PyTorchKR Papers

최신 논문

총 2,786편
태그·기간 등 상세 필터

카테고리 탐색

로그인 후 이 태그 구독

arXiv:2206.05625

Exploring the Intersection between Neural Architecture Search and Continual Learning

Despite the significant advances achieved in Artificial Neural Networks (ANNs), their design process remains notoriously tedious, depending primarily on intuition, experience and trial-and-error. This human-dependent process is often time-consuming and prone to errors. Furthermore, the models are generally bound to their training contexts, with no considerations to their surrounding environments. Continual adaptiveness and automation of neural networks is of paramount importance to several domains where model accessibility is limited after deployment (e.g IoT devices, self-driving vehicles, etc.). Additionally, even accessible models require frequent maintenance post-deployment to overcome issues such as Concept/Data Drift, which can be cumbersome and restrictive. By leveraging and combining approaches from Neural Architecture Search (NAS) and Continual Learning (CL), more robust and adaptive agents can be developed. This study conducts the first extensive review on the intersection between NAS and CL, formalizing the prospective Continually-Adaptive Neural Networks (CANNs) paradigm and outlining research directions for lifelong autonomous ANNs.

arXiv:2206.04016공식 코드 · Papers with Code

SYNERgy between SYNaptic consolidation and Experience Replay for general continual learning

Continual learning (CL) in the brain is facilitated by a complex set of mechanisms. This includes the interplay of multiple memory systems for consolidating information as posited by the complementary learning systems (CLS) theory and synaptic consolidation for protecting the acquired knowledge from erasure. Thus, we propose a general CL method that creates a synergy between SYNaptic consolidation and dual memory Experience Replay (SYNERgy). Our method maintains a semantic memory that accumulates and consolidates information across the tasks and interacts with the episodic memory for effective replay. It further employs synaptic consolidation by tracking the importance of parameters during the training trajectory and anchoring them to the consolidated parameters in the semantic memory. To the best of our knowledge, our study is the first to employ dual memory experience replay in conjunction with synaptic consolidation that is suitable for general CL whereby the network does not utilize task boundaries or task labels during training or inference. Our evaluation on various challenging CL scenarios and characteristics analyses demonstrate the efficacy of incorporating both synaptic consolidation and CLS theory in enabling effective CL in DNNs.

arXiv:2206.03934

A Study of Continual Learning Methods for Q-Learning

We present an empirical study on the use of continual learning (CL) methods in a reinforcement learning (RL) scenario, which, to the best of our knowledge, has not been described before. CL is a very active recent research topic concerned with machine learning under non-stationary data distributions. Although this naturally applies to RL, the use of dedicated CL methods is still uncommon. This may be due to the fact that CL methods often assume a decomposition of CL problems into disjoint sub-tasks of stationary distribution, that the onset of these sub-tasks is known, and that sub-tasks are non-contradictory. In this study, we perform an empirical comparison of selected CL methods in a RL problem where a physically simulated robot must follow a racetrack by vision. In order to make CL methods applicable, we restrict the RL setting and introduce non-conflicting subtasks of known onset, which are however not disjoint and whose distribution, from the learner's point of view, is still non-stationary. Our results show that dedicated CL methods can significantly improve learning when compared to the baseline technique of "experience replay".

arXiv:2206.02916공식 코드 · Papers with Code

Remember the Past: Distilling Datasets into Addressable Memories for Neural Networks

We propose an algorithm that compresses the critical information of a large dataset into compact addressable memories. These memories can then be recalled to quickly re-train a neural network and recover the performance (instead of storing and re-training on the full original dataset). Building upon the dataset distillation framework, we make a key observation that a shared common representation allows for more efficient and effective distillation. Concretely, we learn a set of bases (aka ``memories'') which are shared between classes and combined through learned flexible addressing functions to generate a diverse set of training examples. This leads to several benefits: 1) the size of compressed data does not necessarily grow linearly with the number of classes; 2) an overall higher compression rate with more effective distillation is achieved; and 3) more generalized queries are allowed beyond recalling the original classes. We demonstrate state-of-the-art results on the dataset distillation task across six benchmarks, including up to 16.5% and 9.7% in retained accuracy improvement when distilling CIFAR10 and CIFAR100 respectively. We then leverage our framework to perform continual learning, achieving state-of-the-art results on four benchmarks, with 23.2% accuracy improvement on MANY. The code is released on our project webpage https://github.com/princetonvisualai/RememberThePast-DatasetDistillation.

arXiv:2206.02577

Effects of Auxiliary Knowledge on Continual Learning

In Continual Learning (CL), a neural network is trained on a stream of data whose distribution changes over time. In this context, the main problem is how to learn new information without forgetting old knowledge (i.e., Catastrophic Forgetting). Most existing CL approaches focus on finding solutions to preserve acquired knowledge, so working on the past of the model. However, we argue that as the model has to continually learn new tasks, it is also important to put focus on the present knowledge that could improve following tasks learning. In this paper we propose a new, simple, CL algorithm that focuses on solving the current task in a way that might facilitate the learning of the next ones. More specifically, our approach combines the main data stream with a secondary, diverse and uncorrelated stream, from which the network can draw auxiliary knowledge. This helps the model from different perspectives, since auxiliary data may contain useful features for the current and the next tasks and incoming task classes can be mapped onto auxiliary classes. Furthermore, the addition of data to the current task is implicitly making the classifier more robust as we are forcing the extraction of more discriminative features. Our method can outperform existing state-of-the-art models on the most common CL Image Classification benchmarks.

arXiv:2206.00719공식 코드 · Papers with Code

Dataset Distillation using Neural Feature Regression

Dataset distillation aims to learn a small synthetic dataset that preserves most of the information from the original dataset. Dataset distillation can be formulated as a bi-level meta-learning problem where the outer loop optimizes the meta-dataset and the inner loop trains a model on the distilled data. Meta-gradient computation is one of the key challenges in this formulation, as differentiating through the inner loop learning procedure introduces significant computation and memory costs. In this paper, we address these challenges using neural Feature Regression with Pooling (FRePo), achieving the state-of-the-art performance with an order of magnitude less memory requirement and two orders of magnitude faster training than previous methods. The proposed algorithm is analogous to truncated backpropagation through time with a pool of models to alleviate various types of overfitting in dataset distillation. FRePo significantly outperforms the previous methods on CIFAR100, Tiny ImageNet, and ImageNet-1K. Furthermore, we show that high-quality distilled data can greatly improve various downstream applications, such as continual learning and membership inference defense. Please check out our webpage at https://sites.google.com/view/frepo.

arXiv:2206.00388공식 코드 · Papers with Code

Transfer without Forgetting

This work investigates the entanglement between Continual Learning (CL) and Transfer Learning (TL). In particular, we shed light on the widespread application of network pretraining, highlighting that it is itself subject to catastrophic forgetting. Unfortunately, this issue leads to the under-exploitation of knowledge transfer during later tasks. On this ground, we propose Transfer without Forgetting (TwF), a hybrid approach building upon a fixed pretrained sibling network, which continuously propagates the knowledge inherent in the source domain through a layer-wise loss term. Our experiments indicate that TwF steadily outperforms other CL methods across a variety of settings, averaging a 4.81% gain in Class-Incremental accuracy over a variety of datasets and different buffer sizes.

arXiv:2206.00309공식 코드 · Papers with Code

Label-Efficient Online Continual Object Detection in Streaming Video

Humans can watch a continuous video stream and effortlessly perform continual acquisition and transfer of new knowledge with minimal supervision yet retaining previously learnt experiences. In contrast, existing continual learning (CL) methods require fully annotated labels to effectively learn from individual frames in a video stream. Here, we examine a more realistic and challenging problem$\unicode{x2014}$Label-Efficient Online Continual Object Detection (LEOCOD) in streaming video. We propose a plug-and-play module, Efficient-CLS, that can be easily inserted into and improve existing continual learners for object detection in video streams with reduced data annotation costs and model retraining time. We show that our method has achieved significant improvement with minimal forgetting across all supervision levels on two challenging CL benchmarks for streaming real-world videos. Remarkably, with only 25% annotated video frames, our method still outperforms the base CL learners, which are trained with 100% annotations on all video frames. The data and source code will be publicly available at https://github.com/showlab/Efficient-CLS.

arXiv:2205.15445

Continual Object Detection: A review of definitions, strategies, and challenges

The field of Continual Learning investigates the ability to learn consecutive tasks without losing performance on those previously learned. Its focus has been mainly on incremental classification tasks. We believe that research in continual object detection deserves even more attention due to its vast range of applications in robotics and autonomous vehicles. This scenario is more complex than conventional classification given the occurrence of instances of classes that are unknown at the time, but can appear in subsequent tasks as a new class to be learned, resulting in missing annotations and conflicts with the background label. In this review, we analyze the current strategies proposed to tackle the problem of class-incremental object detection. Our main contributions are: (1) a short and systematic review of the methods that propose solutions to traditional incremental object detection scenarios; (2) A comprehensive evaluation of the existing approaches using a new metric to quantify the stability and plasticity of each technique in a standard way; (3) an overview of the current trends within continual object detection and a discussion of possible future research directions.

arXiv:2205.14495공식 코드 · Papers with Code

Task-Agnostic Continual Reinforcement Learning: Gaining Insights and Overcoming Challenges

Continual learning (CL) enables the development of models and agents that learn from a sequence of tasks while addressing the limitations of standard deep learning approaches, such as catastrophic forgetting. In this work, we investigate the factors that contribute to the performance differences between task-agnostic CL and multi-task (MTL) agents. We pose two hypotheses: (1) task-agnostic methods might provide advantages in settings with limited data, computation, or high dimensionality, and (2) faster adaptation may be particularly beneficial in continual learning settings, helping to mitigate the effects of catastrophic forgetting. To investigate these hypotheses, we introduce a replay-based recurrent reinforcement learning (3RL) methodology for task-agnostic CL agents. We assess 3RL on a synthetic task and the Meta-World benchmark, which includes 50 unique manipulation tasks. Our results demonstrate that 3RL outperforms baseline methods and can even surpass its multi-task equivalent in challenging settings with high dimensionality. We also show that the recurrent task-agnostic agent consistently outperforms or matches the performance of its transformer-based counterpart. These findings provide insights into the advantages of task-agnostic CL over task-aware MTL approaches and highlight the potential of task-agnostic methods in resource-constrained, high-dimensional, and multi-task environments.

arXiv:2205.14922공식 코드 · Papers with Code

ACIL: Analytic Class-Incremental Learning with Absolute Memorization and Privacy Protection

Class-incremental learning (CIL) learns a classification model with training data of different classes arising progressively. Existing CIL either suffers from serious accuracy loss due to catastrophic forgetting, or invades data privacy by revisiting used exemplars. Inspired by linear learning formulations, we propose an analytic class-incremental learning (ACIL) with absolute memorization of past knowledge while avoiding breaching of data privacy (i.e., without storing historical data). The absolute memorization is demonstrated in the sense that class-incremental learning using ACIL given present data would give identical results to that from its joint-learning counterpart which consumes both present and historical samples. This equality is theoretically validated. Data privacy is ensured since no historical data are involved during the learning process. Empirical validations demonstrate ACIL's competitive accuracy performance with near-identical results for various incremental task settings (e.g., 5-50 phases). This also allows ACIL to outperform the state-of-the-art methods for large-phase scenarios (e.g., 25 and 50 phases).

arXiv:2205.13359

Feature Forgetting in Continual Representation Learning

In continual and lifelong learning, good representation learning can help increase performance and reduce sample complexity when learning new tasks. There is evidence that representations do not suffer from "catastrophic forgetting" even in plain continual learning, but little further fact is known about its characteristics. In this paper, we aim to gain more understanding about representation learning in continual learning, especially on the feature forgetting problem. We devise a protocol for evaluating representation in continual learning, and then use it to present an overview of the basic trends of continual representation learning, showing its consistent deficiency and potential issues. To study the feature forgetting problem, we create a synthetic dataset to identify and visualize the prevalence of feature forgetting in neural networks. Finally, we propose a simple technique using gating adapters to mitigate feature forgetting. We conclude by discussing that improving representation learning benefits both old and new tasks in continual learning.

arXiv:2205.13323

The Effect of Task Ordering in Continual Learning

We investigate the effect of task ordering on continual learning performance. We conduct an extensive series of empirical experiments on synthetic and naturalistic datasets and show that reordering tasks significantly affects the amount of catastrophic forgetting. Connecting to the field of curriculum learning, we show that the effect of task ordering can be exploited to modify continual learning performance, and present a simple approach for doing so. Our method computes the distance between all pairs of tasks, where distance is defined as the source task curvature of a gradient step toward the target task. Using statistically rigorous methods and sound experimental design, we show that task ordering is an important aspect of continual learning that can be modified for improved performance.

arXiv:2205.13452공식 코드 · Papers with Code

Continual evaluation for lifelong learning: Identifying the stability gap

Time-dependent data-generating distributions have proven to be difficult for gradient-based training of neural networks, as the greedy updates result in catastrophic forgetting of previously learned knowledge. Despite the progress in the field of continual learning to overcome this forgetting, we show that a set of common state-of-the-art methods still suffers from substantial forgetting upon starting to learn new tasks, except that this forgetting is temporary and followed by a phase of performance recovery. We refer to this intriguing but potentially problematic phenomenon as the stability gap. The stability gap had likely remained under the radar due to standard practice in the field of evaluating continual learning models only after each task. Instead, we establish a framework for continual evaluation that uses per-iteration evaluation and we define a new set of metrics to quantify worst-case performance. Empirically we show that experience replay, constraint-based replay, knowledge-distillation, and parameter regularization methods are all prone to the stability gap; and that the stability gap can be observed in class-, task-, and domain-incremental learning benchmarks. Additionally, a controlled experiment shows that the stability gap increases when tasks are more dissimilar. Finally, by disentangling gradients into plasticity and stability components, we propose a conceptual explanation for the stability gap.

arXiv:2205.13384공식 코드 · Papers with Code

Continual Learning for Visual Search with Backward Consistent Feature Embedding

In visual search, the gallery set could be incrementally growing and added to the database in practice. However, existing methods rely on the model trained on the entire dataset, ignoring the continual updating of the model. Besides, as the model updates, the new model must re-extract features for the entire gallery set to maintain compatible feature space, imposing a high computational cost for a large gallery set. To address the issues of long-term visual search, we introduce a continual learning (CL) approach that can handle the incrementally growing gallery set with backward embedding consistency. We enforce the losses of inter-session data coherence, neighbor-session model coherence, and intra-session discrimination to conduct a continual learner. In addition to the disjoint setup, our CL solution also tackles the situation of increasingly adding new classes for the blurry boundary without assuming all categories known in the beginning and during model update. To our knowledge, this is the first CL method both tackling the issue of backward-consistent feature embedding and allowing novel classes to occur in the new sessions. Extensive experiments on various benchmarks show the efficacy of our approach under a wide range of setups.

arXiv:2205.12393공식 코드 · Papers with Code

Fine-tuned Language Models are Continual Learners

Recent work on large language models relies on the intuition that most natural language processing tasks can be described via natural language instructions. Language models trained on these instructions show strong zero-shot performance on several standard datasets. However, these models even though impressive still perform poorly on a wide range of tasks outside of their respective training and evaluation sets. To address this limitation, we argue that a model should be able to keep extending its knowledge and abilities, without forgetting previous skills. In spite of the limited success of Continual Learning we show that Language Models can be continual learners. We empirically investigate the reason for this success and conclude that Continual Learning emerges from self-supervision pre-training. Our resulting model Continual-T0 (CT0) is able to learn diverse new tasks, while still maintaining good performance on previous tasks, spanning remarkably through 70 datasets in total. Finally, we show that CT0 is able to combine instructions in ways it was never trained for, demonstrating some compositionality.

arXiv:2205.12755공식 코드 · Papers with Code

An Evolutionary Approach to Dynamic Introduction of Tasks in Large-scale Multitask Learning Systems

Multitask learning assumes that models capable of learning from multiple tasks can achieve better quality and efficiency via knowledge transfer, a key feature of human learning. Though, state of the art ML models rely on high customization for each task and leverage size and data scale rather than scaling the number of tasks. Also, continual learning, that adds the temporal aspect to multitask, is often focused to the study of common pitfalls such as catastrophic forgetting instead of being studied at a large scale as a critical component to build the next generation artificial intelligence.We propose an evolutionary method capable of generating large scale multitask models that support the dynamic addition of new tasks. The generated multitask models are sparsely activated and integrates a task-based routing that guarantees bounded compute cost and fewer added parameters per task as the model expands.The proposed method relies on a knowledge compartmentalization technique to achieve immunity against catastrophic forgetting and other common pitfalls such as gradient interference and negative transfer. We demonstrate empirically that the proposed method can jointly solve and achieve competitive results on 69public image classification tasks, for example improving the state of the art on a competitive benchmark such as cifar10 by achieving a 15% relative error reduction compared to the best model trained on public data.

arXiv:2205.12295

lpSpikeCon: Enabling Low-Precision Spiking Neural Network Processing for Efficient Unsupervised Continual Learning on Autonomous Agents

Recent advances have shown that SNN-based systems can efficiently perform unsupervised continual learning due to their bio-plausible learning rule, e.g., Spike-Timing-Dependent Plasticity (STDP). Such learning capabilities are especially beneficial for use cases like autonomous agents (e.g., robots and UAVs) that need to continuously adapt to dynamically changing scenarios/environments, where new data gathered directly from the environment may have novel features that should be learned online. Current state-of-the-art works employ high-precision weights (i.e., 32 bit) for both training and inference phases, which pose high memory and energy costs thereby hindering efficient embedded implementations of such systems for battery-driven mobile autonomous systems. On the other hand, precision reduction may jeopardize the quality of unsupervised continual learning due to information loss. Towards this, we propose lpSpikeCon, a novel methodology to enable low-precision SNN processing for efficient unsupervised continual learning on resource-constrained autonomous agents/systems. Our lpSpikeCon methodology employs the following key steps: (1) analyzing the impacts of training the SNN model under unsupervised continual learning settings with reduced weight precision on the inference accuracy; (2) leveraging this study to identify SNN parameters that have a significant impact on the inference accuracy; and (3) developing an algorithm for searching the respective SNN parameter values that improve the quality of unsupervised continual learning. The experimental results show that our lpSpikeCon can reduce weight memory of the SNN model by 8x (i.e., by judiciously employing 4-bit weights) for performing online training with unsupervised continual learning and achieve no accuracy loss in the inference phase, as compared to the baseline model with 32-bit weights across different network sizes.

arXiv:2205.12186

Enhancing Continual Learning with Global Prototypes: Counteracting Negative Representation Drift

Continual learning (CL) aims to learn a sequence of tasks over time, with data distributions shifting from one task to another. When training on new task data, data representations from old tasks may drift. Some negative representation drift can result in catastrophic forgetting, by causing the locally learned class prototypes and data representations to correlate poorly across tasks. To mitigate such representation drift, we propose a method that finds global prototypes to guide the learning, and learns data representations with the regularization of the self-supervised information. Specifically, for NLP tasks, we formulate each task in a masked language modeling style, and learn the task via a neighbor attention mechanism over a pre-trained language model. Experimental results show that our proposed method can learn fairly consistent representations with less representation drift, and significantly reduce catastrophic forgetting in CL without resampling data from past tasks.

arXiv:2205.11736공식 코드 · Papers with Code

Towards a Defense Against Federated Backdoor Attacks Under Continuous Training

Backdoor attacks are dangerous and difficult to prevent in federated learning (FL), where training data is sourced from untrusted clients over long periods of time. These difficulties arise because: (a) defenders in FL do not have access to raw training data, and (b) a new phenomenon we identify called backdoor leakage causes models trained continuously to eventually suffer from backdoors due to cumulative errors in defense mechanisms. We propose shadow learning, a framework for defending against backdoor attacks in the FL setting under long-range training. Shadow learning trains two models in parallel: a backbone model and a shadow model. The backbone is trained without any defense mechanism to obtain good performance on the main task. The shadow model combines filtering of malicious clients with early-stopping to control the attack success rate even as the data distribution changes. We theoretically motivate our design and show experimentally that our framework significantly improves upon existing defenses against backdoor attacks.