Class incremental learning consists in training discriminative models to classify an increasing number of classes over time. However, doing so using only the newly added class data leads to the known problem of catastrophic forgetting of the previous classes. Recently, dynamic deep learning architectures have been shown to exhibit a better stability-plasticity trade-off by dynamically adding new feature extractors to the model in order to learn new classes followed by a compression step to scale the model back to its original size, thus avoiding a growing number of parameters. In this context, we propose a new algorithm that enhances the compression of previous class knowledge by cutting and mixing patches of previous class samples with the new images during compression using our Rehearsal-CutMix method. We show that this new data augmentation reduces catastrophic forgetting by specifically targeting past class information and improving its compression. Extensive experiments performed on the CIFAR and ImageNet datasets under diverse incremental learning evaluation protocols demonstrate that our approach consistently outperforms the state-of-the-art . The code will be made available upon publication of our work.
Odessa Competence Center for Artificial intelligence and Machine learning（敖德萨人工智能与机器学习能力中心）
The ability to find short representations, i.e. to compress data, is crucial for many intelligent systems. We present a theory of incremental compression showing that arbitrary data strings, that can be described by a set of features, can be compressed by searching for those features incrementally, which results in a partition of the information content of the string into a complete set of pairwise independent pieces. The description length of this partition turns out to be close to optimal in terms of the Kolmogorov complexity of the string. Exploiting this decomposition, we introduce ALICE -…
The ability to learn new concepts continually is necessary in this ever-changing world. However, deep neural networks suffer from catastrophic forgetting when learning new categories. Many works have been proposed to alleviate this phenomenon, whereas most of them either fall into the stability-plasticity dilemma or take too much computation or storage overhead. Inspired by the gradient boosting algorithm to gradually fit the residuals between the target model and the previous ensemble model, we propose a novel two-stage learning paradigm FOSTER, empowering the model to learn new categories ad…
Context-Driven Incremental Compression for Multi-Turn Dialogue Generation
The Hong Kong University of Science and Technology（香港科技大学）；NVIDIA AI Technology Center（NVIDIA AI技术中心）；Shanghai Jiao Tong University（上海交通大学）；The Chinese University of Hong Kong（香港中文大学）
Indian Institute of Technology, Madras（印度理工学院马德拉斯分校）；CY Université（CY塞尔吉巴黎大学）；ENSEA（ENSEA工程师学院）；CNRS（法国国家科学研究中心）
This paper introduces an incremental training framework for compressing popular Deep Neural Network (DNN) based unfolded multiple-input-multiple-output (MIMO) detection algorithms like DetNet. The idea of incremental training is explored to select the optimal depth while training. To reduce the computation requirements or the number of FLoating point OPerations (FLOPs) and enforce sparsity in weights, the concept of structured regularization is explored using group LASSO and sparse group LASSO. Our methods lead to an astounding $98.9\%$ reduction in memory requirement and $81.63\%$ reduction i…
REAL: Representation Enhanced Analytic Learning for Exemplar-free Class-incremental Learning
Shien-Ming Wu School of Intelligent Engineering（申铭武智能工程学院）；School of Future Technology（未来技术学院）；Department of Electrical and Electronic Engineering（电气与电子工程系）
Multi-View Incremental Learning with Structured Hebbian Plasticity for Enhanced Fusion Efficiency
Fuzhou University（福州大学）；Guangdong Institute of Intelligence Science and Technology（广东智能科学与技术研究院）；University of Electronic Science and Technology of China（电子科技大学）；Tsinghua University（清华大学）；Dalian University of Technology（大连理工大学）
Zhejiang University of Technology（浙江工业大学）；Hangzhou Dianzi University（杭州电子科技大学）
Graph classification is crucial in network analyses. Networks face potential security threats, such as adversarial attacks. Some defense methods may trade off the algorithm complexity for robustness, such as adversarial training, whereas others may trade off clean example performance, such as smoothingbased defense. Most suffer from high complexity or low transferability. To address this problem, we proposed EGC2, an enhanced graph classification model with easy graph compression. EGC2 captures the relationship between the features of different nodes by constructing feature graphs and improvin…
NEC Corporation（日本电气公司）；RIKEN Center for Advanced Intelligence Project (RIKEN AIP)（理化学研究所先进智能项目中心）
Neural networks using numerous text data have been successfully applied to a variety of tasks. While massive text data is usually compressed using techniques such as grammar compression, almost all of the previous machine learning methods assume already decompressed sequence data as their input. In this paper, we propose a method to directly apply neural sequence models to text data compressed with grammar compression algorithms without decompression. To encode the unique symbols that appear in compression rules, we introduce composer modules to incrementally encode the symbols into vector rep…
Tsinghua University（清华大学）；Tsinghua-Peking Center for Life Sciences（清华-北大生命科学联合中心）；Huawei Noah’s Ark Lab（华为诺亚方舟实验室）；Renmin University of China（中国人民大学）
Continual learning needs to overcome catastrophic forgetting of the past. Memory replay of representative old training samples has been shown as an effective solution, and achieves the state-of-the-art (SOTA) performance. However, existing work is mainly built on a small memory buffer containing a few original data, which cannot fully characterize the old data distribution. In this work, we propose memory replay with data compression (MRDC) to reduce the storage cost of old training samples and thus increase their amount that can be stored in the memory buffer. Observing that the trade-off bet…
Solomonoff's general theory of inference and the Minimum Description Length principle formalize Occam's razor, and hold that a good model of data is a model that is good at losslessly compressing the data, including the cost of describing the model itself. Deep neural networks might seem to go against this principle given the large number of parameters to be encoded. We demonstrate experimentally the ability of deep neural networks to compress the training data even when accounting for parameter encoding. The compression viewpoint originally motivated the use of variational methods in neural n…
This study presents an efficient incremental/decremental approach for big streams based on Kernel Ridge Regression (KRR), a frequently used data analysis in cloud centers. To avoid reanalyzing the whole dataset whenever sensors receive new training data, typical incremental KRR used a single-instance mechanism for updating an existing system. However, this inevitably increased redundant computational time, not to mention applicability to big streams. To this end, the proposed mechanism supports incremental/decremental processing for both single and multiple samples (i.e., batch processing). A …
University of Colorado, Colorado Springs CO 80918, USA , University of Colorado, Colorado Springs CO 80918, USA
The classification of textual data often yields important information. Most classifiers work in a closed world setting where the classifier is trained on a known corpus, and then it is tested on unseen examples that belong to one of the classes seen during training. Despite the usefulness of this design, often there is a need to classify unseen examples that do not belong to any of the classes on which the classifier was trained. This paper describes the open set scenario where unseen examples from previously unseen classes are handled while testing. This further examines a process of enhanced…
