In multi-task reinforcement learning there are two main challenges: at training time, the ability to learn different policies with a single model; at test time, inferring which of those policies applying without an external signal. In the case of continual reinforcement learning a third challenge arises: learning tasks sequentially without forgetting the previous ones. In this paper, we tackle these challenges by proposing DisCoRL, an approach combining state representation learning and policy distillation. We experiment on a sequence of three simulated 2D navigation tasks with a 3 wheel omni-directional robot. Moreover, we tested our approach's robustness by transferring the final policy into a real life setting. The policy can solve all tasks and automatically infer which one to run.
We focus on the problem of teaching a robot to solve tasks presented sequentially, i.e., in a continual learning scenario. The robot should be able to solve all tasks it has encountered, without forgetting past tasks. We provide preliminary work on applying Reinforcement Learning to such setting, on 2D navigation tasks for a 3 wheel omni-directional robot. Our approach takes advantage of state representation learning and policy distillation. Policies are trained using learned features as input, rather than raw observations, allowing better sample efficiency. Policy distillation is used to comb…
Internalizing Agent Experience into Diffusion Model Weights via On-Policy Context Distillation
Harbin Institute of Technology（哈尔滨工业大学）；Shanghai AI Laboratory（上海人工智能实验室）；Shandong University（山东大学）；Nanyang Technological University（南洋理工大学）；Shanghai Jiao Tong University（上海交通大学）
Suzhou University of Science and Technology（苏州科技大学）；Tianjin University（天津大学）
Rehearsal, retraining on a stored small data subset of old tasks, has been proven effective in solving catastrophic forgetting in continual learning. However, due to the sampled data may have a large bias towards the original dataset, retraining them is susceptible to driving continual domain drift of old tasks in feature space, resulting in forgetting. In this paper, we focus on tackling the continual domain drift problem with centroid distance distillation. First, we propose a centroid caching mechanism for sampling data points based on constructed centroids to reduce the sample bias in rehe…
In this paper, we propose a novel training procedure for the continual representation learning problem in which a neural network model is sequentially learned to alleviate catastrophic forgetting in visual search tasks. Our method, called Contrastive Supervised Distillation (CSD), reduces feature forgetting while learning discriminative features. This is achieved by leveraging labels information in a distillation setting in which the student model is contrastively learned from the teacher model. Extensive experiments show that CSD performs favorably in mitigating catastrophic forgetting by out…
Contrastive Continual Learning with Importance Sampling and Prototype-Instance Relation Distillation
Sun Yat-sen University（中山大学）；Mohamed bin Zayed University of Artificial Intelligence（穆罕默德·本·扎耶德人工智能大学）；The Hong Kong University of Science and Technology (Guangzhou)（香港科技大学（广州））；The Hong Kong University of Science and Technology（香港科技大学）
University of Pisa（比萨大学）；Scuola Normale Superiore（比萨高等师范学校）；Computer Vision Center（计算机视觉中心）
Distributed learning on the edge often comprises self-centered devices (SCD) which learn local tasks independently and are unwilling to contribute to the performance of other SDCs. How do we achieve forward transfer at zero cost for the single SCDs? We formalize this problem as a Distributed Continual Learning scenario, where SCD adapt to local tasks and a CL model consolidates the knowledge from the resulting stream of models without looking at the SCD's private data. Unfortunately, current CL methods are not directly applicable to this scenario. We propose Data-Agnostic Consolidation (DAC), …
Current deep learning models often suffer from catastrophic forgetting of old knowledge when continually learning new knowledge. Existing strategies to alleviate this issue often fix the trade-off between keeping old knowledge (stability) and learning new knowledge (plasticity). However, the stability-plasticity trade-off during continual learning may need to be dynamically changed for better model performance. In this paper, we propose two novel ways to adaptively balance model stability and plasticity. The first one is to adaptively integrate multiple levels of old knowledge and transfer it …
Dynamic Sub-graph Distillation for Robust Semi-supervised Continual Learning
Tianjin University（天津大学）；College of Intelligence and Computing, Tianjin University（天津大学智能与计算学部）；Haihe Laboratory of Information Technology Application Innovation（海河信息技术应用创新实验室）
Pushing the Limits of Distillation-Based Continual Learning via Classifier-Proximal Lightweight Plugins
National Key Laboratory for Novel Software Technology, Nanjing University, China（南京大学计算机软件新技术国家重点实验室）；School of Artificial Intelligence, Nanjing University, China（南京大学人工智能学院）；Department of Computer Science and Technology, Nanjing University, China（南京大学计算机科学与技术系）；School of Electronic Science and Engineering, Nanjing University, China（南京大学电子科学与工程学院）
Federated Learning has been introduced as a new machine learning paradigm enhancing the use of local devices. At a server level, FL regularly aggregates models learned locally on distributed clients to obtain a more general model. Current solutions rely on the availability of large amounts of stored data at the client side in order to fine-tune the models sent by the server. Such setting is not realistic in mobile pervasive computing where data storage must be kept low and data characteristic can change dramatically. To account for this variability, a solution is to use the data regularly coll…
Training models continually to detect and classify objects, from new classes and new domains, remains an open problem. In this work, we conduct a thorough analysis of why and how object detection models forget catastrophically. We focus on distillation-based approaches in two-stage networks; the most-common strategy employed in contemporary continual object detection work.Distillation aims to transfer the knowledge of a model trained on previous tasks -- the teacher -- to a new model -- the student -- while it learns the new task. We show that this works well for the region proposal network, b…
The size and the computational load of fine-tuning large-scale pre-trained neural network are becoming two major obstacles in adopting machine learning in many applications. Continual learning (CL) can serve as a remedy through enabling knowledge-transfer across sequentially arriving tasks which relaxes the need to fine-tune all network weights from scratch. However, existing CL algorithms primarily consider learning unimodal vision-only or language-only tasks. We develop a transformer-based CL architecture for learning bimodal vision-and-language tasks based on increasing the number of the le…
Category Adaptation Meets Projected Distillation in Generalized Continual Category Discovery
IDEAS NCBR；Warsaw University of Technology（华沙理工大学）；Gdańsk University of Technology（格但斯克理工大学）；Tooploox；Autonomous University of Barcelona（巴塞罗那自治大学）；Computer Vision Center（计算机视觉中心）
SAE-FD: Sparse Autoencoder Feature Distillation for Continual Learning of Large Language Models
The Hong Kong University of Science and Technology (Guangzhou)（香港科技大学（广州））；Nanjing University of Aeronautics and Astronautics（南京航空航天大学）；The 63rd Research Institute, National University of Defense Technology, Nanjing（国防科技大学第六十三研究所，南京）
China University of Petroleum Beijing (CUP)（中国石油大学（北京））
Continual learning aims to rapidly and continually learn the current task from a sequence of tasks. Compared to other kinds of methods, the methods based on experience replay have shown great advantages to overcome catastrophic forgetting. One common limitation of this method is the data imbalance between the previous and current tasks, which would further aggravate forgetting. Moreover, how to effectively address the stability-plasticity dilemma in this setting is also an urgent problem to be solved. In this paper, we overcome these challenges by proposing a novel framework called Meta-learni…
Over the last few decades, artificial intelligence research has made tremendous strides, but it still heavily relies on fixed datasets in stationary environments. Continual learning is a growing field of research that examines how AI systems can learn sequentially from a continuous stream of linked data in the same way that biological systems do. Simultaneously, fake media such as deepfakes and synthetic face images have emerged as significant to current multimedia technologies. Recently, numerous method has been proposed which can detect deepfakes with high accuracy. However, they suffer sign…
Adapt Your Teacher: Improving Knowledge Distillation for Exemplar-free Continual Learning
Warsaw University of Technology（华沙理工大学）；IDEAS NCBR；Jagiellonian University（雅盖隆大学）；Gdańsk University of Technology（格但斯克理工大学）；Autonomous University of Barcelona（巴塞罗那自治大学）；Computer Vision Center（计算机视觉中心）；Tooploox
University of Trento（特伦托大学）；SAP AI Research（SAP人工智能研究院）；LTCI, Télécom Paris, Institut Polytechnique de Paris（巴黎理工学院巴黎电信LTCI实验室）；Fondazione Bruno Kessler（布鲁诺·凯斯勒基金会）
Continual Learning (CL) aims to develop agents emulating the human ability to sequentially learn new tasks while being able to retain knowledge obtained from past experiences. In this paper, we introduce the novel problem of Memory-Constrained Online Continual Learning (MC-OCL) which imposes strict constraints on the memory overhead that a possible algorithm can use to avoid catastrophic forgetting. As most, if not all, previous CL methods violate these constraints, we propose an algorithmic solution to MC-OCL: Batch-level Distillation (BLD), a regularization-based CL approach, which effective…
Tianjin University（天津大学）；Binghamton University, State University of New York（纽约州立大学宾汉姆顿分校）
General Continual Learning (GCL) aims at learning from non independent and identically distributed stream data without catastrophic forgetting of the old tasks that don't rely on task boundaries during both training and testing stages. We reveal that the relation and feature deviations are crucial problems for catastrophic forgetting, in which relation deviation refers to the deficiency of the relationship among all classes in knowledge distillation, and feature deviation refers to indiscriminative feature representations. To this end, we propose a Complementary Calibration (CoCa) framework by…
Seoul National University（首尔大学）；DeepBrain AI Inc.（深脑人工智能公司）；Ewha Womans University（梨花女子大学）
The aim of continual learning is to learn new tasks continuously (i.e., plasticity) without forgetting previously learned knowledge from old tasks (i.e., stability). In the scenario of online continual learning, wherein data comes strictly in a streaming manner, the plasticity of online continual learning is more vulnerable than offline continual learning because the training signal that can be obtained from a single data point is limited. To overcome the stability-plasticity dilemma in online continual learning, we propose an online continual learning framework named multi-scale feature adapt…
Self-Supervised Continual Graph Learning in Adaptive Riemannian Spaces
North China Electric Power University（华北电力大学）；Beijing University of Posts and Telecommunications（北京邮电大学）；Beihang University（北京航空航天大学）；University of Illinois at Chicago（伊利诺伊大学芝加哥分校）
The University of Modena and Reggio Emilia（摩德纳-雷焦艾米利亚大学）
The staple of human intelligence is the capability of acquiring knowledge in a continuous fashion. In stark contrast, Deep Networks forget catastrophically and, for this reason, the sub-field of Class-Incremental Continual Learning fosters methods that learn a sequence of tasks incrementally, blending sequentially-gained knowledge into a comprehensive prediction. This work aims at assessing and overcoming the pitfalls of our previous proposal Dark Experience Replay (DER), a simple and effective approach that combines rehearsal and Knowledge Distillation. Inspired by the way our minds constantl…
Tianjin University（天津大学）；Shanghai Artificial Intelligence Laboratory（上海人工智能实验室）；The University of Sheffield（谢菲尔德大学）
Vision Language Models (VLMs), pre-trained on large-scale image-text datasets, enable zero-shot predictions for unseen data but may underperform on specific unseen tasks. Continual learning (CL) can help VLMs effectively adapt to new data distributions without joint training, but faces challenges of catastrophic forgetting and generalization forgetting. Although significant progress has been achieved by distillation-based methods, they exhibit two severe limitations. One is the popularly adopted single-teacher paradigm fails to impart comprehensive knowledge, The other is the existing methods …
