Nowadays, Multi-purpose Messaging Mobile App (MMMA) has become increasingly prevalent. MMMAs attract fraudsters and some cybercriminals provide support for frauds via black market accounts (BMAs). Compared to fraudsters, BMAs are not directly involved in frauds and are more difficult to detect. This paper illustrates our BMA detection system SGRL (Self-supervised Graph Representation Learning) used in WeChat, a representative MMMA with over a billion users. We tailor Graph Neural Network and Graph Self-supervised Learning in SGRL for BMA detection. The workflow of SGRL contains a pretraining phase that utilizes structural information, node attribute information and available human knowledge, and a lightweight detection phase. In offline experiments, SGRL outperforms state-of-the-art methods by 16.06%-58.17% on offline evaluation measures. We deploy SGRL in the online environment to detect BMAs on the billion-scale WeChat graph, and it exceeds the alternative by 7.27% on the online evaluation measure. In conclusion, SGRL can alleviate label reliance, generalize well to unseen data, and effectively detect BMAs in WeChat.

As machine learning being used increasingly in making high-stakes decisions, an arising challenge is to avoid unfair AI systems that lead to discriminatory decisions for protected population. A direct approach for obtaining a fair predictive model is to train the model through optimizing its prediction performance subject to fairness constraints, which achieves Pareto efficiency when trading off performance against fairness. Among various fairness metrics, the ones based on the area under the ROC curve (AUC) are emerging recently because they are threshold-agnostic and effective for unbalanced data. In this work, we formulate the training problem of a fairness-aware machine learning model as an AUC optimization problem subject to a class of AUC-based fairness constraints. This problem can be reformulated as a min-max optimization problem with min-max constraints, which we solve by stochastic first-order methods based on a new Bregman divergence designed for the special structure of the problem. We numerically demonstrate the effectiveness of our approach on real-world data under different fairness metrics.

Video generation requires synthesizing consistent and persistent frames with dynamic content over time. This work investigates modeling the temporal relations for composing video with arbitrary length, from a few frames to even infinite, using generative adversarial networks (GANs). First, towards composing adjacent frames, we show that the alias-free operation for single image generation, together with adequately pre-learned knowledge, brings a smooth frame transition without compromising the per-frame quality. Second, by incorporating the temporal shift module (TSM), originally designed for video understanding, into the discriminator, we manage to advance the generator in synthesizing more consistent dynamics. Third, we develop a novel B-Spline based motion representation to ensure temporal smoothness to achieve infinite-length video generation. It can go beyond the frame number used in training. A low-rank temporal modulation is also proposed to alleviate repeating contents for long video generation. We evaluate our approach on various datasets and show substantial improvements over video generation baselines. Code and models will be publicly available at https://genforce.github.io/StyleSV.

While deep reinforcement learning has proven to be successful in solving control tasks, the "black-box" nature of an agent has received increasing concerns. We propose a prototype-based post-hoc policy explainer, ProtoX, that explains a blackbox agent by prototyping the agent's behaviors into scenarios, each represented by a prototypical state. When learning prototypes, ProtoX considers both visual similarity and scenario similarity. The latter is unique to the reinforcement learning context, since it explains why the same action is taken in visually different states. To teach ProtoX about visual similarity, we pre-train an encoder using contrastive learning via self-supervised learning to recognize states as similar if they occur close together in time and receive the same action from the black-box agent. We then add an isometry layer to allow ProtoX to adapt scenario similarity to the downstream task. ProtoX is trained via imitation learning using behavior cloning, and thus requires no access to the environment or agent. In addition to explanation fidelity, we design different prototype shaping terms in the objective function to encourage better interpretability. We conduct various experiments to test ProtoX. Results show that ProtoX achieved high fidelity to the original black-box agent while providing meaningful and understandable explanations.

多元时间序列异常检测已在半监督的设置下进行了广泛的研究，其中需要所有具有正常实例的训练数据集。但是，准备这样的数据集非常费力，因为每个数据实例应完全保证是正常的。因此，希望在没有任何标签知识的情况下基于数据集探索基于数据集的多元时间序列异常检测方法。在本文中，我们提出了MTGFLOF，这是通过动态图和实体意识到的归一化流量进行多变量时间序列异常检测的无监督异常检测方法，仅依靠广泛接受的假设，即异常实例比正常情况表现出稀疏的密度。但是，实体之间的复杂相互依赖性和每个实体的不同固有特征对密度估计提出了重大挑战，更不用说基于估计的可能性分布来检测异常。为了解决这些问题，我们建议通过图结构学习模型来学习实体之间的相互关系，这有助于建模多元时间序列的准确分布。此外，考虑到各个实体的独特特征，开发了实体意识到的归一化流，以将每个实体描述为参数化的正态分布，从而产生细粒密度估计。结合了这两种策略，MTGFlowChieves出色的异常检测性能。进行了现实世界数据集的实验，表明MTGFLOW的表现分别超过了最先进的（SOTA），分别对SWAT和WADI数据集的实验分别高出5.0％和1.6％的AUROC。同样，通过单个实体贡献的异常得分，MTGFLOF可以为检测结果提供解释信息。

我们提出了一种使用加权节点的联合学习方法，可以在其中修改权重以在单独的验证集上优化模型的性能。该问题被称为双重优化，其中内部问题是加权节点的联合学习问题，外部问题着重于基于从内部问题返回的模型的验证性能优化权重。沟通效率的联合优化算法旨在解决此双重优化问题。在遇到错误的假设下，我们分析了输出模型的概括性能，并识别我们的方法在理论上优于训练模型，而仅在本地训练和使用静态且均匀分布的权重进行联合学习。

视觉任务中变形金刚的兴起不仅可以推进网络骨干设计，而且还启动了一个全新的页面，以实现端到端的图像识别（例如，对象检测和泛型分段）。源自自然语言处理（NLP）的变压器体系结构，包括自我注意力和交叉注意力，有效地学习了序列中元素之间的远距离相互作用。但是，我们观察到，大多数现有的基于变压器的视觉模型只是从NLP中借用了这个想法，忽略了语言和图像之间的关键差异，尤其是空间扁平的像素特征的极高序列长度。随后，这阻碍了像素特征和对象查询之间的交叉注意力学习。在本文中，我们重新考虑像素和对象查询之间的关系，并建议将交叉注意学习作为一个聚类过程进行重新重新制定。受传统K-均值聚类算法的启发，我们开发了K-Means面膜Xformer（Kmax-Deeplab）进行细分任务，这不仅可以改善最先进的艺术品，而且享有简单而优雅的设计。结果，我们的Kmax-Deeplab在Coco Val设置上以58.0％的PQ实现了新的最先进的性能，而CityScapes Val设置为68.4％PQ，44.0％AP和83.5％MIOU，而无需测试时间增加或外部数据集。我们希望我们的工作能够阐明设计为视觉任务量身定制的变压器。代码和型号可在https://github.com/google-research/deeplab2上找到

尖峰神经网络（SNNS）是一种实用方法，可以通过模拟神经元对时间信息的杠杆作用来进行更高的数据有效学习。在本文中，我们提出了时间通道联合注意（TCJA）架构单元，这是一种有效的SNN技术，依赖于注意机制，通过有效地沿空间和时间维度沿着尖峰序列的相关性来实现。我们的基本技术贡献在于：1）通过采用挤压操作，将尖峰流压缩为平均矩阵，然后使用具有高效1-D卷积的两种局部注意机制来建立时间和渠道关系，以在频道和渠道关系中进行特征提取灵活的时尚。 2）利用交叉卷积融合（CCF）层在时间范围和通道范围之间建模相互依赖性，从而破坏了两个维度的独立性，并实现了特征之间的相互作用。通过共同探索和重新启用数据流，我们的方法在所有测试的主流静态和神经形态数据集上，在包括时尚量的所有测试的主流静态数据集上，最高可先进的（SOTA）高达15.7％ ，CIFAR10-DVS，N-Caltech 101和DVS128手势。

我们提出了聚类蒙版变压器（CMT-DeepLab），这是一种基于变压器的框架，用于围绕聚类设计的泛型分割。它重新考虑了用于分割和检测的现有变压器架构；CMT-DeepLab认为对象查询是群集中心，该中心填充了应用于分割时将像素分组的作用。群集通过交替的过程计算，首先通过其功能亲和力将像素分配给簇，然后更新集群中心和像素功能。这些操作共同包含聚类蒙版变压器（CMT）层，该层产生了越野器的交叉注意，并且与最终的分割任务更加一致。CMT-DeepLab在可可Test-DEV集中实现了55.7％的PQ的新最先进的PQ，可显着提高先前ART的性能。

旨在将原始视觉观察映射到动作的深度视觉运动策略学习在控制任务（例如机器人操纵和自动驾驶）中实现了有希望的结果。但是，它需要与培训环境进行大量在线互动，这限制了其现实世界的应用程序。与流行的无监督功能学习以进行视觉识别相比，探索视觉运动控制任务的功能预读量要少得多。在这项工作中，我们的目标是通过观看长达数小时的未经保育的YouTube视频来预先驾驶任务的政策表示。具体而言，我们使用少量标记数据训练一个反向动态模型，并使用它来预测所有YouTube视频帧的动作标签。然后开发了一种新的对比策略预告片，以从带有伪动作标签的视频框架中学习动作条件的功能。实验表明，由此产生的动作条件特征为下游增强学习和模仿学习任务提供了实质性改进，超出了从以前的无监督学习方法和图预审预周化的体重中预见的重量。代码，模型权重和数据可在以下网址提供：https：//metadriverse.github.io/aco。