The ability to jointly learn from multiple modalities, such as text, audio, and visual data, is a defining feature of intelligent systems. While there have been promising advances in designing neural networks to harness multimodal data, the enormous success of data augmentation currently remains limited to single-modality tasks like image classification. Indeed, it is particularly difficult to augment each modality while preserving the overall semantic structure of the data; for example, a caption may no longer be a good description of an image after standard augmentations have been applied, such as translation. Moreover, it is challenging to specify reasonable transformations that are not tailored to a particular modality. In this paper, we introduce LeMDA, Learning Multimodal Data Augmentation, an easy-to-use method that automatically learns to jointly augment multimodal data in feature space, with no constraints on the identities of the modalities or the relationship between modalities. We show that LeMDA can (1) profoundly improve the performance of multimodal deep learning architectures, (2) apply to combinations of modalities that have not been previously considered, and (3) achieve state-of-the-art results on a wide range of applications comprised of image, text, and tabular data.

Pre-trained large language models can efficiently interpolate human-written prompts in a natural way. Multitask prompted learning can help generalization through a diverse set of tasks at once, thus enhancing the potential for more effective downstream fine-tuning. To perform efficient multitask-inference in the same batch, parameter-efficient fine-tuning methods such as prompt tuning have been proposed. However, the existing prompt tuning methods may lack generalization. We propose SPT, a semi-parametric prompt tuning method for multitask prompted learning. The novel component of SPT is a memory bank from where memory prompts are retrieved based on discrete prompts. Extensive experiments, such as (i) fine-tuning a full language model with SPT on 31 different tasks from 8 different domains and evaluating zero-shot generalization on 9 heldout datasets under 5 NLP task categories and (ii) pretraining SPT on the GLUE datasets and evaluating fine-tuning on the SuperGLUE datasets, demonstrate effectiveness of SPT.

Transformer-based models have gained large popularity and demonstrated promising results in long-term time-series forecasting in recent years. In addition to learning attention in time domain, recent works also explore learning attention in frequency domains (e.g., Fourier domain, wavelet domain), given that seasonal patterns can be better captured in these domains. In this work, we seek to understand the relationships between attention models in different time and frequency domains. Theoretically, we show that attention models in different domains are equivalent under linear conditions (i.e., linear kernel to attention scores). Empirically, we analyze how attention models of different domains show different behaviors through various synthetic experiments with seasonality, trend and noise, with emphasis on the role of softmax operation therein. Both these theoretical and empirical analyses motivate us to propose a new method: TDformer (Trend Decomposition Transformer), that first applies seasonal-trend decomposition, and then additively combines an MLP which predicts the trend component with Fourier attention which predicts the seasonal component to obtain the final prediction. Extensive experiments on benchmark time-series forecasting datasets demonstrate that TDformer achieves state-of-the-art performance against existing attention-based models.

Multimodal image-text models have shown remarkable performance in the past few years. However, evaluating their robustness against distribution shifts is crucial before adopting them in real-world applications. In this paper, we investigate the robustness of 9 popular open-sourced image-text models under common perturbations on five tasks (image-text retrieval, visual reasoning, visual entailment, image captioning, and text-to-image generation). In particular, we propose several new multimodal robustness benchmarks by applying 17 image perturbation and 16 text perturbation techniques on top of existing datasets. We observe that multimodal models are not robust to image and text perturbations, especially to image perturbations. Among the tested perturbation methods, character-level perturbations constitute the most severe distribution shift for text, and zoom blur is the most severe shift for image data. We also introduce two new robustness metrics (MMI and MOR) for proper evaluations of multimodal models. We hope our extensive study sheds light on new directions for the development of robust multimodal models.

The substitute-based recommendation is widely used in E-commerce to provide better alternatives to customers. However, existing research typically uses the customer behavior signals like co-view and view-but-purchase-another to capture the substitute relationship. Despite its intuitive soundness, we find that such an approach might ignore the functionality and characteristics of products. In this paper, we adapt substitute recommendation into language matching problem by taking product title description as model input to consider product functionality. We design a new transformation method to de-noise the signals derived from production data. In addition, we consider multilingual support from the engineering point of view. Our proposed end-to-end transformer-based model achieves both successes from offline and online experiments. The proposed model has been deployed in a large-scale E-commerce website for 11 marketplaces in 6 languages. Our proposed model is demonstrated to increase revenue by 19% based on an online A/B experiment.

Models should be able to adapt to unseen data during test-time to avoid performance drops caused by inevitable distribution shifts in real-world deployment scenarios. In this work, we tackle the practical yet challenging test-time adaptation (TTA) problem, where a model adapts to the target domain without accessing the source data. We propose a simple recipe called \textit{Data-efficient Prompt Tuning} (DePT) with two key ingredients. First, DePT plugs visual prompts into the vision Transformer and only tunes these source-initialized prompts during adaptation. We find such parameter-efficient finetuning can efficiently adapt the model representation to the target domain without overfitting to the noise in the learning objective. Second, DePT bootstraps the source representation to the target domain by memory bank-based online pseudo-labeling. A hierarchical self-supervised regularization specially designed for prompts is jointly optimized to alleviate error accumulation during self-training. With much fewer tunable parameters, DePT demonstrates not only state-of-the-art performance on major adaptation benchmarks VisDA-C, ImageNet-C, and DomainNet-126, but also superior data efficiency, i.e., adaptation with only 1\% or 10\% data without much performance degradation compared to 100\% data. In addition, DePT is also versatile to be extended to online or multi-source TTA settings.

从传统上讲，地球系统（例如天气和气候）的预测依赖于具有复杂物理模型的数值模拟，因此在计算中既昂贵又对领域专业知识的需求既昂贵。在过去十年中时空地球观察数据的爆炸性增长中，应用深度学习（DL）的数据驱动模型表明了各种地球系统预测任务的潜力。尽管在其他领域取得了广泛的成功，但作为新兴DL架构的变压器在该领域的采用量有限。在本文中，我们提出了Earthformer，这是一种用于地球系统预测的时空变压器。 Earthformer基于一个通用，灵活和有效的时空注意块，名为Cuboid的注意力。这个想法是将数据分解为立方体，并平行应用立方体级别的自我注意力。这些立方体与全球矢量的集合进一步相关。我们对MovingMnist数据集和新提出的混沌N体MNIST数据集进行了实验，以验证Cuboid注意的有效性，并找出地球形式的最佳设计。关于降水现象和El Nino/Southern振荡（ENSO）预测的两个现实基准测试的实验表明，Earthformer实现了最新的性能。

对抗性训练（AT）捍卫深层神经网络免受对抗攻击。限制其实际应用的一个挑战是对干净样品的性能降解。以前的作品确定的主要瓶颈是广泛使用的批准化（BN），它努力为AT中的清洁和对抗训练样本的不同统计数据建模。尽管主要的方法是扩展BN以捕获这种分布的混合物，但我们建议通过去除AT中的所有BN层来完全消除这种瓶颈。我们的无标准器稳健训练（NOFROST）方法将无标准器网络的最新进展扩展到了AT，因为它在处理混合分配挑战方面未开发优势。我们表明，Nofrost在干净的样品准确性上只有轻微的牺牲才能实现对抗性的鲁棒性。在具有RESNET50的Imagenet上，Nofrost可实现$ 74.06 \％$清洁精度，从标准培训中降低了$ 2.00 \％$。相比之下，基于BN的基于BN的$ 59.28 \％$清洁准确性，从标准培训中获得了$ 16.78 \％$的大幅下降。此外，Nofrost在PGD Attack上达到了23.56美元的$ 23.56 \％$的对抗性，这提高了基于BN AT的13.57美元\％$ $鲁棒性。我们观察到更好的模型平滑度和来自Nofrost的较大决策边缘，这使得模型对输入扰动的敏感程度降低，从而更加健壮。此外，当将更多的数据增强纳入NOFROST时，它可以针对多个分配变化实现全面的鲁棒性。代码和预训练的模型在https://github.com/amazon-research/normalizer-free-robust-training上公开。

我们考虑使用自动监督学习系统的数据表，不仅包含数字/分类列，而且还包含一个或多个文本字段。在这里，我们组装了18个多模式数据表，每个数据表都包含一些文本字段并源于真正的业务应用程序。我们的公开的基准使研究人员能够通过数字，分类和文本功能全面评估自己的监督学习方法。为了确保在所有18个数据集上执行良好的任何单一建模策略将作为多式化文本/表格自动机的实用基础，我们的基准中的不同数据集在：样本大小，问题类型（分类和回归任务组合），功能数量（数据集之间的文本列的数量范围为1到28），以及预测信号如何在文本与数字/分类特征（以及预测相互作用）之间分解。在此基准测试中，我们评估各种直接的流水线来模拟这些数据，包括标准的两阶段方法，其中NLP用于团体化文本，然后可以应用表格数据的自动机。与人类数据科学团队相比，在我们的基准测试（堆叠与各种树模型的堆栈组合多峰变压器的堆栈）的全自动方法也可以在两个机器预测竞赛中符合原始文本/表格数据和第二次在卡格的Mercari价格建议挑战中的地方（2380支球队）。

The goal of precipitation nowcasting is to predict the future rainfall intensity in a local region over a relatively short period of time. Very few previous studies have examined this crucial and challenging weather forecasting problem from the machine learning perspective. In this paper, we formulate precipitation nowcasting as a spatiotemporal sequence forecasting problem in which both the input and the prediction target are spatiotemporal sequences. By extending the fully connected LSTM (FC-LSTM) to have convolutional structures in both the input-to-state and state-to-state transitions, we propose the convolutional LSTM (ConvLSTM) and use it to build an end-to-end trainable model for the precipitation nowcasting problem. Experiments show that our ConvLSTM network captures spatiotemporal correlations better and consistently outperforms FC-LSTM and the state-of-theart operational ROVER algorithm for precipitation nowcasting.