Pasricha
Localization Focus Localization Accuracy Indoor Localization Adversarial Curriculum

October 9, 2023

WeatherDepth: Curriculum Contrastive Learning for Self-Supervised Depth Estimation under Adverse Weather Conditions
Jiyuan Wang, Chunyu Lin, Lang Nie, Shujun Huang, Yao Zhao, Xing Pan, Rui Ai
Depth Estimation Adverse Weather Self Supervised Depth Depth Estimation Model Weather Image Adversarial Curriculum Depth Cue

March 24, 2023

Curricular Contrastive Regularization for Physics-aware Single Image Dehazing
Yu Zheng, Jiahui Zhan, Shengfeng He, Junyu Dong, Yong Du
Image Dehazing Contrastive Regularization Adversarial Curriculum

February 25, 2023

DCLP: Neural Architecture Predictor with Curriculum Contrastive Learning
Shenghe Zheng, Hongzhi Wang, Tianyu Mu
Neural Architecture Search Unsupervised Training Adversarial Curriculum Neural Predictor

January 23, 2023

Semantic-aware Contrastive Learning for Electroencephalography-to-Text Generation with Curriculum Learning
Xiachong Feng, Xiaocheng Feng, Bing Qin
Contrastive Learning Curriculum Learning EEG Representation Adversarial Curriculum EEG to Text

June 21, 2022

Robust Deep Reinforcement Learning through Bootstrapped Opportunistic Curriculum
Junlin Wu, Yevgeniy Vorobeychik
Adversarial Robustness Adversarial Perturbation Robust Reinforcement Learning Robust Deep Reinforcement Learning Adversarial Curriculum

June 9, 2022

Learning to generalize Dispatching rules on the Job Shop Scheduling
Zangir Iklassov, Dmitrii Medvedev, Ruben Solozabal, Martin Takac
LeArning Abstract Strong Generalization Reinforcement Learning Approach Job Shop Scheduling Job Shop Scheduling Problem Adversarial Curriculum

April 7, 2022

Pretraining Text Encoders with Adversarial Mixture of Training Signal Generators
Yu Meng, Chenyan Xiong, Payal Bajaj, Saurabh Tiwary, Paul Bennett, Jiawei Han, Xia Song
Language Model Adversarial Learning Text Encoder Pre Training Model Pre Trained Text Adversarial Curriculum Training Data Generator Discriminative Sample Aware Loss Function

March 30, 2022

Weakly-supervised Temporal Path Representation Learning with Contrastive Curriculum Learning -- Extended Version
Sean Bin Yang, Chenjuan Guo, Jilin Hu, Bin Yang, Jian Tang, Christian S. Jensen
Extended Version 2 Dimensional Label Adversarial Curriculum Temporal Path Path Representation

November 26, 2021

Contrastive Object-level Pre-training with Spatial Noise Curriculum Learning
Chenhongyi Yang, Lichao Huang, Elliot J. Crowley
Contrastive Learning Contrastive Loss Detection Loss Adversarial Curriculum

Adversarial Curriculum

Papers

Multi-Task Curriculum Graph Contrastive Learning with Clustering Entropy Guidance

Adversarial Curriculum Graph Contrastive Learning with Pair-wise Augmentation

CALLOC: Curriculum Adversarial Learning for Secure and Robust Indoor Localization

WeatherDepth: Curriculum Contrastive Learning for Self-Supervised Depth Estimation under Adverse Weather Conditions

Curricular Contrastive Regularization for Physics-aware Single Image Dehazing

DCLP: Neural Architecture Predictor with Curriculum Contrastive Learning

Semantic-aware Contrastive Learning for Electroencephalography-to-Text Generation with Curriculum Learning

Robust Deep Reinforcement Learning through Bootstrapped Opportunistic Curriculum

Learning to generalize Dispatching rules on the Job Shop Scheduling

Pretraining Text Encoders with Adversarial Mixture of Training Signal Generators

Weakly-supervised Temporal Path Representation Learning with Contrastive Curriculum Learning -- Extended Version

Contrastive Object-level Pre-training with Spatial Noise Curriculum Learning