Strong Generalization

Strong generalization, the ability of machine learning models to perform well on unseen data, is a central objective in current research. Active areas of investigation include improving the robustness of self-supervised learning, understanding the optimization dynamics of transformers and other architectures (including CNNs and RNNs), and developing methods to enhance generalization through data augmentation, regularization techniques (e.g., logical regularization, consistency regularization), and improved training strategies (e.g., few-shot learning, meta-learning). These advancements are crucial for building reliable and adaptable AI systems across diverse applications, from image classification and natural language processing to healthcare and robotics.

Papers

August 21, 2022

DiscrimLoss: A Universal Loss for Hard Samples and Incorrect Samples Discrimination
Tingting Wu, Xiao Ding, Hao Zhang, Jinglong Gao, Li Du, Bing Qin, Ting Liu
Strong Generalization Self Supervised Curriculum Learning Model Generalization Hard Sample

August 19, 2022

Intersection of Parallels as an Early Stopping Criterion
Ali Vardasbi, Maarten de Rijke, Mostafa Dehghani
Strong Generalization Supervised Learning Intersection Scenario Model Overfitting Better Generalization Early Stopping Parallel Text

August 18, 2022

Domain-Specific Risk Minimization for Out-of-Distribution Generalization
Yi-Fan Zhang, Jindong Wang, Jian Liang, Zhang Zhang, Baosheng Yu, Liang Wang, Dacheng Tao, Xing Xie
Strong Generalization Distribution Generalization

August 17, 2022

Investigating the Impact of Model Width and Density on Generalization in Presence of Label Noise
Yihao Xue, Kyle Whitecross, Baharan Mirzasoleiman
Strong Generalization Noisy Label Label Noise Speech Presence Model Size Double Descent Particle Density Optimal Generalization

August 16, 2022

August 12, 2022

Lattice Generalizations of the Concept of Fuzzy Numbers and Zadeh's Extension Principle
Dmitry Maximov
Strong Generalization High Impact Concept Cognitive Map Distributive Lattice Lattice Volume Fuzzy Number Natural Extension

August 10, 2022

Semantic Self-adaptation: Enhancing Generalization with a Single Sample
Sherwin Bahmani, Oliver Hahn, Eduard Zamfir, Nikita Araslanov, Daniel Cremers, Stefan Roth
Semantic Segmentation Strong Generalization Convolutional Layer Neural Network Generalization Self Adaptation Single Sample

August 9, 2022

Intrinsically Motivated Learning of Causal World Models
Louis Annabi
Reinforcement Learning Strong Generalization Causal Structure Sensorimotor Norm General Intelligence Causal World Model

August 8, 2022

Generalization and Overfitting in Matrix Product State Machine Learning Architectures
Artem Strashko, E. Miles Stoudenmire
Strong Generalization Model Overfitting Generalization Property Matrix Product State

August 7, 2022

August 4, 2022

Homomorphisms Between Transfer, Multi-Task, and Meta-Learning Systems
Tyler Cody
LeArning Abstract Strong Generalization Transfer Learning Multi Task Learning Multi Task Formality Transfer

August 2, 2022

Semantic Data Augmentation based Distance Metric Learning for Domain Generalization
Mengzhu Wang, Jianlong Yuan, Qi Qian, Zhibin Wang, Hao Li
Data Augmentation Strong Generalization Domain Generalization Metric Learning Target Domain

July 29, 2022

A Survey of Learning on Small Data: Generalization, Optimization, and Challenge
Xiaofeng Cao, Weixin Bu, Shengjun Huang, Minling Zhang, Ivor W. Tsang, Yew Soon Ong, James T. Kwok
LeArning Abstract Strong Generalization Active Learning Optimization Purpose Shot Learning Meta Learning Challenge Task Small Datasets Data Representation

July 28, 2022

Combining human parsing with analytical feature extraction and ranking schemes for high-generalization person reidentification
Nikita Gabdullin
Deep Learning Strong Generalization Cross Domain Person Re Identification Feature Extraction Human Parsing

July 20, 2022

Probable Domain Generalization via Quantile Risk Minimization
Cian Eastwood, Alexander Robey, Shashank Singh, Julius von Kügelgen, Hamed Hassani, George J. Pappas, Bernhard Schölkopf
Strong Generalization Domain Generalization Training Distribution Unseen Test Distribution Quantile Temporal Difference

July 18, 2022

Towards a General Pre-training Framework for Adaptive Learning in MOOCs
Qingyang Zhong, Jifan Yu, Zheyuan Zhang, Yiming Mao, Yuquan Wang, Yankai Lin, Lei Hou, Juanzi Li, Jie Tang
Strong Generalization New Framework Adaptive Learning Sequential Learning General Text Massive Open Online Course Heterogeneous Learning Adaptive System

July 16, 2022

Approximation Capabilities of Neural Networks using Morphological Perceptrons and Generalizations
William Chang, Hassan Hamad, Keith M. Chugg
Neural Network Strong Generalization Standard Deep Nonlinear Activation Artificial Neural Network Approximation Capability Morphological Neural Network

Strong Generalization

Papers

DiscrimLoss: A Universal Loss for Hard Samples and Incorrect Samples Discrimination

Intersection of Parallels as an Early Stopping Criterion

Domain-Specific Risk Minimization for Out-of-Distribution Generalization

Investigating the Impact of Model Width and Density on Generalization in Presence of Label Noise

On the generalization of learning algorithms that do not converge

Counterfactual Supervision-based Information Bottleneck for Out-of-Distribution Generalization

Lattice Generalizations of the Concept of Fuzzy Numbers and Zadeh's Extension Principle

Semantic Self-adaptation: Enhancing Generalization with a Single Sample

Intrinsically Motivated Learning of Causal World Models

Generalization and Overfitting in Matrix Product State Machine Learning Architectures

Learning Modular Structures That Generalize Out-of-Distribution

A Game-Theoretic Perspective of Generalization in Reinforcement Learning

Label-Efficient Domain Generalization via Collaborative Exploration and Generalization

Homomorphisms Between Transfer, Multi-Task, and Meta-Learning Systems

Semantic Data Augmentation based Distance Metric Learning for Domain Generalization

A Survey of Learning on Small Data: Generalization, Optimization, and Challenge

Combining human parsing with analytical feature extraction and ranking schemes for high-generalization person reidentification

Probable Domain Generalization via Quantile Risk Minimization

Towards a General Pre-training Framework for Adaptive Learning in MOOCs

Approximation Capabilities of Neural Networks using Morphological Perceptrons and Generalizations