对比学习是机器学习中最快的研究领域之一，因为它可以在没有标记数据的情况下学习有用的表示。然而，对比学学习易于特征抑制，即，它可能会丢弃与感兴趣的任务相关的重要信息，并学习无关的功能。过去的工作通过消除无关信息的手工制作的数据增强解决了这一限制。然而，这种方法不适用于所有数据集和任务。此外，当一个属性可以抑制与其他属性相关的特征时，数据增强在解决多属性分类中的功能抑制中失败。在本文中，我们分析了对比学习的目标函数，并正式证明它易于特征抑制。然后，我们提出预测对比学习（PCL），一种学习对特征抑制具有鲁棒的无监督表示的框架。关键的想法是强制学习的表示来预测输入，因此防止它丢弃重要信息。广泛的实验验证PCL是否强大地对特征抑制和优于各种数据集和任务的最先进的对比学习方法。

Contrastive learning between multiple views of the data has recently achieved state of the art performance in the field of self-supervised representation learning. Despite its success, the influence of different view choices has been less studied. In this paper, we use theoretical and empirical analysis to better understand the importance of view selection, and argue that we should reduce the mutual information (MI) between views while keeping task-relevant information intact. To verify this hypothesis, we devise unsupervised and semi-supervised frameworks that learn effective views by aiming to reduce their MI. We also consider data augmentation as a way to reduce MI, and show that increasing data augmentation indeed leads to decreasing MI and improves downstream classification accuracy. As a byproduct, we achieve a new state-of-the-art accuracy on unsupervised pre-training for ImageNet classification (73% top-1 linear readout with a ResNet-50) 1 .

Contrastive learning applied to self-supervised representation learning has seen a resurgence in recent years, leading to state of the art performance in the unsupervised training of deep image models. Modern batch contrastive approaches subsume or significantly outperform traditional contrastive losses such as triplet, max-margin and the N-pairs loss. In this work, we extend the self-supervised batch contrastive approach to the fully-supervised setting, allowing us to effectively leverage label information. Clusters of points belonging to the same class are pulled together in embedding space, while simultaneously pushing apart clusters of samples from different classes. We analyze two possible versions of the supervised contrastive (SupCon) loss, identifying the best-performing formulation of the loss. On ResNet-200, we achieve top-1 accuracy of 81.4% on the Ima-geNet dataset, which is 0.8% above the best number reported for this architecture. We show consistent outperformance over cross-entropy on other datasets and two ResNet variants. The loss shows benefits for robustness to natural corruptions, and is more stable to hyperparameter settings such as optimizers and data augmentations. Our loss function is simple to implement and reference TensorFlow code is released at https://t.ly/supcon 1 .

The focus of recent meta-learning research has been on the development of learning algorithms that can quickly adapt to test time tasks with limited data and low computational cost. Few-shot learning is widely used as one of the standard benchmarks in meta-learning. In this work, we show that a simple baseline: learning a supervised or selfsupervised representation on the meta-training set, followed by training a linear classifier on top of this representation, outperforms state-of-the-art few-shot learning methods. An additional boost can be achieved through the use of selfdistillation. This demonstrates that using a good learned embedding model can be more effective than sophisticated meta-learning algorithms. We believe that our findings motivate a rethinking of few-shot image classification benchmarks and the associated role of meta-learning algorithms.

Often we wish to transfer representational knowledge from one neural network to another. Examples include distilling a large network into a smaller one, transferring knowledge from one sensory modality to a second, or ensembling a collection of models into a single estimator. Knowledge distillation, the standard approach to these problems, minimizes the KL divergence between the probabilistic outputs of a teacher and student network. We demonstrate that this objective ignores important structural knowledge of the teacher network. This motivates an alternative objective by which we train a student to capture significantly more information in the teacher's representation of the data. We formulate this objective as contrastive learning. Experiments demonstrate that our resulting new objective outperforms knowledge distillation and other cutting-edge distillers on a variety of knowledge transfer tasks, including single model compression, ensemble distillation, and cross-modal transfer. Our method sets a new state-of-the-art in many transfer tasks, and sometimes even outperforms the teacher network when combined with knowledge distillation.

不确定性估计是评估计算机视觉中深度学习模型的稳健性的重要步骤，特别是在风险敏感区域时。然而，大多数最先进的深层学习模型未能获得不确定性估计或需要显着的修改（例如，制定适当的贝叶斯治疗）以获得它。最先前的方法无法从架子上取下任意模型，并在不培训或重新设计的情况下产生不确定性估计。为了解决这一差距，我们对培训的不确定性估算进行了系统的探索，以进行密集的回归，一个无法识别的，一个重要的问题，并提供理论建设证明这种估计。我们提出了三种简单且可扩展的方法来分析可容忍的扰动中训练网络的输出方差：推断 - 转换，推断噪声和推断出来。它们仅在推理期间运营，无需重新列车，重新设计或微调模型，通常是由最先进的不确定性估算方法所必需的。令人惊讶的是，即使不涉及这种在训练中的这种扰动，与训练所需的最先进方法相比，我们的方法也会产生可比或甚至更好的不确定性估计。

Humans view the world through many sensory channels, e.g., the long-wavelength light channel, viewed by the left eye, or the high-frequency vibrations channel, heard by the right ear. Each view is noisy and incomplete, but important factors, such as physics, geometry, and semantics, tend to be shared between all views (e.g., a "dog" can be seen, heard, and felt). We investigate the classic hypothesis that a powerful representation is one that models view-invariant factors. We study this hypothesis under the framework of multiview contrastive learning, where we learn a representation that aims to maximize mutual information between different views of the same scene but is otherwise compact. Our approach scales to any number of views, and is viewagnostic. We analyze key properties of the approach that make it work, finding that the contrastive loss outperforms a popular alternative based on cross-view prediction, and that the more views we learn from, the better the resulting representation captures underlying scene semantics. Our approach achieves state-of-the-art results on image and video unsupervised learning benchmarks.

Recent deep learning approaches for representation learning on graphs follow a neighborhood aggregation procedure. We analyze some important properties of these models, and propose a strategy to overcome those. In particular, the range of "neighboring" nodes that a node's representation draws from strongly depends on the graph structure, analogous to the spread of a random walk. To adapt to local neighborhood properties and tasks, we explore an architecture -jumping knowledge (JK) networks -that flexibly leverages, for each node, different neighborhood ranges to enable better structure-aware representation. In a number of experiments on social, bioinformatics and citation networks, we demonstrate that our model achieves state-of-the-art performance. Furthermore, combining the JK framework with models like Graph Convolutional Networks, GraphSAGE and Graph Attention Networks consistently improves those models' performance.

Given the increasingly intricate forms of partial differential equations (PDEs) in physics and related fields, computationally solving PDEs without analytic solutions inevitably suffers from the trade-off between accuracy and efficiency. Recent advances in neural operators, a kind of mesh-independent neural-network-based PDE solvers, have suggested the dawn of overcoming this challenge. In this emerging direction, Koopman neural operator (KNO) is a representative demonstration and outperforms other state-of-the-art alternatives in terms of accuracy and efficiency. Here we present KoopmanLab, a self-contained and user-friendly PyTorch module of the Koopman neural operator family for solving partial differential equations. Beyond the original version of KNO, we develop multiple new variants of KNO based on different neural network architectures to improve the general applicability of our module. These variants are validated by mesh-independent and long-term prediction experiments implemented on representative PDEs (e.g., the Navier-Stokes equation and the Bateman-Burgers equation) and ERA5 (i.e., one of the largest high-resolution data sets of global-scale climate fields). These demonstrations suggest the potential of KoopmanLab to be considered in diverse applications of partial differential equations.

Humans have internal models of robots (like their physical capabilities), the world (like what will happen next), and their tasks (like a preferred goal). However, human internal models are not always perfect: for example, it is easy to underestimate a robot's inertia. Nevertheless, these models change and improve over time as humans gather more experience. Interestingly, robot actions influence what this experience is, and therefore influence how people's internal models change. In this work we take a step towards enabling robots to understand the influence they have, leverage it to better assist people, and help human models more quickly align with reality. Our key idea is to model the human's learning as a nonlinear dynamical system which evolves the human's internal model given new observations. We formulate a novel optimization problem to infer the human's learning dynamics from demonstrations that naturally exhibit human learning. We then formalize how robots can influence human learning by embedding the human's learning dynamics model into the robot planning problem. Although our formulations provide concrete problem statements, they are intractable to solve in full generality. We contribute an approximation that sacrifices the complexity of the human internal models we can represent, but enables robots to learn the nonlinear dynamics of these internal models. We evaluate our inference and planning methods in a suite of simulated environments and an in-person user study, where a 7DOF robotic arm teaches participants to be better teleoperators. While influencing human learning remains an open problem, our results demonstrate that this influence is possible and can be helpful in real human-robot interaction.