In the field of cross-modal retrieval, single encoder models tend to perform better than dual encoder models, but they suffer from high latency and low throughput. In this paper, we present a dual encoder model called BagFormer that utilizes a cross modal interaction mechanism to improve recall performance without sacrificing latency and throughput. BagFormer achieves this through the use of bag-wise interactions, which allow for the transformation of text to a more appropriate granularity and the incorporation of entity knowledge into the model. Our experiments demonstrate that BagFormer is able to achieve results comparable to state-of-the-art single encoder models in cross-modal retrieval tasks, while also offering efficient training and inference with 20.72 times lower latency and 25.74 times higher throughput.
translated by 谷歌翻译
The number of international benchmarking competitions is steadily increasing in various fields of machine learning (ML) research and practice. So far, however, little is known about the common practice as well as bottlenecks faced by the community in tackling the research questions posed. To shed light on the status quo of algorithm development in the specific field of biomedical imaging analysis, we designed an international survey that was issued to all participants of challenges conducted in conjunction with the IEEE ISBI 2021 and MICCAI 2021 conferences (80 competitions in total). The survey covered participants' expertise and working environments, their chosen strategies, as well as algorithm characteristics. A median of 72% challenge participants took part in the survey. According to our results, knowledge exchange was the primary incentive (70%) for participation, while the reception of prize money played only a minor role (16%). While a median of 80 working hours was spent on method development, a large portion of participants stated that they did not have enough time for method development (32%). 25% perceived the infrastructure to be a bottleneck. Overall, 94% of all solutions were deep learning-based. Of these, 84% were based on standard architectures. 43% of the respondents reported that the data samples (e.g., images) were too large to be processed at once. This was most commonly addressed by patch-based training (69%), downsampling (37%), and solving 3D analysis tasks as a series of 2D tasks. K-fold cross-validation on the training set was performed by only 37% of the participants and only 50% of the participants performed ensembling based on multiple identical models (61%) or heterogeneous models (39%). 48% of the respondents applied postprocessing steps.
translated by 谷歌翻译
Recently, the success of pre-training in text domain has been fully extended to vision, audio, and cross-modal scenarios. The proposed pre-training models of different modalities are showing a rising trend of homogeneity in their model structures, which brings the opportunity to implement different pre-training models within a uniform framework. In this paper, we present TencentPretrain, a toolkit supporting pre-training models of different modalities. The core feature of TencentPretrain is the modular design. The toolkit uniformly divides pre-training models into 5 components: embedding, encoder, target embedding, decoder, and target. As almost all of common modules are provided in each component, users can choose the desired modules from different components to build a complete pre-training model. The modular design enables users to efficiently reproduce existing pre-training models or build brand-new one. We test the toolkit on text, vision, and audio benchmarks and show that it can match the performance of the original implementations.
translated by 谷歌翻译
尽管强化学习可以为复杂的任务取得令人印象深刻的结果,但学习的政策通常容易在下游任务中失败,甚至较小的模型不匹配或意外的扰动。最近的工作表明,具有不同行为特征的政策人群可以推广到具有各种差异的下游环境。但是,由于受过训练的政策的不受限制行为,这种政策在部署过程中的部署期间可能会导致灾难性损害。此外,培训不同的策略而不对行为进行调节的策略可能导致不足的政策,以推断出具有动态变化的广泛测试条件。在这项工作中,我们旨在根据行为模式的正规化培训各种政策。我们通过观察环境中的反向动态来激励我们的范式,并提出了通过调节行为进行调节的多样性(DIR)培训各种政策,以发现受益的概括的所需模式。对不同环境的各种变化的大量经验结果表明,我们的方法比其他多样性驱动的对应物取得了改进。
translated by 谷歌翻译
培训强大的政策对于现实世界中的政策部署至关重要,或者处理不同动态系统中未知动态不匹配。域随机化〜(DR)是一种简单而优雅的方法,可以训练保守的政策,以反对不同的动态系统,而无需有关目标系统参数的专家知识。但是,现有的作品表明,通过DR培训的政策往往保守过度保守,并且在目标领域的表现差。我们的关键见解是,具有不同参数的动态系统为策略提供了不同级别的难度,并且由于策略的发展,在系统中表现良好的难度正在不断变化。如果我们可以为该政策进行适当的困难来积极地对系统进行采样,它将稳定培训过程,并防止政策变得过于保守或过度优势。为了实现这一想法,我们引入了主动动力学偏好(ADP),从而量化了采样系统参数的信息性和密度。 ADP积极选择具有高信息性和低密度的系统参数。我们在四个机器人运动任务中验证我们的方法,并在训练环境和测试环境之间存在各种差异。广泛的结果表明,与几个基线相比,我们的方法对系统不一致具有较高的鲁棒性。
translated by 谷歌翻译
尽管条件变异自动编码器(CVAE)模型比传统的SEQ2SEQ模型可以产生更多的多样化响应,但响应通常与输入词的相关性低或与问题不合逻辑。进行因果分析以研究背后的原因,并提供了一种寻找调解人并减轻对话中混杂偏见的方法。具体而言,我们建议预测调解人,以保留相关信息,并自动将调解人纳入生成过程中。此外,动态主题图指导条件变异自动编码器(TGG-CVAE)模型用于补充语义空间并减少响应中的混杂偏置。广泛的实验表明,所提出的模型能够产生相关和信息性的响应,并且在自动指标和人类评估方面优于最先进的响应。
translated by 谷歌翻译
联合学习(FL)已成为解决数据筒仓问题的实用解决方案,而不会损害用户隐私。它的一种变体垂直联合学习(VFL)最近引起了人们的关注,因为VFL与企业对利用更有价值的功能的需求相匹配,以构建更好的机器学习模型,同时保留用户隐私。当前在VFL中的工作集中于为特定VFL算法开发特定的保护或攻击机制。在这项工作中,我们提出了一个评估框架,该框架提出了隐私 - 私人评估问题。然后,我们将此框架作为指南,以全面评估针对三种广泛依据的VFL算法的大多数最先进的隐私攻击的广泛保护机制。这些评估可以帮助FL从业人员在特定要求下选择适当的保护机制。我们的评估结果表明:模型反转和大多数标签推理攻击可能会因现有保护机制而挫败;很难防止模型完成(MC)攻击,这需要更高级的MC靶向保护机制。根据我们的评估结果,我们为提高VFL系统的隐私保护能力提供具体建议。
translated by 谷歌翻译
联合学习(FL)使参与方能够在不公开私人数据信息的情况下协作建立一个全球模型。必须采用适当的保护机制,以满足保留\ textit {privacy}并维护高模型\ textit {utility}的相反要求。此外,为了实现大规模的模型培训和部署,联合学习系统实现高\ textit {效率}是一项任务。我们提出了一个统一的联合学习框架,可以调和水平和垂直的联合学习。基于此框架,我们制定和量化了隐私泄漏,公用事业损失和降低效率之间的权衡,这使我们成为了联合学习系统的无午餐定理(NFL)定理。 NFL表示,期望FL算法同时在某些情况下同时提供出色的隐私,实用性和效率是不现实的。然后,我们分析了几种广泛补习的保护机制的隐私泄漏,效用损失和效率降低的下限,包括\ textit {Randomization},\ textIt {同粒子加密},\ textit {secretit {secret {sertial {sertion {sertion {compression} {Compression}。我们的分析可以作为选择保护参数以满足特定要求的指南。
translated by 谷歌翻译
二进制代码相似性检测(BCSD)方法测量了两个二进制可执行代码的相似性。最近,基于学习的BCSD方法取得了巨大的成功,在检测准确性和效率方面表现优于传统的BCSD。但是,现有的研究在基于学习的BCSD方法的对抗脆弱性上相当稀疏,这会导致与安全相关的应用程序危害。为了评估对抗性的鲁棒性,本文设计了一种高效且黑色的对抗代码生成算法,即FuncFooler。 FuncFooler限制了对抗代码1)保持程序的控制流程图(CFG)和2)保持相同的语义含义。具体而言,funcfooler连续1)在恶意代码中确定脆弱的候选人,2)从良性代码中选择和插入对抗性指令,以及3)纠正对抗代码的语义副作用以满足约束。从经验上讲,我们的FuncFooler可以成功攻击包括Safe,ASM2VEC和JTRAN在内的三种基于学习的BCSD模型,它们质疑是否需要基于学习的BCSD。
translated by 谷歌翻译
营销活动是一系列战略活动,可以促进企业的目标。在真正的工业场景中,营销活动的效果预测非常复杂且具有挑战性,因为通常从观察数据中学到了先验知识,而没有任何营销活动干预。此外,每个主题始终在几个营销活动的干预下同时受到干扰。因此,我们无法轻松解析和评估单个营销活动的效果。据我们所知,目前尚无有效的方法来解决此类问题,即,基于具有多个相互缠绕事件的层次结构对个体级别的预测任务进行建模。在本文中,我们对效果预测任务中涉及的基础解析树的结构进行了深入的分析,并进一步建立了一个层次结构胶囊预测网络(HAPNET)来预测营销活动的影响。基于合成数据和实际数据的广泛结果证明了我们模型比最新方法的优越性,并在实际工业应用中表现出显着的实用性。
translated by 谷歌翻译