Video super-resolution is one of the most popular tasks on mobile devices, being widely used for an automatic improvement of low-bitrate and low-resolution video streams. While numerous solutions have been proposed for this problem, they are usually quite computationally demanding, demonstrating low FPS rates and power efficiency on mobile devices. In this Mobile AI challenge, we address this problem and propose the participants to design an end-to-end real-time video super-resolution solution for mobile NPUs optimized for low energy consumption. The participants were provided with the REDS training dataset containing video sequences for a 4X video upscaling task. The runtime and power efficiency of all models was evaluated on the powerful MediaTek Dimensity 9000 platform with a dedicated AI processing unit capable of accelerating floating-point and quantized neural networks. All proposed solutions are fully compatible with the above NPU, demonstrating an up to 500 FPS rate and 0.2 [Watt / 30 FPS] power consumption. A detailed description of all models developed in the challenge is provided in this paper.

Image super-resolution is a common task on mobile and IoT devices, where one often needs to upscale and enhance low-resolution images and video frames. While numerous solutions have been proposed for this problem in the past, they are usually not compatible with low-power mobile NPUs having many computational and memory constraints. In this Mobile AI challenge, we address this problem and propose the participants to design an efficient quantized image super-resolution solution that can demonstrate a real-time performance on mobile NPUs. The participants were provided with the DIV2K dataset and trained INT8 models to do a high-quality 3X image upscaling. The runtime of all models was evaluated on the Synaptics VS680 Smart Home board with a dedicated edge NPU capable of accelerating quantized neural networks. All proposed solutions are fully compatible with the above NPU, demonstrating an up to 60 FPS rate when reconstructing Full HD resolution images. A detailed description of all models developed in the challenge is provided in this paper.

知识图（kg）嵌入是一种主流方法，用于推理不完整的kg。但是，受其固有浅层和静态体系结构的限制，它们几乎无法处理对复杂逻辑查询的不断上升，这些查询包括逻辑运算符，估算的边缘，多个源实体和未知的中间实体。在这项工作中，我们通过掩盖的预训练和微调策略介绍了知识图变压器（kgtransformer）。我们设计了一种kg三重变换方法，以使变压器能够处理kg，这是通过稀疏（MOE）稀疏激活的混合物进一步增强的。然后，我们将复杂的逻辑查询作为掩盖预测提出，并引入了两阶段掩盖的预训练策略，以提高可转移性和概括性。在两个基准上进行的广泛实验表明，KGTRANSFORMER可以始终超过基于KG的基准和九个内域和室外推理任务的高级编码。此外，KGTRANSFORMER可以通过提供解释给定答案的完整推理路径来解释性。

对用户偏好的演变进行建模对于推荐系统至关重要。最近，已经研究并实现了基于图形的动态方法以供推荐使用，其中大多数侧重于用户稳定的长期偏好。但是，在实际情况下，用户的短期偏好会随着时间的流逝而动态发展。尽管存在试图捕获它的顺序方法，但是如何使用基于动态图的方法对短期偏好的演变进行建模尚未得到很好的认可。特别是：1）现有方法不会像顺序方法一样明确编码和捕获短期偏好的演变； 2）简单地使用最后几个交互不足以建模变化的趋势。在本文中，我们提出了连续时间顺序推荐（LSTSR）的长期短期偏好模型（LSTSR），以捕获动态图下短期偏好的演变。具体而言，我们明确编码短期优先偏好并通过内存机制进行优化，该内存机制具有三个关键操作：消息，汇总和更新。我们的内存机制不仅可以存储单跳信息，而且还可以通过在线新的交互触发。在五个公共数据集上进行的广泛实验表明，LSTSR始终优于各种线路上许多最先进的建议方法。

在线影响最大化旨在通过选择一些种子节点，最大程度地利用未知网络模型的社交网络中内容的影响。最近的研究遵循非自适应设置，在扩散过程开始之前选择种子节点，并且在扩散停止时更新网络参数。我们考虑了与内容相关的在线影响最大化问题的自适应版本，其中种子节点是根据实时反馈依次激活的。在本文中，我们将问题提出为无限马在线性扩散过程中的折扣MDP，并提出了基于模型的增强学习解决方案。我们的算法维护网络模型估算，并适应种子用户，探索社交网络，同时乐观地改善最佳策略。我们建立了$ \ widetilde o（\ sqrt {t}）$遗憾的算法。合成网络的经验评估证明了我们的算法效率。

量化的神经网络通常需要较小的内存占用和较低的计算复杂性，这对于有效部署至关重要。然而，量化不可避免地导致原始网络的分布分发，这通常会降低性能。为了解决这个问题，已经制定了大规模的努力，但大多数现有方法缺乏统计因素，依赖于几种手动配置。在本文中，我们提出了一种自适应映射量化方法，以学习模型内固有的最佳潜在子分布，并用混凝土高斯混合物（GM）平稳地近似。特别地，网络权重被符合GM - 近似的子分布。该子分布随着直接任务客观优化引导的共同调整模式中的重量更新而发展。在各种现代架构上的图像分类和物体检测的充分实验证明了所提出的方法的有效性，泛化性能和可转移性。此外，开发了用于移动CPU的有效部署流，在Octa-Core ARM CPU上实现高达7.46 $ \ Times $推理加速。代码在https://github.com/runpeidong/dgms公开发布。

This work considers the sample complexity of obtaining an $\varepsilon$-optimal policy in an average reward Markov Decision Process (AMDP), given access to a generative model (simulator). When the ground-truth MDP is weakly communicating, we prove an upper bound of $\widetilde O(H \varepsilon^{-3} \ln \frac{1}{\delta})$ samples per state-action pair, where $H := sp(h^*)$ is the span of bias of any optimal policy, $\varepsilon$ is the accuracy and $\delta$ is the failure probability. This bound improves the best-known mixing-time-based approaches in [Jin & Sidford 2021], which assume the mixing-time of every deterministic policy is bounded. The core of our analysis is a proper reduction bound from AMDP problems to discounted MDP (DMDP) problems, which may be of independent interests since it allows the application of DMDP algorithms for AMDP in other settings. We complement our upper bound by proving a minimax lower bound of $\Omega(|\mathcal S| |\mathcal A| H \varepsilon^{-2} \ln \frac{1}{\delta})$ total samples, showing that a linear dependent on $H$ is necessary and that our upper bound matches the lower bound in all parameters of $(|\mathcal S|, |\mathcal A|, H, \ln \frac{1}{\delta})$ up to some logarithmic factors.

Rising usage of deep neural networks to perform decision making in critical applications like medical diagnosis and financial analysis have raised concerns regarding their reliability and trustworthiness. As automated systems become more mainstream, it is important their decisions be transparent, reliable and understandable by humans for better trust and confidence. To this effect, concept-based models such as Concept Bottleneck Models (CBMs) and Self-Explaining Neural Networks (SENN) have been proposed which constrain the latent space of a model to represent high level concepts easily understood by domain experts in the field. Although concept-based models promise a good approach to both increasing explainability and reliability, it is yet to be shown if they demonstrate robustness and output consistent concepts under systematic perturbations to their inputs. To better understand performance of concept-based models on curated malicious samples, in this paper, we aim to study their robustness to adversarial perturbations, which are also known as the imperceptible changes to the input data that are crafted by an attacker to fool a well-learned concept-based model. Specifically, we first propose and analyze different malicious attacks to evaluate the security vulnerability of concept based models. Subsequently, we propose a potential general adversarial training-based defense mechanism to increase robustness of these systems to the proposed malicious attacks. Extensive experiments on one synthetic and two real-world datasets demonstrate the effectiveness of the proposed attacks and the defense approach.

值得信赖的强化学习算法应有能力解决挑战性的现实问题，包括{Robustly}处理不确定性，满足{安全}的限制以避免灾难性的失败，以及在部署过程中{prencepentiming}以避免灾难性的失败}。这项研究旨在概述这些可信赖的强化学习的主要观点，即考虑其在鲁棒性，安全性和概括性上的内在脆弱性。特别是，我们给出严格的表述，对相应的方法进行分类，并讨论每个观点的基准。此外，我们提供了一个前景部分，以刺激有希望的未来方向，并简要讨论考虑人类反馈的外部漏洞。我们希望这项调查可以在统一的框架中将单独的研究汇合在一起，并促进强化学习的可信度。

鉴于神经网络有区别，公平性改善的问题是系统地减少歧视，而不会显着削弱其性能（即准确性）。已经提出了针对神经网络的多种公平改进方法，包括预处理，处理和后处理。然而，我们的实证研究表明，这些方法并不总是有效的（例如，它们可以通过支付巨大准确性下降的价格来提高公平性），甚至没有帮助（例如，它们甚至可能使公平性和准确性都恶化）。在这项工作中，我们提出了一种基于因果分析的公平性改进方法的方法。也就是说，我们根据如何在输入属性和隐藏的神经元之间分布的神经元和属性如何选择方法。我们的实验评估表明，我们的方法是有效的（即，始终确定最佳的公平改善方法）和有效的效率（即，平均时间开销为5分钟）。