While the backpropagation of error algorithm allowed for a rapid rise in the development and deployment of artificial neural networks, two key issues currently preclude biological plausibility: (i) symmetry is required between forward and backward weights, which is known as the weight transport problem, and (ii) updates are locked before both the forward and backward passes have been completed. The feedback alignment (FA) algorithm uses fixed random feedback weights to release the weight transport problem. The direct feedback alignment (DFA) variation directly propagates the output error to each hidden layer through fixed random connectivity matrices. In this work, we show that using only the error sign is sufficient to maintain feedback alignment and to provide learning in the hidden layers. As in classification problems the error sign information is already contained in the target vector, using the latter as a proxy for the error brings three advantages: (i) it solves the weight transport problem by eliminating the requirement for an explicit feedback pathway, which also reduces the computational workload, (ii) it reduces memory requirements by removing update locking, allowing for weight updates to be computed in each layer independently without requiring a full forward pass, and (iii) it leads to a purely feedforward and low-cost algorithm that only requires a label-dependent random vector selection to estimate the layerwise loss gradients. Therefore, in this work, we propose the direct random target projection (DRTP) algorithm and demonstrate on the MNIST and CIFAR-10 datasets that, despite the absence of an explicit error feedback, DRTP performance can still lie close to the one of BP, FA and DFA. The low memory and computational cost of DRTP and its reliance only on layerwise feedforward computation make it suitable for deployment in adaptive edge computing devices.

Graph Neural Networks (GNNs) have been widely studied for graph data representation and learning. However, existing GNNs generally conduct context-aware learning on node feature representation only which usually ignores the learning of edge (weight) representation. In this paper, we propose a novel unified GNN model, named Context-aware Adaptive Graph Attention Network (CaGAT). CaGAT aims to learn a context-aware attention representation for each graph edge by further exploiting the context relationships among different edges. In particular, CaGAT conducts context-aware learning on both node feature representation and edge (weight) representation simultaneously and cooperatively in a unified manner which can boost their respective performance in network training. We apply CaGAT on semi-supervised learning tasks. Promising experimental results on several benchmark datasets demonstrate the effectiveness and benefits of CaGAT.

When a robot acquires new information, ideally it would immediately be capable of using that information to understand its environment. While deep neural networks are now widely used by robots for inferring semantic information, conventional neural networks suffer from catastrophic forgetting when they are incrementally updated, with new knowledge overwriting established representations. While a variety of approaches have been developed that attempt to mitigate catastrophic forgetting in the incremental batch learning scenario, in which an agent learns a large collection of labeled samples at once, streaming learning has been much less studied in the robotics and deep learning communities. In streaming learning, an agent learns instances one-by-one and can be tested at any time. Here, we revisit streaming linear discriminant analysis, which has been widely used in the data mining research community. By combining streaming linear discriminant analysis with deep learning, we are able to outperform both incremental batch learning and streaming learning algorithms on both ImageNet-1K and CORe50.

Graph Convolutional Networks (GCNs) have been widely studied for graph data representation and learning. The graph convolution operation in GCNs can usually be regarded as a composition of feature aggregation/propagation and transformation. Existing GCNs generally conduct feature aggregation on a fixed neighborhood graph in which each node computes its representation by aggregating the feature representations of all its neighbors (biased by its own representation). However, this fixed aggregation strategy is not guaranteed to be optimal for GCN based graph learning and also can be affected by some graph structure noises, such as incorrect or undesired edge connections. To address these issues, we propose a novel Graph mask Convolutional Network (GmCN) in which nodes can adaptively select the optimal neighbors in their feature aggregation to better serve GCN learning. More importantly, GmCN can be theoretically interpreted by a unified regularization framework, based on which we derive a simple update algorithm to determine the optimal mask adaptively in GmCN training process. Experiments on several datasets demonstrate the effectiveness of GmCN.

Despite many years of research into latent Dirichlet allocation (LDA), applying LDA to collections of non-categorical items is still challenging. Yet many problems with much richer data share a similar structure and could benefit from the vast literature on LDA. We propose logistic LDA, a novel discriminative variant of latent Dirichlet allocation which is easy to apply to arbitrary inputs. In particular, our model can easily be applied to groups of images, arbitrary text embeddings, and integrate well with deep neural networks. Although it is a discriminative model, we show that logistic LDA can learn from unlabeled data in an unsupervised manner by exploiting the group structure present in the data. In contrast to other recent topic models designed to handle arbitrary inputs, our model does not sacrifice the interpretability and principled motivation of LDA.

To improve the ability of VAE to disentangle in the latent space, existing works mostly focus on enforcing independence among the learned latent factors. However, the ability of these models to disentangle often decreases as the complexity of the generative factors increases. In this paper, we investigate the little-explored effect of the modeling capacity of a posterior density on the disentangling ability of the VAE. We note that the independence within and the complexity of the latent density are two different properties we constrain when regularizing the posterior density: while the former promotes the disentangling ability of VAE, the latter -- if overly limited -- creates an unnecessary competition with the data reconstruction objective in VAE. Therefore, if we preserve the independence but allow richer modeling capacity in the posterior density, we will lift this competition and thereby allow improved independence and data reconstruction at the same time. We investigate this theoretical intuition with a VAE that utilizes a non-parametric latent factor model, the Indian Buffet Process (IBP), as a latent density that is able to grow with the complexity of the data. Across three widely-used benchmark data sets and two clinical data sets little explored for disentangled learning, we qualitatively and quantitatively demonstrated the improved disentangling performance of IBP-VAE over the state of the art. In the latter two clinical data sets riddled with complex factors of variations, we further demonstrated that unsupervised disentangling of nuisance factors via IBP-VAE -- when combined with a supervised objective -- can not only improve task accuracy in comparison to relevant supervised deep architectures but also facilitate knowledge discovery related to task decision-making. A shorter version of this work will appear in the ICDM 2019 conference proceedings.

Model extraction allows an adversary to steal a copy of a remotely deployed machine learning model given access to its predictions. Adversaries are motivated to mount such attacks for a variety of reasons, ranging from reducing their computational costs, to eliminating the need to collect expensive training data, to obtaining a copy of a model in order to find adversarial examples, perform membership inference, or model inversion attacks. In this paper, we taxonomize the space of model extraction attacks around two objectives: \emph{accuracy}, i.e., performing well on the underlying learning task, and \emph{fidelity}, i.e., matching the predictions of the remote victim classifier on any input. To extract a high-accuracy model, we develop a learning-based attack which exploits the victim to supervise the training of an extracted model. Through analytical and empirical arguments, we then explain the inherent limitations that prevent any learning-based strategy from extracting a truly high-fidelity model---i.e., extracting a functionally-equivalent model whose predictions are identical to those of the victim model on all possible inputs. Addressing these limitations, we expand on prior work to develop the first practical functionally-equivalent extraction attack for direct extraction (i.e., without training) of a model's weights. We perform experiments both on academic datasets and a state-of-the-art image classifier trained with 1 billion proprietary images. In addition to broadening the scope of model extraction research, our work demonstrates the practicality of model extraction attacks against production-grade systems.

Recently, consistency-based methods have achieved state-of-the-art results in semi-supervised learning (SSL). These methods always involve two roles, an explicit or implicit teacher model and a student model, and penalize predictions under different perturbations by a consistency constraint. However, the weights of these two roles are tightly coupled since the teacher is essentially an exponential moving average (EMA) of the student. In this work, we show that the coupled EMA teacher causes a performance bottleneck. To address this problem, we introduce Dual Student, which replaces the teacher with another student. We also define a novel concept, stable sample, following which a stabilization constraint is designed for our structure to be trainable. Further, we discuss two variants of our method, which produce even higher performance. Extensive experiments show that our method improves the classification performance significantly on several main SSL benchmarks. Specifically, it reduces the error rate of the 13-layer CNN from 16.84% to 12.39% on CIFAR-10 with 1k labels and from 34.10% to 31.56% on CIFAR-100 with 10k labels. In addition, our method also achieves a clear improvement in domain adaptation.

Recent years have witnessed a significant increase in the online sharing of medical information, with videos representing a large fraction of such online sources. Previous studies have however shown that more than half of the health-related videos on platforms such as YouTube contain misleading information and biases. Hence, it is crucial to build computational tools that can help evaluate the quality of these videos so that users can obtain accurate information to help inform their decisions. In this study, we focus on the automatic detection of misinformation in YouTube videos. We select prostate cancer videos as our entry point to tackle this problem. The contribution of this paper is twofold. First, we introduce a new dataset consisting of 250 videos related to prostate cancer manually annotated for misinformation. Second, we explore the use of linguistic, acoustic, and user engagement features for the development of classification models to identify misinformation. Using a series of ablation experiments, we show that we can build automatic models with accuracies of up to 74%, corresponding to a 76.5% precision and 73.2% recall for misinformative instances.

Abstract--This paper studies the problem of cross-network node classification to overcome the insufficiency of labeled data in a single network. It aims to leverage the label information in a partially labeled source network to assist node classification in a completely unlabeled or partially labeled target network. Existing methods for single network learning cannot solve this problem due to the domain shift across networks. Some multi-network learning methods heavily rely on the existence of cross-network connections, thus are inapplicable for this problem. T o tackle this problem, we propose a novel network transfer learning framework AdaGCN by leveraging the techniques of adversarial domain adaptation and graph convolution. It consists of two components: a semi-supervised learning component and an adversarial domain adaptation component. The former aims to learn class discriminative node representations with given label information of the source and target networks, while the latter contributes to mitigating the distribution divergence between the source and target domains to facilitate knowledge transfer. Extensive empirical evaluations on real-world datasets show that AdaGCN can successfully transfer class information with a low label rate on the source network and a substantial divergence between the source and target domains. Codes will be released upon acceptance. It is an important building block of numerous real-world applications, such as product recommendation in e-commerce websites, advertisement distribution in social networks, and protein function identification for disease diagnosis. Many research efforts have been made to develop reliable and efficient methods for node classification in networked data. In the era of big data, massive amount of raw data in information networks is produced everyday . However, labeled data is significantly expensive and slow to acquire due to the high cost and long time of human annotations, making it difficult to train a well-generalized classifier [2]. Moreover, in some newly-formed networks such as a protein-protein interaction network constructed by some researchers, there may be no labels at all. Hence, it would be impossible to classify the nodes with only the information of this network. T o tackle these issues, a promising approach is to utilize class information from other similar or related networks to assist in classification, i.e., transfer learning on networked data [3], [4].