在本文中，我们提出了与IEEE计算机协会在CVPR 2022上同时与IEEE计算机协会研讨会同时举行的多手术检测挑战。我们的多手术检测挑战旨在检测自动图像操作，包括但不限于图像编辑，图像合成，图像合成，图像，图像，图像，图像合成，图像，图像编辑一代，图像Photoshop等。我们的挑战吸引了来自世界各地的674支团队，约有2000个有效的结果提交数量。我们邀请了前十支球队为挑战提供解决方案，其中三支球队在大结局中获得了奖项。在本文中，我们介绍了前三名团队的解决方案，以增强图像伪造检测领域的研究工作。

异质图神经网络（HGNN）提供了强大的能力，可以将异质图的丰富结构和语义信息嵌入到低维节点表示中。现有的HGNN通常会学习使用层次结构注意机制和重复的邻居聚集来嵌入信息，并遭受不必要的复杂性和冗余计算。本文提出了简单有效的异质图神经网络（SEHGNN），该图通过避免在相同关系中避免过度使用的节点级别的注意来降低这种过度的复杂性，并在预处理阶段预先计算邻居聚集。与以前的工作不同，Sehgnn利用轻重量参数的邻居聚合器来学习每个Metapath的结构信息，以及一个基于变压器的语义聚合器将跨Metapaths的语义信息组合为每个节点的最终嵌入。结果，SEHGNN提供了简单的网络结构，高预测准确性和快速训练速度。在五个现实世界的异质图上进行了广泛的实验，证明了Sehgnn在准确性和训练速度上的优越性。代码可在https://github.com/ict-gimlab/sehgnn上找到。

最近，图形神经网络（GNN）通过利用图形结构和节点特征的知识来表现出图表表示的显着性能。但是，他们中的大多数都有两个主要限制。首先，GNN可以通过堆叠更多的层来学习高阶结构信息，但由于过度光滑的问题，无法处理较大的深度。其次，由于昂贵的计算成本和高内存使用情况，在大图上应用这些方法并不容易。在本文中，我们提出了节点自适应特征平滑（NAFS），这是一种简单的非参数方法，该方法构建了没有参数学习的节点表示。 NAFS首先通过特征平滑提取每个节点及其不同啤酒花的邻居的特征，然后自适应地结合了平滑的特征。此外，通过不同的平滑策略提取的平滑特征的合奏可以进一步增强构建的节点表示形式。我们在两个不同的应用程序方案上对四个基准数据集进行实验：节点群集和链接预测。值得注意的是，具有功能合奏的NAFS优于这些任务上最先进的GNN，并减轻上述大多数基于学习的GNN对应物的两个限制。

Cooperative multi-agent reinforcement learning (MARL) has made prominent progress in recent years. For training efficiency and scalability, most of the MARL algorithms make all agents share the same policy or value network. However, in many complex multi-agent tasks, different agents are expected to possess specific abilities to handle different subtasks. In those scenarios, sharing parameters indiscriminately may lead to similar behavior across all agents, which will limit the exploration efficiency and degrade the final performance. To balance the training complexity and the diversity of agent behavior, we propose a novel framework to learn dynamic subtask assignment (LDSA) in cooperative MARL. Specifically, we first introduce a subtask encoder to construct a vector representation for each subtask according to its identity. To reasonably assign agents to different subtasks, we propose an ability-based subtask selection strategy, which can dynamically group agents with similar abilities into the same subtask. In this way, agents dealing with the same subtask share their learning of specific abilities and different subtasks correspond to different specific abilities. We further introduce two regularizers to increase the representation difference between subtasks and stabilize the training by discouraging agents from frequently changing subtasks, respectively. Empirical results show that LDSA learns reasonable and effective subtask assignment for better collaboration and significantly improves the learning performance on the challenging StarCraft II micromanagement benchmark and Google Research Football.

基于最新的激光痛的3D对象检测方法依赖于监督学习和大型标记数据集。但是，注释LiDAR数据是资源消耗的，仅取决于监督的学习限制了训练有素的模型的适用性。自我监督的培训策略可以通过学习下游3D视觉任务的通用点云主链模型来减轻这些问题。在此背景下，我们显示了自我监督的多帧流程表示与单帧3D检测假设之间的关系。我们的主要贡献利用了流动和运动表示，并将自我保护的主链与有监督的3D检测头结合在一起。首先，自我监督的场景流估计模型通过循环一致性进行了训练。然后，该模型的点云编码器用作单帧3D对象检测头模型的骨干。第二个3D对象检测模型学会利用运动表示来区分表现出不同运动模式的动态对象。 Kitti和Nuscenes基准的实验表明，提出的自我监管的预训练可显着提高3D检测性能。 https://github.com/emecercelik/ssl-3d-detection.git

移动机器人的成功操作要求它们迅速适应环境变化。为了为移动机器人开发自适应决策工具，我们提出了一种新颖的算法，该算法将元强化学习（META-RL）与模型预测控制（MPC）相结合。我们的方法采用额外的元元素算法作为基线，以使用MPC生成的过渡样本来训练策略，当机器人检测到某些事件可以通过MPC有效处理的某些事件，并明确使用机器人动力学。我们方法的关键思想是以随机和事件触发的方式在元学习策略和MPC控制器之间进行切换，以弥补由有限的预测范围引起的次优MPC动作。在元测试期间，将停用MPC模块，以显着减少运动控制中的计算时间。我们进一步提出了一种在线适应方案，该方案使机器人能够在单个轨迹中推断并适应新任务。通过使用（i）障碍物的合成运动和（ii）现实世界的行人运动数据，使用非线性汽车样的车辆模型来证明我们方法的性能。模拟结果表明，我们的方法在学习效率和导航质量方面优于其他算法。

Feature selection helps reduce data acquisition costs in ML, but the standard approach is to train models with static feature subsets. Here, we consider the dynamic feature selection (DFS) problem where a model sequentially queries features based on the presently available information. DFS is often addressed with reinforcement learning (RL), but we explore a simpler approach of greedily selecting features based on their conditional mutual information. This method is theoretically appealing but requires oracle access to the data distribution, so we develop a learning approach based on amortized optimization. The proposed method is shown to recover the greedy policy when trained to optimality and outperforms numerous existing feature selection methods in our experiments, thus validating it as a simple but powerful approach for this problem.

Relation Extraction (RE) has been extended to cross-document scenarios because many relations are not simply described in a single document. This inevitably brings the challenge of efficient open-space evidence retrieval to support the inference of cross-document relations, along with the challenge of multi-hop reasoning on top of entities and evidence scattered in an open set of documents. To combat these challenges, we propose Mr.CoD, a multi-hop evidence retrieval method based on evidence path mining and ranking with adapted dense retrievers. We explore multiple variants of retrievers to show evidence retrieval is an essential part in cross-document RE. Experiments on CodRED show that evidence retrieval with Mr.Cod effectively acquires cross-document evidence that essentially supports open-setting cross-document RE. Additionally, we show that Mr.CoD facilitates evidence retrieval and boosts end-to-end RE performance with effective multi-hop reasoning in both closed and open settings of RE.

Two key obstacles in biomedical relation extraction (RE) are the scarcity of annotations and the prevalence of instances without explicitly pre-defined labels due to low annotation coverage. Existing approaches, which treat biomedical RE as a multi-class classification task, often result in poor generalization in low-resource settings and do not have the ability to make selective prediction on unknown cases but give a guess from seen relations, hindering the applicability of those approaches. We present NBR, which converts biomedical RE as natural language inference formulation through indirect supervision. By converting relations to natural language hypotheses, NBR is capable of exploiting semantic cues to alleviate annotation scarcity. By incorporating a ranking-based loss that implicitly calibrates abstinent instances, NBR learns a clearer decision boundary and is instructed to abstain on uncertain instances. Extensive experiments on three widely-used biomedical RE benchmarks, namely ChemProt, DDI and GAD, verify the effectiveness of NBR in both full-set and low-resource regimes. Our analysis demonstrates that indirect supervision benefits biomedical RE even when a domain gap exists, and combining NLI knowledge with biomedical knowledge leads to the best performance gains.

Optimization in multi-task learning (MTL) is more challenging than single-task learning (STL), as the gradient from different tasks can be contradictory. When tasks are related, it can be beneficial to share some parameters among them (cooperation). However, some tasks require additional parameters with expertise in a specific type of data or discrimination (specialization). To address the MTL challenge, we propose Mod-Squad, a new model that is Modularized into groups of experts (a 'Squad'). This structure allows us to formalize cooperation and specialization as the process of matching experts and tasks. We optimize this matching process during the training of a single model. Specifically, we incorporate mixture of experts (MoE) layers into a transformer model, with a new loss that incorporates the mutual dependence between tasks and experts. As a result, only a small set of experts are activated for each task. This prevents the sharing of the entire backbone model between all tasks, which strengthens the model, especially when the training set size and the number of tasks scale up. More interestingly, for each task, we can extract the small set of experts as a standalone model that maintains the same performance as the large model. Extensive experiments on the Taskonomy dataset with 13 vision tasks and the PASCAL-Context dataset with 5 vision tasks show the superiority of our approach.