大多数在对话率问题回答中建模对话历史记录(CQA)的作品报告了共同CQA基准测试的主要结果。尽管现有模型在CQA排行榜上显示出令人印象深刻的结果,但尚不清楚它们在设置方面(有时是更现实的),训练数据大小(例如从大型集合到小型集合)和域是否有牢固的变化。在这项工作中,我们设计并进行了首次针对CQA的历史建模方法的大规模鲁棒性研究。我们发现,高基准分数不一定会转化为强大的鲁棒性,并且在不同的设置下,各种方法的性能都大不相同。配备了我们研究的见解,我们设计了一种基于及时的新型历史建模方法,并在各种环境中展示了其强大的鲁棒性。我们的方法灵感来自现有方法,这些方法突出了段落中的历史答案。但是,我们不是通过修改段落令牌嵌入来突出显示,而是直接在段落文本中添加文本提示。我们的方法简单,易于插入实际上任何模型,并且非常有效,因此我们建议它作为未来模型开发人员的起点。我们还希望我们的研究和见解将提高人们对以鲁棒性评估的重要性的认识,除了获得较高的排行榜分数,从而提高了更好的CQA系统。
translated by 谷歌翻译
Models trained from real-world data tend to imitate and amplify social biases. Although there are many methods suggested to mitigate biases, they require a preliminary information on the types of biases that should be mitigated (e.g., gender or racial bias) and the social groups associated with each data sample. In this work, we propose a debiasing method that operates without any prior knowledge of the demographics in the dataset, detecting biased examples based on an auxiliary model that predicts the main model's success and down-weights them during the training process. Results on racial and gender bias demonstrate that it is possible to mitigate social biases without having to use a costly demographic annotation process.
translated by 谷歌翻译
We review clustering as an analysis tool and the underlying concepts from an introductory perspective. What is clustering and how can clusterings be realised programmatically? How can data be represented and prepared for a clustering task? And how can clustering results be validated? Connectivity-based versus prototype-based approaches are reflected in the context of several popular methods: single-linkage, spectral embedding, k-means, and Gaussian mixtures are discussed as well as the density-based protocols (H)DBSCAN, Jarvis-Patrick, CommonNN, and density-peaks.
translated by 谷歌翻译
Transformers have attained superior performance in natural language processing and computer vision. Their self-attention and feedforward layers are overparameterized, limiting inference speed and energy efficiency. Tensor decomposition is a promising technique to reduce parameter redundancy by leveraging tensor algebraic properties to express the parameters in a factorized form. Prior efforts used manual or heuristic factorization settings without hardware-aware customization, resulting in poor hardware efficiencies and large performance degradation. In this work, we propose a hardware-aware tensor decomposition framework, dubbed HEAT, that enables efficient exploration of the exponential space of possible decompositions and automates the choice of tensorization shape and decomposition rank with hardware-aware co-optimization. We jointly investigate tensor contraction path optimizations and a fused Einsum mapping strategy to bridge the gap between theoretical benefits and real hardware efficiency improvement. Our two-stage knowledge distillation flow resolves the trainability bottleneck and thus significantly boosts the final accuracy of factorized Transformers. Overall, we experimentally show that our hardware-aware factorized BERT variants reduce the energy-delay product by 5.7x with less than 1.1% accuracy loss and achieve a better efficiency-accuracy Pareto frontier than hand-tuned and heuristic baselines.
translated by 谷歌翻译
In this paper we look into the conjecture of Entezari et al. (2021) which states that if the permutation invariance of neural networks is taken into account, then there is likely no loss barrier to the linear interpolation between SGD solutions. First, we observe that neuron alignment methods alone are insufficient to establish low-barrier linear connectivity between SGD solutions due to a phenomenon we call variance collapse: interpolated deep networks suffer a collapse in the variance of their activations, causing poor performance. Next, we propose REPAIR (REnormalizing Permuted Activations for Interpolation Repair) which mitigates variance collapse by rescaling the preactivations of such interpolated networks. We explore the interaction between our method and the choice of normalization layer, network width, and depth, and demonstrate that using REPAIR on top of neuron alignment methods leads to 60%-100% relative barrier reduction across a wide variety of architecture families and tasks. In particular, we report a 74% barrier reduction for ResNet50 on ImageNet and 90% barrier reduction for ResNet18 on CIFAR10.
translated by 谷歌翻译
秋季和春季的寒冷温度有可能对葡萄藤和其他水果植物造成霜冻损害,这可能会大大降低收获产量。为了防止这些损失,农民在判断可能造成损失时,采取了昂贵的霜冻缓解措施,例如洒水装置,加热器和风车。然而,这种判断是具有挑战性的,因为植物的冷耐度在整个休眠期间变化,并且很难直接测量。这导致科学家开发了基于费力的现场测量数据,可以将其调整为不同的葡萄品种。在本文中,我们研究了深度学习模型是否可以基于在30年期间收集的数据来改善葡萄的冷坚硬预测。一个关键的挑战是,每个品种的数据量高度可变,有些品种只有少量。为此,我们研究了多任务学习来利用各种品种的数据,以提高个人品种的预测性能。我们评估了许多多任务学习方法,并表明,性能最高的方法能够显着改善单个品种的学习,并优于大多数品种的当前最新科学模型。
translated by 谷歌翻译
在许多情况下,有必要通过观察时间序列监视复杂的系统,并确定何时发生异源事件,以便采取相关的动作。确定当前的观察是否异常是具有挑战性的。它需要从历史数据中学习动力学的外推性概率模型,并使用有限数量的当前观察结果来进行分类。我们利用长期概率预测的最新进展,即{\ em Deep概率Koopman},构建了一种在多维时序数据中对异常进行分类的通用方法。我们还展示了如何利用具有域知识的模型来减少I型和II型错误。我们展示了我们提出的关于全球大气污染监测的重要现实世界任务的方法,并将其与NASA的全球地球系统模型集成在一起。该系统成功地检测到由于COVID-19锁定和野火等事件而导致的空气质量异常情况。
translated by 谷歌翻译
合成孔径声纳(SAS)图像对于多种应用至关重要,包括目标识别和环境分割。深度学习模型在SAS分析中取得了很大的成功。但是,这些方法提取的功能可能不适合捕获某些纹理信息。为了解决这个问题,我们介绍了直方图在SAS图像上的新应用。在深度学习模型中添加直方图层,通过合并合成和现实世界数据集的统计纹理信息来改善性能。
translated by 谷歌翻译
在这项工作中,我们提出了一个完全可区分的图形神经网络(GNN)的架构,用于用于通道解码和展示各种编码方案的竞争性解码性能,例如低密度奇偶校验检查(LDPC)和BCH代码。这个想法是让神经网络(NN)通过给定图的通用消息传递算法,该算法通过用可训练的函数替换节点和边缘消息更新来代表正向误差校正(FEC)代码结构。与许多其他基于深度学习的解码方法相反,提出的解决方案享有对任意块长度的可扩展性,并且训练不受维数的诅咒的限制。我们在常规渠道解码中对最新的解码以及最近的基于深度学习的结果基准了我们提出的解码器。对于(63,45)BCH代码,我们的解决方案优于加权信念传播(BP)的解码约0.4 dB,而解码迭代率明显较小,甚至对于5G NR LDPC代码,我们观察到与常规BP解码相比,我们观察到竞争性能。对于BCH代码,所得的GNN解码器只能以9640个权重进行完全参数。
translated by 谷歌翻译
自Covid-19大流行病开始以来,疫苗一直是公共话语中的重要话题。疫苗周围的讨论被两极分化,因为有些人认为它们是结束大流行的重要措施,而另一些人则犹豫不决或发现它们有害。这项研究调查了与Twitter上的Covid-19疫苗有关的帖子,并着重于对疫苗有负姿态的帖子。收集了与COVID-19疫苗相关的16,713,238个英文推文的数据集,收集了涵盖从2020年3月1日至2021年7月31日的该期间。我们使用Scikit-Learn Python库来应用支持向量机(SVM)分类器针对Covid-19疫苗的推文具有负姿态。总共使用了5,163个推文来训练分类器,其中有2,484个推文由我们手动注释并公开提供。我们使用Berttopic模型来提取和调查负推文中讨论的主题以及它们如何随时间变化。我们表明,随着疫苗的推出,对COVID-19疫苗的负面影响随时间而下降。我们确定了37个讨论主题,并随着时间的推移介绍了各自的重要性。我们表明,流行的主题包括阴谋讨论,例如5G塔和微芯片,但还涉及涉及疫苗接种安全性和副作用以及对政策的担忧。我们的研究表明,即使是不受欢迎的观点或阴谋论,与广受欢迎的讨论主题(例如Covid-19疫苗)配对时,也会变得广泛。了解问题和讨论的主题以及它们如何随着时间的变化对于政策制定者和公共卫生当局提供更好和时间的信息和政策,以促进未来类似危机的人口接种。
translated by 谷歌翻译