Pretrained Language Models (LMs) memorize a vast amount of knowledge during initial pretraining, including information that may violate the privacy of personal lives and identities. Previous work addressing privacy issues for language models has mostly focused on data preprocessing and differential privacy methods, both requiring re-training the underlying LM. We propose knowledge unlearning as an alternative method to reduce privacy risks for LMs post hoc. We show that simply performing gradient ascent on target token sequences is effective at forgetting them with little to no degradation of general language modeling performances for larger LMs; it sometimes even substantially improves the underlying LM with just a few iterations. We also find that sequential unlearning is better than trying to unlearn all the data at once and that unlearning is highly dependent on which kind of data (domain) is forgotten. By showing comparisons with a previous data preprocessing method and a decoding method known to mitigate privacy risks for LMs, we show that unlearning can give a stronger empirical privacy guarantee in scenarios where the data vulnerable to extraction attacks are known a priori while being much more efficient and robust. We release the code and dataset needed to replicate our results at https://github.com/joeljang/knowledge-unlearning.

持续学习（CL）旨在从依次到达的任务中学习，而无需忘记以前的任务。尽管CL算法试图在到目前为止所学的所有任务中实现更高的平均测试准确性，但学习对成功的概括和下游转移至关重要。为了衡量代表性质量，我们仅使用一个小平衡数据集对所有任务进行重新培训，从而评估平均准确性，而无需对当前任务进行任何偏见的预测。我们还测试了几个下游任务，测量了学习表示的转移学习准确性。通过测试我们在Imagenet-100和Imagenet-1000上的新形式主义，我们发现使用更多的示例记忆是在学习的表示形式中产生有意义差异的唯一选择，以及大多数基于正则化或蒸馏的CL算法，都使用了示例记忆无法在课堂学习学习中学习不断有用的表示。令人惊讶的是，具有足够记忆大小的无监督（或自制的）CL可以达到与受监督对应物相当的性能。考虑到非平凡的标签成本，我们声称找到更有效的无监督CL算法，这些算法最少使用示例性记忆将是CL研究的下一个有希望的方向。

通过将其与监督学习框架相结合，我们改善了最近开发的神经元，是一种基于神经网络的自适应离散的丹机。即，我们通过基于给定嘈杂的数据受到去噪的给定嘈杂的数据来使神经调整的监督训练兼容。结果，与香草神经元伙子相比，我们实现了显着的去噪能力，这只需要采用随机初始化参数的自适应微调步骤。此外，我们示出了自适应微调使得算法稳健使得噪声错配或盲目训练的监督模型仍然可以实现匹配模型的性能。此外，我们制作一些算法的进步，使神经伙伴更可扩展，并处理具有更大字母大小的多维数据或数据。我们系统地显示了我们对两个非常多元化的数据集，二值图像和DNA序列的改进。

我们提出了一种新颖且有效的纯化基于纯化的普通防御方法，用于预处理盲目的白色和黑匣子攻击。我们的方法仅在一般图像上进行了自我监督学习，在计算上效率和培训，而不需要对分类模型的任何对抗训练或再培训。我们首先显示对原始图像与其对抗示例之间的残余的对抗噪声的实证分析，几乎均为对称分布。基于该观察，我们提出了一种非常简单的迭代高斯平滑（GS），其可以有效地平滑对抗性噪声并实现大大高的鲁棒精度。为了进一步改进它，我们提出了神经上下文迭代平滑（NCIS），其以自我监督的方式列举盲点网络（BSN）以重建GS也平滑的原始图像的辨别特征。从我们使用四种分类模型对大型想象成的广泛实验，我们表明我们的方法既竞争竞争标准精度和最先进的强大精度，则针对最强大的净化器 - 盲目的白色和黑匣子攻击。此外，我们提出了一种用于评估基于商业图像分类API的纯化方法的新基准，例如AWS，Azure，Clarifai和Google。我们通过基于集合转移的黑匣子攻击产生对抗性实例，这可以促进API的完全错误分类，并证明我们的方法可用于增加API的抗逆性鲁棒性。

本文介绍了类增量语义分割（CISS）问题的固态基线。虽然最近的CISS算法利用了知识蒸馏（KD）技术的变体来解决问题，但他们未能充分解决CISS引起灾难性遗忘的关键挑战;背景类的语义漂移和多标签预测问题。为了更好地解决这些挑战，我们提出了一种新方法，被称为SSUL-M（具有内存的未知标签的语义分割），通过仔细组合为语义分割量身定制的技术。具体来说，我们要求三项主要贡献。 （1）在背景课程中定义未知的类，以帮助学习未来的课程（帮助可塑性），（2）冻结骨干网以及与二进制交叉熵丢失和伪标签的跨熵丢失的分类器，以克服灾难性的遗忘（帮助稳定）和（3）首次利用微小的示例存储器在CISS中提高可塑性和稳定性。广泛进行的实验表明了我们的方法的有效性，而不是标准基准数据集上最近的最新的基线的性能明显更好。此外，与彻底的消融分析有关我们对彻底消融分析的贡献，并与传统的类增量学习针对分类相比，讨论了CISS问题的不同自然。官方代码可在https://github.com/clovaai/ssul获得。

Harmonic functions are abundant in nature, appearing in limiting cases of Maxwell's, Navier-Stokes equations, the heat and the wave equation. Consequently, there are many applications of harmonic functions, spanning applications from industrial process optimisation to robotic path planning and the calculation of first exit times of random walks. Despite their ubiquity and relevance, there have been few attempts to develop effective means of representing harmonic functions in the context of machine learning architectures, either in machine learning on classical computers, or in the nascent field of quantum machine learning. Architectures which impose or encourage an inductive bias towards harmonic functions would facilitate data-driven modelling and the solution of inverse problems in a range of applications. For classical neural networks, it has already been established how leveraging inductive biases can in general lead to improved performance of learning algorithms. The introduction of such inductive biases within a quantum machine learning setting is instead still in its nascent stages. In this work, we derive exactly-harmonic (conventional- and quantum-) neural networks in two dimensions for simply-connected domains by leveraging the characteristics of holomorphic complex functions. We then demonstrate how these can be approximately extended to multiply-connected two-dimensional domains using techniques inspired by domain decomposition in physics-informed neural networks. We further provide architectures and training protocols to effectively impose approximately harmonic constraints in three dimensions and higher, and as a corollary we report divergence-free network architectures in arbitrary dimensions. Our approaches are demonstrated with applications to heat transfer, electrostatics and robot navigation, with comparisons to physics-informed neural networks included.

Skeleton-based action recognition has attracted considerable attention due to its compact skeletal structure of the human body. Many recent methods have achieved remarkable performance using graph convolutional networks (GCNs) and convolutional neural networks (CNNs), which extract spatial and temporal features, respectively. Although spatial and temporal dependencies in the human skeleton have been explored, spatio-temporal dependency is rarely considered. In this paper, we propose the Inter-Frame Curve Network (IFC-Net) to effectively leverage the spatio-temporal dependency of the human skeleton. Our proposed network consists of two novel elements: 1) The Inter-Frame Curve (IFC) module; and 2) Dilated Graph Convolution (D-GC). The IFC module increases the spatio-temporal receptive field by identifying meaningful node connections between every adjacent frame and generating spatio-temporal curves based on the identified node connections. The D-GC allows the network to have a large spatial receptive field, which specifically focuses on the spatial domain. The kernels of D-GC are computed from the given adjacency matrices of the graph and reflect large receptive field in a way similar to the dilated CNNs. Our IFC-Net combines these two modules and achieves state-of-the-art performance on three skeleton-based action recognition benchmarks: NTU-RGB+D 60, NTU-RGB+D 120, and Northwestern-UCLA.

We propose Universal Document Processing (UDOP), a foundation Document AI model which unifies text, image, and layout modalities together with varied task formats, including document understanding and generation. UDOP leverages the spatial correlation between textual content and document image to model image, text, and layout modalities with one uniform representation. With a novel Vision-Text-Layout Transformer, UDOP unifies pretraining and multi-domain downstream tasks into a prompt-based sequence generation scheme. UDOP is pretrained on both large-scale unlabeled document corpora using innovative self-supervised objectives and diverse labeled data. UDOP also learns to generate document images from text and layout modalities via masked image reconstruction. To the best of our knowledge, this is the first time in the field of document AI that one model simultaneously achieves high-quality neural document editing and content customization. Our method sets the state-of-the-art on 9 Document AI tasks, e.g., document understanding and QA, across diverse data domains like finance reports, academic papers, and websites. UDOP ranks first on the leaderboard of the Document Understanding Benchmark (DUE).

We tackle open-world semantic segmentation, which aims at learning to segment arbitrary visual concepts in images, by using only image-text pairs without dense annotations. Existing open-world segmentation methods have shown impressive advances by employing contrastive learning (CL) to learn diverse visual concepts and adapting the learned image-level understanding to the segmentation task. However, these methods based on CL have a discrepancy since it only considers image-text level alignment in training time, while the segmentation task requires region-text level alignment at test time. In this paper, we propose a novel Text-grounded Contrastive Learning (TCL) framework to directly align a text and a region described by the text to address the train-test discrepancy. Our method generates a segmentation mask associated with a given text, extracts grounded image embedding from the masked region, and aligns it with text embedding via TCL. The framework addresses the discrepancy by letting the model learn region-text level alignment instead of image-text level alignment and encourages the model to directly improve the quality of generated segmentation masks. In addition, for a rigorous and fair comparison, we present a unified evaluation protocol with widely used 8 semantic segmentation datasets. TCL achieves state-of-the-art zero-shot segmentation performance with large margins in all datasets. Code is available at https://github.com/kakaobrain/tcl.

We present HOReeNet, which tackles the novel task of manipulating images involving hands, objects, and their interactions. Especially, we are interested in transferring objects of source images to target images and manipulating 3D hand postures to tightly grasp the transferred objects. Furthermore, the manipulation needs to be reflected in the 2D image space. In our reenactment scenario involving hand-object interactions, 3D reconstruction becomes essential as 3D contact reasoning between hands and objects is required to achieve a tight grasp. At the same time, to obtain high-quality 2D images from 3D space, well-designed 3D-to-2D projection and image refinement are required. Our HOReeNet is the first fully differentiable framework proposed for such a task. On hand-object interaction datasets, we compared our HOReeNet to the conventional image translation algorithms and reenactment algorithm. We demonstrated that our approach could achieved the state-of-the-art on the proposed task.