Sequential Learning

Sequential learning focuses on training machine learning models on data arriving in a sequence of tasks, aiming to mitigate catastrophic forgetting—the loss of previously learned knowledge. Current research emphasizes developing algorithms and architectures, such as continual learning frameworks, graph neural networks, and transformer models, to address this challenge and improve knowledge transfer between tasks, often incorporating techniques like knowledge distillation and bias pruning. This field is crucial for building adaptable AI systems capable of handling real-world data streams in applications ranging from recommendation systems and medical image analysis to robotics and materials science.

Papers

June 25, 2022

Making Look-Ahead Active Learning Strategies Feasible with Neural Tangent Kernels
Mohamad Amin Mohamadi, Wonho Bae, Danica J. Sutherland
Active Learning Deep Network Neural Tangent Kernel Sequential Learning Pool Based Active Learning

May 20, 2022

Explanatory machine learning for sequential human teaching
Lun Ai, Johannes Langer, Stephen H. Muggleton, Ute Schmid
Sequential Learning Concept Learning Inductive Logic Programming Interpretable Machine Learning Logic Program

May 17, 2022

Learnable Optimal Sequential Grouping for Video Scene Detection
Daniel Rotman, Yevgeny Yaroker, Elad Amrani, Udi Barzelay, Rami Ben-Ari
Sequential Learning Optimal Grouping Scene Detection

May 13, 2022

Large-Scale Sequential Learning for Recommender and Engineering Systems
Aleksandra Burashnikova
Gradient Descent Recommender System Movie Recommendation Sequential Learning Fading Memory Engineering System

May 4, 2022

Multivariate Prediction Intervals for Random Forests
Brendan Folie, Maxwell Hutchinson
Random Forest Sequential Learning Prediction Interval Accurate Uncertainty Iterative Design

April 27, 2022

Autonomous Vehicle Calibration via Linear Optimization
Georg Novotny, Yuzhou Liu, Wilfried Wöber, Cristina Olaverri-Monreal
Leg ODOmetry Sequential Learning Linear Programming Sensor Calibration Dead Reckoning

April 25, 2022

Loss-based Sequential Learning for Active Domain Adaptation
Kyeongtak Han, Youngeun Kim, Dongyoon Han, Sungeun Hong
Domain Adaptation Sequential Learning Query Learning Active Domain Adaptation

April 5, 2022

Generative Enriched Sequential Learning (ESL) Approach for Molecular Design via Augmented Domain Knowledge
Mohammad Sajjad Ghaemi, Karl Grantham, Isaac Tamblyn, Yifeng Li, Hsu Kiang Ooi
Constructive Approach Molecular Design Sequential Learning Novel Molecule Molecular Fingerprint Chemical Discovery

March 23, 2022

Asynchronous Reinforcement Learning for Real-Time Control of Physical Robots
Yufeng Yuan, A. Rupam Mahmood
Reinforcement Learning Real Time Sequential Learning Physical Robot Real World Reinforcement Learning Asynchronous Learning

February 1, 2022

Regression Transformer: Concurrent sequence regression and generation for molecular language modeling
Jannis Born, Matteo Manica
Generative Model Faithful Generation Molecule Generation Sequential Learning Molecule Text

January 27, 2022

Grad2Task: Improved Few-shot Text Classification Using Gradients for Task Representation
Jixuan Wang, Kuan-Chieh Wang, Frank Rudzicz, Michael Brudno
Sequential Learning Task Specification Shot Text Classification

January 19, 2022

Batch versus Sequential Active Learning for Recommender Systems
Toon De Pessemier, Sander Vanhove, Luc Martens
Active Learning Recommender System Sequential Learning ActIve Learning algORithm Batch Greenkhorn Active Learner

December 31, 2021

Training Recurrent Neural Networks by Sequential Least Squares and the Alternating Direction Method of Multipliers
Alberto Bemporad
Nonlinear Dynamic Sequential Learning Alternating Direction Method of Multiplier Nonlinear System Identification Class Wise Multiplier

December 10, 2021

Blockwise Sequential Model Learning for Partially Observable Reinforcement Learning
Giseung Park, Sungho Choi, Youngchul Sung
Markov Decision Process Sequential Learning Partially Observable Markov Decision Process Sequential Model Sequential Information

December 3, 2021

Learning Curves for Continual Learning in Neural Networks: Self-Knowledge Transfer and Forgetting
Ryo Karakida, Shotaro Akaho
Neural Network Strong Generalization Transfer Learning Continual LEArning Generalization Performance Sequential Learning Learning Curve

November 11, 2021

Kronecker Factorization for Preventing Catastrophic Forgetting in Large-scale Medical Entity Linking
Denis Jered McInerney, Luyang Kong, Kristjan Arumae, Byron Wallace, Parminder Bhatia
Multi Task Learning Catastrophic Forgetting BERT Model Sequential Learning Kronecker Product Biomedical Entity Linking

November 5, 2021

Supervised Advantage Actor-Critic for Recommender Systems
Xin Xin, Alexandros Karatzoglou, Ioannis Arapakis, Joemon M. Jose
Reinforcement Learning Recommender System Sequential Recommendation Sequential Learning Advantage Actor Critic