The aggregation of medin forming aortic medial amyloid is linked to arterial wall degeneration and cerebrovascular dysfunction. Elevated levels of arteriolar medin are correlated with an increased presence of vascular amyloid-β (Aβ) aggregates, a hallmark of Alzheimer's disease (AD) and vascular dementia. The cross-interaction between medin and Aβ results in the formation of heterologous fibrils through co-aggregation and cross-seeding processes both in vitro and in vivo. However, a comprehensive molecular understanding of the cross-interaction between medin and Aβ-two intrinsically disordered proteins-is critically lacking. Here, we employed atomistic discrete molecular dynamics simulations to systematically investigate the self-association, co-aggregation and also the phenomenon of cross-seeding between these two proteins. Our results demonstrated that both Aβ and medin were aggregation prone and their mixture tended to form β-sheet-rich hetero-aggregates. The formation of Aβ-medin hetero-aggregates did not hinder Aβ and medin from recruiting additional Aβ and medin peptides to grow into larger β-sheet-rich aggregates. The β-barrel oligomer intermediates observed in the self-aggregations of Aβ and medin were also present during their co-aggregation. In cross-seeding simulations, preformed Aβ fibrils could recruit isolated medin monomers to form elongated β-sheets. Overall, our comprehensive simulations suggested that the cross-interaction between Aβ and medin may contribute to their pathological aggregation, given the inherent amyloidogenic tendencies of both medin and Aβ. Targeting medin, therefore, could offer a novel therapeutic approach to preserving brain function during aging and AD by improving vascular health.

Single domain generalization aims to learn a model that performs well on many unseen domains with only one domain data for training. Existing works focus on studying the adversarial domain augmentation (ADA) to improve the model’s generalization capability. The impact on domain generalization of the statistics of normalization layers is still underinvestigated. In this paper, we propose a generic normalization approach, adaptive standardization and rescaling normalization (ASR-Norm), to complement the missing part in previous works. ASR-Norm learns both the standardization and rescaling statistics via neural networks. This new form of normalization can be viewed as a generic form of the traditional normalizations. When trained with ADA, the statistics in ASR-Norm are learned to be adaptive to the data coming from different domains, and hence improves the model generalization performance across domains, especially on the target domain with large discrepancy from the source domain. The experimental results show that ASR-Norm can bring consistent improvement to the state-of-the-art ADA approaches by 1.6%, 2.7%, and 6.3% averagely on the Digits, CIFAR-10-C, and PACS benchmarks, respectively. As a generic tool, the improvement introduced by ASR-Norm is agnostic to the choice of ADA methods.

Attention-based neural networks have achieved state-of-the-art results on a wide range of tasks. Most such models use deterministic attention while stochastic attention is less explored due to the optimization difficulties or complicated model design. This paper introduces Bayesian attention belief networks, which construct a decoder network by modeling unnormalized attention weights with a hierarchy of gamma distributions, and an encoder network by stacking Weibull distributions with a deterministic-upward-stochastic-downward structure to approximate the posterior. The resulting auto-encoding networks can be optimized in a differentiable way with a variational lower bound. It is simple to convert any models with deterministic attention, including pretrained ones, to the proposed Bayesian attention belief networks. On a variety of language understanding tasks, we show that our method outperforms deterministic attention and state-of-the-art stochastic attention in accuracy, uncertainty estimation, generalization across domains, and robustness to adversarial attacks. We further demonstrate the general applicability of our method on neural machine translation and visual question answering, showing great potential of incorporating our method into various attention-related tasks.

Existing methods for unsupervised domain adaptation often rely on minimizing some statistical distance between the source and target samples in the latent space. To avoid the sampling variability, class imbalance, and data-privacy concerns that often plague these methods, we instead provide a memory and computation-efficient probabilistic framework to extract class prototypes and align the target features with them. We demonstrate the general applicability of our method on a wide range of scenarios, including single-source, multi-source, class-imbalance, and source-private domain adaptation. Requiring no additional model parameters and having a moderate increase in computation over the source model alone, the proposed method achieves competitive performance with state-of-the-art methods.

The neural attention mechanism has been incorporated into deep neural networks to achieve state-of-the-art performance in various domains. Most such models use multi-head self-attention which is appealing for the ability to attend to information from different perspectives. This paper introduces alignment attention that explicitly encourages self-attention to match the distributions of the key and query within each head. The resulting alignment attention networks can be optimized as an unsupervised regularization in the existing attention framework. It is simple to convert any models with self-attention, including pre-trained ones, to the proposed alignment attention. On a variety of language understanding tasks, we show the effectiveness of our method in accuracy, uncertainty estimation, generalization across domains, and robustness to adversarial attacks. We further demonstrate the general applicability of our approach on graph attention and visual question answering, showing the great potential of incorporating our alignment method into various attention-related tasks.

Tuning hyperparameters for unsupervised learning problems is difficult in general due to the lack of ground truth for validation. However, the success of most clustering methods depends heavily on the correct choice of the involved hyperparameters. Take for example the Lagrange multipliers of penalty terms in semidefinite programming (SDP) relaxations of community detection in networks, or the bandwidth parameter needed in the Gaussian kernel used to construct similarity matrices for spectral clustering. Despite the popularity of these clustering algorithms, there are not many provable methods for tuning these hyperparameters. In this paper, we provide an overarching framework with provable guarantees for tuning hyperparameters in the above class of problems under two different models. Our framework can be augmented with a cross validation procedure to do model selection as well. In a variety of simulation and real data experiments, we show that our framework outperforms other widely used tuning procedures in a broad range of parameter settings.

Attention modules, as simple and effective tools, have not only enabled deep neural networks to achieve state-of-the-art results in many domains, but also enhanced their interpretability. Most current models use deterministic attention modules due to their simplicity and ease of optimization. Stochastic counterparts, on the other hand, are less popular despite their potential benefits. The main reason is that stochastic attention often introduces optimization issues or requires significant model changes. In this paper, we propose a scalable stochastic version of attention that is easy to implement and optimize. We construct simplex-constrained attention distributions by normalizing reparameterizable distributions, making the training process differentiable. We learn their parameters in a Bayesian framework where a data-dependent prior is introduced for regularization. We apply the proposed stochastic attention modules to various attention-based models, with applications to graph node classification, visual question answering, image captioning, machine translation, and language understanding. Our experiments show the proposed method brings consistent improvements over the corresponding baselines.

Hashing has become an increasingly popular technique for fast nearest neighbor search. Despite its successful progress in classic pointto-point search, there are few studies regarding point-to-hyperplane search, which has strong practical capabilities of scaling up applications like active learning with SVMs. Existing hyperplane hashing methods enable the fast search based on randomly generated hash codes, but still suffer from a low collision probability and thus usually require long codes for a satisfying performance. To overcome this problem, this paper proposes a multilinear hyperplane hashing that generates a hash bit using multiple linear projections. Our theoretical analysis shows that with an even number of random linear projections, the multilinear hash function possesses strong locality sensitivity to hyperplane queries. To leverage its sensitivity to the angle distance, we further introduce an angular quantization based learning framework for compact multilinear hashing, which considerably boosts the search performance with less hash bits. Experiments with applications to large-scale (up to one million) active learning on two datasets demonstrate the overall superiority of the proposed approach.