PyTorchKR Papers

최신 논문

총 2,786편
태그·기간 등 상세 필터

카테고리 탐색

로그인 후 이 태그 구독

arXiv:2401.17401

Step-size Optimization for Continual Learning

In continual learning, a learner has to keep learning from the data over its whole life time. A key issue is to decide what knowledge to keep and what knowledge to let go. In a neural network, this can be implemented by using a step-size vector to scale how much gradient samples change network weights. Common algorithms, like RMSProp and Adam, use heuristics, specifically normalization, to adapt this step-size vector. In this paper, we show that those heuristics ignore the effect of their adaptation on the overall objective function, for example by moving the step-size vector away from better step-size vectors. On the other hand, stochastic meta-gradient descent algorithms, like IDBD (Sutton, 1992), explicitly optimize the step-size vector with respect to the overall objective function. On simple problems, we show that IDBD is able to consistently improve step-size vectors, where RMSProp and Adam do not. We explain the differences between the two approaches and their respective limitations. We conclude by suggesting that combining both approaches could be a promising future direction to improve the performance of neural networks in continual learning.

arXiv:2401.16432

Improving conversion rate prediction via self-supervised pre-training in online advertising

The task of predicting conversion rates (CVR) lies at the heart of online advertising systems aiming to optimize bids to meet advertiser performance requirements. Even with the recent rise of deep neural networks, these predictions are often made by factorization machines (FM), especially in commercial settings where inference latency is key. These models are trained using the logistic regression framework on labeled tabular data formed from past user activity that is relevant to the task at hand. Many advertisers only care about click-attributed conversions. A major challenge in training models that predict conversions-given-clicks comes from data sparsity - clicks are rare, conversions attributed to clicks are even rarer. However, mitigating sparsity by adding conversions that are not click-attributed to the training set impairs model calibration. Since calibration is critical to achieving advertiser goals, this is infeasible. In this work we use the well-known idea of self-supervised pre-training, and use an auxiliary auto-encoder model trained on all conversion events, both click-attributed and not, as a feature extractor to enrich the main CVR prediction model. Since the main model does not train on non click-attributed conversions, this does not impair calibration. We adapt the basic self-supervised pre-training idea to our online advertising setup by using a loss function designed for tabular data, facilitating continual learning by ensuring auto-encoder stability, and incorporating a neural network into a large-scale real-time ad auction that ranks tens of thousands of ads, under strict latency constraints, and without incurring a major engineering cost. We show improvements both offline, during training, and in an online A/B test. Following its success in A/B tests, our solution is now fully deployed to the Yahoo native advertising system.

arXiv:2401.16694

EdgeOL: Efficient in-situ Online Learning on Edge Devices

Emerging applications, such as robot-assisted eldercare and object recognition, generally employ deep learning neural networks (DNNs) and naturally require: i) handling streaming-in inference requests and ii) adapting to possible deployment scenario changes. Online model fine-tuning is widely adopted to satisfy these needs. However, an inappropriate fine-tuning scheme could involve significant energy consumption, making it challenging to deploy on edge devices. In this paper, we propose EdgeOL, an edge online learning framework that optimizes inference accuracy, fine-tuning execution time, and energy efficiency through both inter-tuning and intra-tuning optimizations. Experimental results show that, on average, EdgeOL reduces overall fine-tuning execution time by 64%, energy consumption by 52%, and improves average inference accuracy by 1.75% over the immediate online learning strategy

arXiv:2401.16650공식 코드 · Papers with Code

Augmenting Replay in World Models for Continual Reinforcement Learning

Continual RL requires an agent to learn new tasks without forgetting previous ones, while improving on both past and future tasks. The most common approaches use model-free algorithms and replay buffers can help to mitigate catastrophic forgetting, but often struggle with scalability due to large memory requirements. Biologically inspired replay suggests replay to a world model, aligning with model-based RL; as opposed to the common setting of replay in model-free algorithms. Model-based RL offers benefits for continual RL by leveraging knowledge of the environment, independent of policy. We introduce WMAR (World Models with Augmented Replay), a model-based RL algorithm with a memory-efficient distribution-matching replay buffer. WMAR extends the well known DreamerV3 algorithm, which employs a simple FIFO buffer and was not tested in continual RL. We evaluated WMAR and DreamerV3, with the same-size replay buffers. They were tested on two scenarios: tasks with shared structure using OpenAI Procgen and tasks without shared structure using the Atari benchmark. WMAR demonstrated favourable properties for continual RL considering metrics for forgetting as well as skill transfer on past and future tasks. Compared to DreamerV3, WMAR showed slight benefits in tasks with shared structure and substantially better forgetting characteristics on tasks without shared structure. Our results suggest that model-based RL with a memory-efficient replay buffer can be an effective approach to continual RL, justifying further research.

arXiv:2401.16386공식 코드 · Papers with Code

Continual Learning with Pre-Trained Models: A Survey

Nowadays, real-world applications often face streaming data, which requires the learning system to absorb new knowledge as data evolves. Continual Learning (CL) aims to achieve this goal and meanwhile overcome the catastrophic forgetting of former knowledge when learning new ones. Typical CL methods build the model from scratch to grow with incoming data. However, the advent of the pre-trained model (PTM) era has sparked immense research interest, particularly in leveraging PTMs' robust representational capabilities. This paper presents a comprehensive survey of the latest advancements in PTM-based CL. We categorize existing methodologies into three distinct groups, providing a comparative analysis of their similarities, differences, and respective advantages and disadvantages. Additionally, we offer an empirical study contrasting various state-of-the-art methods to highlight concerns regarding fairness in comparisons. The source code to reproduce these evaluations is available at: https://github.com/sun-hailong/LAMDA-PILOT

arXiv:2401.15973공식 코드 · Papers with Code

Sample Weight Estimation Using Meta-Updates for Online Continual Learning

The loss function plays an important role in optimizing the performance of a learning system. A crucial aspect of the loss function is the assignment of sample weights within a mini-batch during loss computation. In the context of continual learning (CL), most existing strategies uniformly treat samples when calculating the loss value, thereby assigning equal weights to each sample. While this approach can be effective in certain standard benchmarks, its optimal effectiveness, particularly in more complex scenarios, remains underexplored. This is particularly pertinent in training "in the wild," such as with self-training, where labeling is automated using a reference model. This paper introduces the Online Meta-learning for Sample Importance (OMSI) strategy that approximates sample weights for a mini-batch in an online CL stream using an inner- and meta-update mechanism. This is done by first estimating sample weight parameters for each sample in the mini-batch, then, updating the model with the adapted sample weights. We evaluate OMSI in two distinct experimental settings. First, we show that OMSI enhances both learning and retained accuracy in a controlled noisy-labeled data stream. Then, we test the strategy in three standard benchmarks and compare it with other popular replay-based strategies. This research aims to foster the ongoing exploration in the area of self-adaptive CL.

arXiv:2401.15275

Dynamic Transformer Architecture for Continual Learning of Multimodal Tasks

Transformer neural networks are increasingly replacing prior architectures in a wide range of applications in different data modalities. The increasing size and computational demands of fine-tuning large pre-trained transformer neural networks pose significant challenges for the widespread adoption of these models for applications that demand on-edge computing. To tackle this challenge, continual learning (CL) emerges as a solution by facilitating the transfer of knowledge across tasks that arrive sequentially for an autonomously learning agent. However, current CL methods mainly focus on learning tasks that are exclusively vision-based or language-based. We propose a transformer-based CL framework focusing on learning tasks that involve both vision and language, known as Vision-and-Language (VaL) tasks. Due to the success of transformers in other modalities, our architecture has the potential to be used in multimodal learning settings. In our framework, we benefit from introducing extra parameters to a base transformer to specialize the network for each task. As a result, we enable dynamic model expansion to learn several tasks in a sequence. We also use knowledge distillation to benefit from relevant past experiences to learn the current task more efficiently. Our proposed method, Task Attentive Multimodal Continual Learning (TAM-CL), allows for the exchange of information between tasks while mitigating the problem of catastrophic forgetting. Notably, our approach is scalable, incurring minimal memory and time overhead. TAM-CL achieves state-of-the-art (SOTA) performance on challenging multimodal tasks

arXiv:2401.15045

Emulating Complex Synapses Using Interlinked Proton Conductors

In terms of energy efficiency and computational speed, neuromorphic electronics based on non-volatile memory devices is expected to be one of most promising hardware candidates for future artificial intelligence (AI). However, catastrophic forgetting, networks rapidly overwriting previously learned weights when learning new tasks, remains as a pivotal hurdle in either digital or analog AI chips for unleashing the true power of brain-like computing. To address catastrophic forgetting in the context of online memory storage, a complex synapse model (the Benna-Fusi model) has been proposed recently[1], whose synaptic weight and internal variables evolve following a diffusion dynamics. In this work, by designing a proton transistor with a series of charge-diffusion-controlled storage components, we have experimentally realized the Benna-Fusi artificial complex synapse. The memory consolidation from coupled storage components is revealed by both numerical simulations and experimental observations. Different memory timescales for the complex synapse are engineered by the diffusion length of charge carriers, the capacity and number of coupled storage components. The advantage of the demonstrated complex synapse in both memory capacity and memory consolidation is revealed by neural network simulations of face familiarity detection. Our experimental realization of the complex synapse suggests a promising approach to enhance memory capacity and to enable continual learning.

arXiv:2401.13200공식 코드 · Papers with Code

Topology-aware Embedding Memory for Continual Learning on Expanding Networks

Memory replay based techniques have shown great success for continual learning with incrementally accumulated Euclidean data. Directly applying them to continually expanding networks, however, leads to the potential memory explosion problem due to the need to buffer representative nodes and their associated topological neighborhood structures. To this end, we systematically analyze the key challenges in the memory explosion problem, and present a general framework, \textit{i.e.}, Parameter Decoupled Graph Neural Networks (PDGNNs) with Topology-aware Embedding Memory (TEM), to tackle this issue. The proposed framework not only reduces the memory space complexity from $\mathcal{O}(nd^L)$ to $\mathcal{O}(n)$~\footnote{$n$: memory budget, $d$: average node degree, $L$: the radius of the GNN receptive field}, but also fully utilizes the topological information for memory replay. Specifically, PDGNNs decouple trainable parameters from the computation ego-subnetwork via \textit{Topology-aware Embeddings} (TEs), which compress ego-subnetworks into compact vectors (\textit{i.e.}, TEs) to reduce the memory consumption. Based on this framework, we discover a unique \textit{pseudo-training effect} in continual learning on expanding networks and this effect motivates us to develop a novel \textit{coverage maximization sampling} strategy that can enhance the performance with a tight memory budget. Thorough empirical studies demonstrate that, by tackling the memory explosion problem and incorporating topological information into memory replay, PDGNNs with TEM significantly outperform state-of-the-art techniques, especially in the challenging class-incremental setting.

arXiv:2401.13034

Locality Sensitive Sparse Encoding for Learning World Models Online

Acquiring an accurate world model online for model-based reinforcement learning (MBRL) is challenging due to data nonstationarity, which typically causes catastrophic forgetting for neural networks (NNs). From the online learning perspective, a Follow-The-Leader (FTL) world model is desirable, which optimally fits all previous experiences at each round. Unfortunately, NN-based models need re-training on all accumulated data at every interaction step to achieve FTL, which is computationally expensive for lifelong agents. In this paper, we revisit models that can achieve FTL with incremental updates. Specifically, our world model is a linear regression model supported by nonlinear random features. The linear part ensures efficient FTL update while the nonlinear random feature empowers the fitting of complex environments. To best trade off model capacity and computation efficiency, we introduce a locality sensitive sparse encoding, which allows us to conduct efficient sparse updates even with very high dimensional nonlinear features. We validate the representation power of our encoding and verify that it allows efficient online learning under data covariate shift. We also show, in the Dyna MBRL setting, that our world models learned online using a single pass of trajectory data either surpass or match the performance of deep world models trained with replay and other continual learning methods.

arXiv:2401.12617

The Joint Effect of Task Similarity and Overparameterization on Catastrophic Forgetting -- An Analytical Model

In continual learning, catastrophic forgetting is affected by multiple aspects of the tasks. Previous works have analyzed separately how forgetting is affected by either task similarity or overparameterization. In contrast, our paper examines how task similarity and overparameterization jointly affect forgetting in an analyzable model. Specifically, we focus on two-task continual linear regression, where the second task is a random orthogonal transformation of an arbitrary first task (an abstraction of random permutation tasks). We derive an exact analytical expression for the expected forgetting - and uncover a nuanced pattern. In highly overparameterized models, intermediate task similarity causes the most forgetting. However, near the interpolation threshold, forgetting decreases monotonically with the expected task similarity. We validate our findings with linear regression on synthetic data, and with neural networks on established permutation task benchmarks.

arXiv:2401.11544

Hierarchical Prompts for Rehearsal-free Continual Learning

Continual learning endeavors to equip the model with the capability to integrate current task knowledge while mitigating the forgetting of past task knowledge. Inspired by prompt tuning, prompt-based methods maintain a frozen backbone and train with slight learnable prompts to minimize the catastrophic forgetting that arises due to updating a large number of backbone parameters. Nonetheless, these learnable prompts tend to concentrate on the discriminatory knowledge of the current task while ignoring past task knowledge, leading to that learnable prompts still suffering from catastrophic forgetting. This paper introduces a novel rehearsal-free paradigm for continual learning termed Hierarchical Prompts (H-Prompts), comprising three categories of prompts -- class prompt, task prompt, and general prompt. To effectively depict the knowledge of past classes, class prompt leverages Bayesian Distribution Alignment to model the distribution of classes in each task. To reduce the forgetting of past task knowledge, task prompt employs Cross-task Knowledge Excavation to amalgamate the knowledge encapsulated in the learned class prompts of past tasks and current task knowledge. Furthermore, general prompt utilizes Generalized Knowledge Exploration to deduce highly generalized knowledge in a self-supervised manner. Evaluations on two benchmarks substantiate the efficacy of the proposed H-Prompts, exemplified by an average accuracy of 87.8% in Split CIFAR-100 and 70.6% in Split ImageNet-R.

arXiv:2401.11144

Towards Open-World Gesture Recognition

Providing users with accurate gestural interfaces, such as gesture recognition based on wrist-worn devices, is a key challenge in mixed reality. However, static machine learning processes in gesture recognition assume that training and test data come from the same underlying distribution. Unfortunately, in real-world applications involving gesture recognition, such as gesture recognition based on wrist-worn devices, the data distribution may change over time. We formulate this problem of adapting recognition models to new tasks, where new data patterns emerge, as open-world gesture recognition (OWGR). We propose the use of continual learning to enable machine learning models to be adaptive to new tasks without degrading performance on previously learned tasks. However, the process of exploring parameters for questions around when, and how, to train and deploy recognition models requires resource-intensive user studies may be impractical. To address this challenge, we propose a design engineering approach that enables offline analysis on a collected large-scale dataset by systematically examining various parameters and comparing different continual learning methods. Finally, we provide design guidelines to enhance the development of an open-world wrist-worn gesture recognition process.

arXiv:2401.11667

INCPrompt: Task-Aware incremental Prompting for Rehearsal-Free Class-incremental Learning

This paper introduces INCPrompt, an innovative continual learning solution that effectively addresses catastrophic forgetting. INCPrompt's key innovation lies in its use of adaptive key-learner and task-aware prompts that capture task-relevant information. This unique combination encapsulates general knowledge across tasks and encodes task-specific knowledge. Our comprehensive evaluation across multiple continual learning benchmarks demonstrates INCPrompt's superiority over existing algorithms, showing its effectiveness in mitigating catastrophic forgetting while maintaining high performance. These results highlight the significant impact of task-aware incremental prompting on continual learning performance.

arXiv:2401.11726

Detecting Out-of-Distribution Samples via Conditional Distribution Entropy with Optimal Transport

When deploying a trained machine learning model in the real world, it is inevitable to receive inputs from out-of-distribution (OOD) sources. For instance, in continual learning settings, it is common to encounter OOD samples due to the non-stationarity of a domain. More generally, when we have access to a set of test inputs, the existing rich line of OOD detection solutions, especially the recent promise of distance-based methods, falls short in effectively utilizing the distribution information from training samples and test inputs. In this paper, we argue that empirical probability distributions that incorporate geometric information from both training samples and test inputs can be highly beneficial for OOD detection in the presence of test inputs available. To address this, we propose to model OOD detection as a discrete optimal transport problem. Within the framework of optimal transport, we propose a novel score function known as the \emph{conditional distribution entropy} to quantify the uncertainty of a test input being an OOD sample. Our proposal inherits the merits of certain distance-based methods while eliminating the reliance on distribution assumptions, a-prior knowledge, and specific training mechanisms. Extensive experiments conducted on benchmark datasets demonstrate that our method outperforms its competitors in OOD detection.

arXiv:2401.12051공식 코드 · Papers with Code

CloSe: A 3D Clothing Segmentation Dataset and Model

3D Clothing modeling and datasets play crucial role in the entertainment, animation, and digital fashion industries. Existing work often lacks detailed semantic understanding or uses synthetic datasets, lacking realism and personalization. To address this, we first introduce CloSe-D: a novel large-scale dataset containing 3D clothing segmentation of 3167 scans, covering a range of 18 distinct clothing classes. Additionally, we propose CloSe-Net, the first learning-based 3D clothing segmentation model for fine-grained segmentation from colored point clouds. CloSe-Net uses local point features, body-clothing correlation, and a garment-class and point features-based attention module, improving performance over baselines and prior work. The proposed attention module enables our model to learn appearance and geometry-dependent clothing prior from data. We further validate the efficacy of our approach by successfully segmenting publicly available datasets of people in clothing. We also introduce CloSe-T, a 3D interactive tool for refining segmentation labels. Combining the tool with CloSe-T in a continual learning setup demonstrates improved generalization on real-world data. Dataset, model, and tool can be found at https://virtualhumans.mpi-inf.mpg.de/close3dv24/.

arXiv:2401.10567공식 코드 · Papers with Code

Self-training from Self-memory in Data-to-text Generation

This paper introduces a novel training model, self-training from self-memory (STSM) in data-to-text generation (DTG), allowing the model to self-train on subsets, including self-memory as outputs inferred directly from the trained models and/or the new data. The quality of self-memory is validated by two models, data-to-text (D2T) and text-to-data (T2D), by two pre-defined conditions: (1) the appearance of all source values in the outputs of the D2T model and (2) the ability to convert back to source data in the outputs in the T2D model. We utilize a greedy algorithm to generate shorter D2T outputs if they contain all source values. Subsequently, we use the T2D model to confirm that these outputs can capture input relationships by demonstrating their capacity to convert text back into data. With 30% of the dataset, we can train the D2T model with a competitive performance compared to full training in the same setup. We experiment with our model on two datasets, E2E NLG and DART. STSM offers the D2T model a generalization capability from its subset memory while reducing training data volume. Ultimately, we anticipate that this paper will contribute to continual learning solutions that adapt to new training data, incorporating it as a form of self-memory in DTG tasks. The curated dataset is publicly available at: https://github.com/hoangthangta/STSM.

arXiv:2401.10393

Natural Mitigation of Catastrophic Interference: Continual Learning in Power-Law Learning Environments

Neural networks often suffer from catastrophic interference (CI): performance on previously learned tasks drops off significantly when learning a new task. This contrasts strongly with humans, who can continually learn new tasks without appreciably forgetting previous tasks. Prior work has explored various techniques for mitigating CI and promoting continual learning such as regularization, rehearsal, generative replay, and context-specific components. This paper takes a different approach, one guided by cognitive science research showing that in naturalistic environments, the probability of encountering a task decreases as a power-law of the time since it was last performed. We argue that techniques for mitigating CI should be compared against the intrinsic mitigation in simulated naturalistic learning environments. Thus, we evaluate the extent of the natural mitigation of CI when training models in power-law environments, similar to those humans face. Our results show that natural rehearsal environments are better at mitigating CI than existing methods, calling for the need for better evaluation processes. The benefits of this environment include simplicity, rehearsal that is agnostic to both tasks and models, and the lack of a need for extra neural circuitry. In addition, we explore popular mitigation techniques in power-law environments to create new baselines for continual learning research.

arXiv:2401.09916

Enabling On-device Continual Learning with Binary Neural Networks

On-device learning remains a formidable challenge, especially when dealing with resource-constrained devices that have limited computational capabilities. This challenge is primarily rooted in two key issues: first, the memory available on embedded devices is typically insufficient to accommodate the memory-intensive back-propagation algorithm, which often relies on floating-point precision. Second, the development of learning algorithms on models with extreme quantization levels, such as Binary Neural Networks (BNNs), is critical due to the drastic reduction in bit representation. In this study, we propose a solution that combines recent advancements in the field of Continual Learning (CL) and Binary Neural Networks to enable on-device training while maintaining competitive performance. Specifically, our approach leverages binary latent replay (LR) activations and a novel quantization scheme that significantly reduces the number of bits required for gradient computation. The experimental validation demonstrates a significant accuracy improvement in combination with a noticeable reduction in memory requirement, confirming the suitability of our approach in expanding the practical applications of deep learning in real-world scenarios.

arXiv:2401.10191공식 코드 · Papers with Code

Divide and not forget: Ensemble of selectively trained experts in Continual Learning

Class-incremental learning is becoming more popular as it helps models widen their applicability while not forgetting what they already know. A trend in this area is to use a mixture-of-expert technique, where different models work together to solve the task. However, the experts are usually trained all at once using whole task data, which makes them all prone to forgetting and increasing computational burden. To address this limitation, we introduce a novel approach named SEED. SEED selects only one, the most optimal expert for a considered task, and uses data from this task to fine-tune only this expert. For this purpose, each expert represents each class with a Gaussian distribution, and the optimal expert is selected based on the similarity of those distributions. Consequently, SEED increases diversity and heterogeneity within the experts while maintaining the high stability of this ensemble method. The extensive experiments demonstrate that SEED achieves state-of-the-art performance in exemplar-free settings across various scenarios, showing the potential of expert diversification through data in continual learning.