Graph neural networks (GNNs) build on the success of deep learning models by extending them for use in graph spaces. Transfer learning has proven extremely successful for traditional deep learning problems: resulting in faster training and improved performance. Despite the increasing interest in GNNs and their use cases, there is little research on their transferability. This research demonstrates that transfer learning is effective with GNNs, and describes how source tasks and the choice of GNN impact the ability to learn generalisable knowledge. We perform experiments using real-world and synthetic data within the contexts of node classification and graph classification. To this end, we also provide a general methodology for transfer learning experimentation and present a novel algorithm for generating synthetic graph classification tasks. We compare the performance of GCN, GraphSAGE and GIN across both the synthetic and real-world datasets. Our results demonstrate empirically that GNNs with inductive operations yield statistically significantly improved transfer. Further we show that similarity in community structure between source and target tasks support statistically significant improvements in transfer over and above the use of only the node attributes.
Istanbul Technical University（伊斯坦布尔理工大学）；Faculty of Medicine of Sousse（苏塞医学院）
Graph neural networks (GNNs) have achieved extraordinary enhancements in various areas including the fields medical imaging and network neuroscience where they displayed a high accuracy in diagnosing challenging neurological disorders such as autism. In the face of medical data scarcity and high-privacy, training such data-hungry models remains challenging. Federated learning brings an efficient solution to this issue by allowing to train models on multiple datasets, collected independently by different hospitals, in fully data-preserving manner. Although both state-of-the-art GNNs and federat…
The Self-Loop Paradox: Investigating the Impact of Self-Loops on Graph Neural Networks
Chair of Machine Learning for Complex Networks（复杂网络机器学习讲席组）；Center for Artificial Intelligence and Data Science (CAIDAS)（人工智能与数据科学中心（CAIDAS））；Julius-Maximilians-Universität Würzburg（维尔茨堡朱利叶斯-马克西米利安大学）
TU Dresden（德累斯顿工业大学）；HZDR（亥姆霍兹德累斯顿罗森多夫研究中心）；UKE（汉堡埃彭多夫大学医院）
Functional connectivity plays an essential role in modern neuroscience. The modality sheds light on the brain's functional and structural aspects, including mechanisms behind multiple pathologies. One such pathology is schizophrenia which is often followed by auditory verbal hallucinations. The latter is commonly studied by observing functional connectivity during speech processing. In this work, we have made a step toward an in-depth examination of functional connectivity during a dichotic listening task via deep learning for three groups of people: schizophrenia patients with and without aud…
University of Nebraska（内布拉斯加大学）；University of Nebraska-Lincoln（内布拉斯加大学林肯分校）；Georgia Institute of Technology（佐治亚理工学院）；Ford R&A（福特研究与创新中心）；German University in Cairo（开罗德国大学）
Understanding the per-layer learning dynamics of deep neural networks is of significant interest as it may provide insights into how neural networks learn and the potential for better training regimens. We investigate learning in Deep Convolutional Neural Networks (CNNs) by measuring the relative weight change of layers while training. Several interesting trends emerge in a variety of CNN architectures across various computer vision classification tasks, including the overall increase in relative weight change of later layers as compared to earlier ones.
State of the art reinforcement learning has enabled training agents on tasks of ever increasing complexity. However, the current paradigm tends to favor training agents from scratch on every new task or on collections of tasks with a view towards generalizing to novel task configurations. The former suffers from poor data efficiency while the latter is difficult when test tasks are out-of-distribution. Agents that can effectively transfer their knowledge about the world pose a potential solution to these issues. In this paper, we investigate transfer learning in the context of model-based agen…
One barrier to more widespread adoption of differentially private neural networks is the entailed accuracy loss. To address this issue, the relationship between neural network architectures and model accuracy under differential privacy constraints needs to be better understood. As a first step, we test whether extant knowledge on architecture design also holds in the differentially private setting. Our findings show that it does not; architectures that perform well without differential privacy, do not necessarily do so with differential privacy. Consequently, extant knowledge on neural network…
Neural Networks have been proved to work as decoders in telecommunications, so the ways of making it efficient will be investigated in this thesis. The different parameters to maximize the Neural Network Decoder's efficiency will be investigated. The parameters will be tested for inversion errors only.
How does language model pretraining help transfer learning? We consider a simple ablation technique for determining the impact of each pretrained layer on transfer task performance. This method, partial reinitialization, involves replacing different layers of a pretrained model with random weights, then finetuning the entire model on the transfer task and observing the change in performance. This technique reveals that in BERT, layers with high probing performance on downstream GLUE tasks are neither necessary nor sufficient for high accuracy on those tasks. Furthermore, the benefit of using p…
Understanding neural networks is becoming increasingly important. Over the last few years different types of visualisation and explanation methods have been proposed. However, none of them explicitly considered the behaviour in the presence of noise and distracting elements. In this work, we will show how noise and distracting dimensions can influence the result of an explanation model. This gives a new theoretical insights to aid selection of the most appropriate explanation model within the deep-Taylor decomposition framework.
The transformer-based pre-trained language models have been tremendously successful in most of the conventional NLP tasks. But they often struggle in those tasks where numerical understanding is required. Some possible reasons can be the tokenizers and pre-training objectives which are not specifically designed to learn and preserve numeracy. Here we investigate the ability of text-to-text transfer learning model (T5), which has outperformed its predecessors in the conventional NLP tasks, to learn numeracy. We consider four numeracy tasks: numeration, magnitude order prediction, finding minimu…
Investigating Batch Inference in a Sequential Monte Carlo Framework for Neural Networks
Department of Electronics and Electrical Engineering, University of Liverpool（电子与电气工程系，利物浦大学）；Department of Mechanical and Aerospace Engineering, University of Liverpool（机械与航空航天工程系，利物浦大学）
University of Milan-Bicocca（米兰比可卡大学）；Consiglio Nazionale delle Ricerche (IBFM-CNR)（意大利国家研究委员会（分子生物成像与生理学研究所））
The current understanding of deep neural networks can only partially explain how input structure, network parameters and optimization algorithms jointly contribute to achieve the strong generalization power that is typically observed in many real-world applications. In order to improve the comprehension and interpretability of deep neural networks, we here introduce a novel theoretical framework based on the compositional structure of piecewise linear activation functions. By defining a direct acyclic graph representing the composition of activation patterns through the network layers, it is p…
Multilingual Neural Machine Translation (NMT) models have yielded large empirical success in transfer learning settings. However, these black-box representations are poorly understood, and their mode of transfer remains elusive. In this work, we attempt to understand massively multilingual NMT representations (with 103 languages) using Singular Value Canonical Correlation Analysis (SVCCA), a representation similarity framework that allows us to compare representations across different languages, layers and models. Our analysis validates several empirical results and long-standing intuitions, a…
Dropout Regularization, serving to reduce variance, is nearly ubiquitous in Deep Learning models. We explore the relationship between the dropout rate and model complexity by training 2,000 neural networks configured with random combinations of the dropout rate and the number of hidden units in each dense layer, on each of the three data sets we selected. The generated figures, with binary cross entropy loss and binary accuracy on the z-axis, question the common assumption that adding depth to a dense layer while increasing the dropout rate will certainly enhance performance. We also discover …
University of Maryland, College Park（马里兰大学帕克分校）；Rice University（莱斯大学）；New York University（纽约大学）
We discuss methods for visualizing neural network decision boundaries and decision regions. We use these visualizations to investigate issues related to reproducibility and generalization in neural network training. We observe that changes in model architecture (and its associate inductive bias) cause visible changes in decision boundaries, while multiple runs with the same architecture yield results with strong similarities, especially in the case of wide architectures. We also use decision boundary methods to visualize double descent phenomena. We see that decision boundary reproducibility d…
We measure the effect of small amounts of systematic and random label noise caused by slightly misaligned ground truth labels in a fine grained audio signal labeling task. The task we choose to demonstrate these effects on is also known as framewise polyphonic transcription or note quantized multi-f0 estimation, and transforms a monaural audio signal into a sequence of note indicator labels. It will be shown that even slight misalignments have clearly apparent effects, demonstrating a great sensitivity of convolutional neural networks to label noise. The implications are clear: when using conv…
Aided by advances in neural density estimation, considerable progress has been made in recent years towards a suite of simulation-based inference (SBI) methods capable of performing flexible, black-box, approximate Bayesian inference for stochastic simulation models. While it has been demonstrated that neural SBI methods can provide accurate posterior approximations, the simulation studies establishing these results have considered only well-specified problems -- that is, where the model and the data generating process coincide exactly. However, the behaviour of such algorithms in the case of …
Surface plasmon polaritons (SPPs) confined along metal-dielectric interface have attracted a relevant interest in the area of ultracompact photonic circuits, photovoltaic devices and other applications due to their strong field confinement and enhancement. This paper investigates a novel cascade neural network (NN) architecture to find the dependance of metal thickness on the SPP propagation. Additionally, a novel training procedure for the proposed cascade NN has been developed using an OpenMP-based framework, thus greatly reducing training time. The performed experiments confirm the effectiv…
Beihang University（北京航空航天大学）；Tianjin Medical University（天津医科大学）
In recent years, deep learning has witnessed its blossom in the field of Electrocardiography (ECG) processing, outperforming traditional signal processing methods in various tasks, for example, classification, QRS detection, wave delineation. Although many neural architectures have been proposed in the literature, there is a lack of systematic studies and open-source libraries for ECG deep learning. In this paper, we propose a deep learning framework, named \texttt{torch\_ecg}, which gathers a large number of neural networks, both from literature and novel, for various ECG processing tasks. It…
TensorCell；University of Warsaw（华沙大学）；Jagiellonian University（雅盖隆大学）
We analyze the accuracy of traffic simulations metamodels based on neural networks and gradient boosting models (LightGBM), applied to traffic optimization as fitness functions of genetic algorithms. Our metamodels approximate outcomes of traffic simulations (the total time of waiting on a red signal) taking as an input different traffic signal settings, in order to efficiently find (sub)optimal settings. Their accuracy was proven to be very good on randomly selected test sets, but it turned out that the accuracy may drop in case of settings expected (according to genetic algorithms) to be clo…
The University of Tokyo（东京大学）；IBM Research AI - Tokyo（IBM研究AI - 东京）
In this paper, we study the generalization properties of neural networks under input perturbations and show that minimal training data corruption by a few pixel modifications can cause drastic overfitting. We propose an evolutionary algorithm to search for optimal pixel perturbations using novel cost function inspired from literature in domain adaptation that explicitly maximizes the generalization gap and domain divergence between clean and corrupted images. Our method outperforms previous pixel-based data distribution shift methods on state-of-the-art Convolutional Neural Networks (CNNs) arc…
Most problems in natural language processing can be approximated as inverse problems such as analysis and generation at variety of levels from morphological (e.g., cat+Plural <-> cats) to semantic (e.g., (call + 1 2) <-> "Calculate one plus two."). Although the tasks in both directions are closely related, general approach in the field has been to design separate models specific for each task. However, having one shared model for both tasks, would help the researchers exploit the common knowledge among these problems with reduced time and memory requirements. We investigate a specific class of…
In this paper we explore whether the fundamental tool of experimental psychology, the behavioral experiment, has the power to generate insight not only into humans and animals, but artificial systems too. We apply the techniques of experimental psychology to investigating catastrophic forgetting in neural networks. We present a series of controlled experiments with two-layer ReLU networks, and exploratory results revealing a new understanding of the behavior of catastrophic forgetting. Alongside our empirical findings, we demonstrate an alternative, behavior-first approach to investigating neu…
Investigating the generative dynamics of energy-based neural networks
Department of Mathematics, University of Padova（帕多瓦大学数学系）；Department of General Psychology and Padova Neuroscience Center, University of Padova（帕多瓦大学心理学系和帕多瓦神经科学中心）；IRCCS San Camillo Hospital（IRCCS圣卡米尔医院）
本文系统研究 RBM 的自上而下生成动力学，发现从编码多数字视觉特征的 chimera states 启动采样可提升原型多样性，但能量地形限制了单轨迹内的数字状态转换。
Deep learning models have been the subject of study from various perspectives, for example, their training process, interpretation, generalization error, robustness to adversarial attacks, etc. A trained model is defined by its decision boundaries, and therefore, many of the studies about deep learning models speculate about the decision boundaries, and sometimes make simplifying assumptions about them. So far, finding exact points on the decision boundaries of trained deep models has been considered an intractable problem. Here, we compute exact points on the decision boundaries of these mode…
Investigating layer-selective transfer learning of QAOA parameters for Max-Cut problem
Department of Engineering, University Pompeu Fabra（工程系，庞贝法布拉大学）；Department of Physics and Astronomy, University of Florence（物理与天文学系，佛罗伦萨大学）；QUANTIC, Barcelona Supercomputing Center（QUANTIC，巴塞罗那超级计算中心）；Institute for Cross-Disciplinary Physics and Complex Systems (IFISC) UIB-CSIC（跨学科物理与复杂系统研究所（IFISC） UIB-CSIC）；European Laboratory for Non-Linear Spectroscopy (LENS), University of Florence（非线性光谱欧洲实验室（LENS），佛罗伦萨大学）
Reinforcement learning policies based on deep neural networks are vulnerable to imperceptible adversarial perturbations to their inputs, in much the same way as neural network image classifiers. Recent work has proposed several methods to improve the robustness of deep reinforcement learning agents to adversarial perturbations based on training in the presence of these imperceptible perturbations (i.e. adversarial training). In this paper, we study the effects of adversarial training on the neural policy learned by the agent. In particular, we follow two distinct parallel approaches to investi…
With the growth of adversarial attacks against machine learning models, several concerns have emerged about potential vulnerabilities in designing deep neural network-based intrusion detection systems (IDS). In this paper, we study the resilience of deep learning-based intrusion detection systems against adversarial attacks. We apply the min-max (or saddle-point) approach to train intrusion detection systems against adversarial attack samples in NSW-NB 15 dataset. We have the max approach for generating adversarial samples that achieves maximum loss and attack deep neural networks. On the othe…
University of Oxford（牛津大学）；Google DeepMind（谷歌DeepMind）
This paper aims to explore the effect of prior disambiguation on neural network- based compositional models, with the hope that better semantic representations for text compounds can be produced. We disambiguate the input word vectors before they are fed into a compositional deep net. A series of evaluations shows the positive effect of prior disambiguation for such deep models.
Convolutional Neural Networks (CNN) have been pivotal to the success of many state-of-the-art classification problems, in a wide variety of domains (for e.g. vision, speech, graphs and medical imaging). A commonality within those domains is the presence of hierarchical, spatially agglomerative local-to-global interactions within the data. For two-dimensional images, such interactions may induce an a priori relationship between the pixel data and the underlying spatial ordering of the pixels. For instance in natural images, neighboring pixels are more likely contain similar values than non-neig…
A typical architecture for end-to-end entity linking systems consists of three steps: mention detection, candidate generation and entity disambiguation. In this study we investigate the following questions: (a) Can all those steps be learned jointly with a model for contextualized text-representations, i.e. BERT (Devlin et al., 2019)? (b) How much entity knowledge is already contained in pretrained BERT? (c) Does additional entity knowledge improve BERT's performance in downstream tasks? To this end, we propose an extreme simplification of the entity linking setup that works surprisingly well:…
Investigating Target Class Influence on Neural Network Compressibility for Energy-Autonomous Avian Monitoring
Fraunhofer Institute for Integrated Circuits IIS（弗劳恩霍夫整合电路研究所）；Fachhochschule Erfurt（埃弗特应用技术大学）；Universität Erfurt（埃弗特大学）；Friedrich-Alexander-Universität Erlangen-Nürnberg (FAU)（埃尔朗根-纽伦堡弗赖堡-亚历山大大学）；Center for Artificial Intelligence and Robotics (CAIRO)（人工智能与机器人中心）；Technische Hochschule Würzburg-Schweinfurt（韦尔茨堡-施维茨技术大学）
Uncertainty quantification in neural networks gained a lot of attention in the past years. The most popular approaches, Bayesian neural networks (BNNs), Monte Carlo dropout, and deep ensembles have one thing in common: they are all based on some kind of mixture model. While the BNNs build infinite mixture models and are derived via variational inference, the latter two build finite mixtures trained with the maximum likelihood method. In this work we investigate the effect of training an infinite mixture distribution with the maximum likelihood method instead of variational inference. We find t…
Deconstructing Recurrence, Attention, and Gating: Investigating the transferability of Transformers and Gated Recurrent Neural Networks in forecasting of dynamical systems
School of Engineering and Applied Sciences, Harvard University（哈佛大学工程与应用科学学院）；Institute of Structural Engineering, ETH Zurich（苏黎世联邦理工学院结构工程研究所）
The inner representation of deep neural networks (DNNs) is indecipherable, which makes it difficult to tune DNN models, control their training process, and interpret their outputs. In this paper, we propose a novel approach to investigate the inner representation of DNNs through topological data analysis (TDA). Persistent homology (PH), one of the outstanding methods in TDA, was employed for investigating the complexities of trained DNNs. We constructed clique complexes on trained DNNs and calculated the one-dimensional PH of DNNs. The PH reveals the combinational effects of multiple neurons i…
