Towards Knowledgeable Supervised Lifelong Learning Systems

Abstract

Learning a sequence of tasks is a long-standing challenge in machine learning. This setting applies to learning systems that observe examples of a range of tasks at different points in time. A learning system should become more knowledgeable as more related tasks are learned. Although the problem of learning sequentially was acknowledged for the first time decades ago, the research in this area has been rather limited. Research in transfer learning, multitask learning, metalearning and deep learning has studied some challenges of these kinds of systems. Recent research in lifelong machine learning and continual learning has revived interest in this problem. We propose Proficiente, a full framework for long-term learning systems. Proficiente relies on knowledge transferred between hypotheses learned with Support Vector Machines. The first component of the framework is focused on transferring forward selectively from a set of existing hypotheses or functions representing knowledge acquired during previous tasks to a new target task. A second component of Proficiente is focused on transferring backward, a novel ability of long-term learning systems that aim to exploit knowledge derived from recent tasks to encourage refinement of existing knowledge. We propose a method that transfers selectively from a task learned recently to existing hypotheses representing previous tasks. The method encourages retention of existing knowledge whilst refining. We analyse the theoretical properties of the proposed framework. Proficiente is accompanied by an agnostic metric that can be used to determine if a long-term learning system is becoming more knowledgeable. We evaluate Proficiente in both synthetic and real-world datasets, and demonstrate scenarios where knowledgeable supervised learning systems can be achieved by means of transfer.

CoLLIE: Continual Learning of Language Grounding from Language-Image Embeddings

“…Whereas most previous studies on continual learning have focused on incremental class learning in image classification (e.g., Rebuffi et al, 2017;Benavides-Prado et al, 2020), we have addressed a somewhat different problem.…”

Adaptive Orthogonal Projection for Batch and Online Continual Learning

“…Several works have performed knowledge transfer across tasks (Ke, Liu, and Huang 2020;Ke et al 2021;Schwarz et al 2018;Fernando et al 2017;Rusu et al 2016). Early techniques under lifelong learning mainly perform knowledge transfer but do not tackle CF (Chen and Liu 2014;Ruvolo and Eaton 2013;Benavides-Prado, Koh, and Riddle 2020).…”

“…They typically save some randomly selected exemplars or the mean of each class. In testing, a distance function over the nearest exemplar/class mean is used for classification (Rebuffi et al 2017;Lee et al 2018;Javed and Shafait 2018;Bendale and Boult 2015). AOP does not use any of these approaches.…”

A Theory for Knowledge Transfer in Continual Learning

“…Beyond catastrophic forgetting, the classic aim of continual learning systems has been to achieve increasingly knowledgeable systems (Ring, 1997;Chen & Liu, 2018). Knowledge transfer has been proposed as a mechanism to achieve this (Ke et al, 2020;Rostami et al, 2020;Benavides-Prado, 2020). Forward transfer with continual deep neural networks has been studied recently (Ke et al, 2021).…”

“…Backward transfer on the other hand has been paid much less attention in continual learning with deep neural networks (Riemer et al, 2018;Ke et al, 2020;Vogelstein et al, 2020;New et al, 2022). However, backward transfer has succeeded in other lifelong learning studies that use techniques such as Support Vector Machines (SVMs) (Benavides-Prado et al, 2020), and continues to be a desired property of continual learning systems (Rish, 2022).…”