In this report we investigate fundamental requirements for the application of classifier patching on neural networks. Neural network patching is an approach for adapting neural network models to handle concept drift in nonstationary environments. Instead of creating or updating the existing network to accommodate concept drift, neural network patching leverages the inner layers of the network as well as its output to learn a patch that enhances the classification and corrects errors caused by the drift. It learns (i) a predictor that estimates whether the original network will misclassify an instance, and (ii) a patching network that fixes the misclassification. Neural network patching is based on the idea that the original network can still classify a majority of instances well, and that the inner feature representations encoded in the deep network aid the classifier to cope with unseen or changed inputs. In order to apply this kind of patching, we evaluate different engagement layers and patch architectures in this report, and find a set of generally applicable heuristics, which aid in parametrizing the patching procedure.
Classifiers in machine learning are often brittle when deployed. Particularly concerning are models with inconsistent performance on specific subgroups of a class, e.g., exhibiting disparities in skin cancer classification in the presence or absence of a spurious bandage. To mitigate these performance differences, we introduce model patching, a two-stage framework for improving robustness that encourages the model to be invariant to subgroup differences, and focus on class information shared by subgroups. Model patching first models subgroup features within a class and learns semantic transfor…
Two main obstacles preventing the widespread adoption of variational Bayesian neural networks are the high parameter overhead that makes them infeasible on large networks, and the difficulty of implementation, which can be thought of as "programming overhead." MC dropout [Gal and Ghahramani, 2016] is popular because it sidesteps these obstacles. Nevertheless, dropout is often harmful to model performance when used in networks with batch normalization layers [Li et al., 2018], which are an indispensable part of modern neural networks. We construct a general variational family for ensemble-based…
Analysis and manipulation of trained neural networks is a challenging and important problem. We propose a symbolic representation for piecewise-linear neural networks and discuss its efficient computation. With this representation, one can translate the problem of analyzing a complex neural network into that of analyzing a finite set of affine functions. We demonstrate the use of this representation for three applications. First, we apply the symbolic representation to computing weakest preconditions on network inputs, which we use to exactly visualize the advisories made by a network meant to…
Rutgers University（罗格斯大学）；MIT-IBM Watson AI Lab（MIT-IBM沃森人工智能实验室）；IBM Research（IBM研究院）
Graph neural networks (GNNs) are a class of effective deep learning models for node classification tasks; yet their predictive capability may be severely compromised under adversarially designed unnoticeable perturbations to the graph structure and/or node data. Most of the current work on graph adversarial attacks aims at lowering the overall prediction accuracy, but we argue that the resulting abnormal model performance may catch attention easily and invite quick counterattack. Moreover, attacks through modification of existing graph data may be hard to conduct if good security protocols are…
Tencent Inc.（腾讯公司）；Jinan University（暨南大学）；Alibaba Group（阿里巴巴集团）；The Hong Kong Polytechnic University（香港理工大学）
Cold start is an essential and persistent problem in recommender systems. State-of-the-art solutions rely on training hybrid models for both cold-start and existing users/items, based on the auxiliary information. Such a hybrid model would compromise the performance of existing users/items, which might make these solutions not applicable in real-worlds recommender systems where the experience of existing users/items must be guaranteed. Meanwhile, graph neural networks (GNNs) have been demonstrated to perform effectively warm (non-cold-start) recommendations. However, they have never been appli…
