The competition "Predicting Generalization in Deep Learning (PGDL)" aims to provide a platform for rigorous study of generalization of deep learning models and offer insight into the progress of understanding and explaining these models. This report presents the solution that was submitted by the user \emph{smeznar} which achieved the eight place in the competition. In the proposed approach, we create simple metrics and find their best combination with automatic testing on the provided dataset, exploring how combinations of various properties of the input neural network architectures can be used for the prediction of their generalization.
University of California, San Francisco（加州大学旧金山分校）；University of California, Santa Barbara（加州大学圣巴巴拉分校）
We study generalization in deep learning by appealing to complexity measures originally developed in approximation and information theory. While these concepts are challenged by the high-dimensional and data-defined nature of deep learning, we show that simple vector quantization approaches such as PCA, GMMs, and SVMs capture their spirit when applied layer-wise to deep extracted features giving rise to relatively inexpensive complexity measures that correlate well with generalization performance. We discuss our results in 2020 NeurIPS PGDL challenge.
U.S. Geological Survey（美国地质调查局）；University of Pittsburgh（匹兹堡大学）；University of Minnesota（明尼苏达大学）
Most environmental data come from a minority of well-monitored sites. An ongoing challenge in the environmental sciences is transferring knowledge from monitored sites to unmonitored sites. Here, we demonstrate a novel transfer learning framework that accurately predicts depth-specific temperature in unmonitored lakes (targets) by borrowing models from well-monitored lakes (sources). This method, Meta Transfer Learning (MTL), builds a meta-learning model to predict transfer performance from candidate source models to targets using lake attributes and candidates' past performance. We constructe…
The field of Deep Learning is rich with empirical evidence of human-like performance on a variety of prediction tasks. However, despite these successes, the recent Predicting Generalization in Deep Learning (PGDL) NeurIPS 2020 competition suggests that there is a need for more robust and efficient measures of network generalization. In this work, we propose a new framework for evaluating the generalization capabilities of trained networks. We use perturbation response (PR) curves that capture the accuracy change of a given network as a function of varying levels of training sample perturbation…
Indian Institute of Technology Madras（印度理工学院马德拉斯分校）
Recent papers have shown that sufficiently overparameterized neural networks can perfectly fit even random labels. Thus, it is crucial to understand the underlying reason behind the generalization performance of a network on real-world data. In this work, we propose several measures to predict the generalization error of a network given the training data and its parameters. Using one of these measures, based on noise resilience of the network, we secured 5th position in the predicting generalization in deep learning (PGDL) competition at NeurIPS 2020.
Learning by integrating multiple heterogeneous data sources is a common requirement in many tasks. Collective Matrix Factorization (CMF) is a technique to learn shared latent representations from arbitrary collections of matrices. It can be used to simultaneously complete one or more matrices, for predicting the unknown entries. Classical CMF methods assume linearity in the interaction of latent factors which can be restrictive and fails to capture complex non-linear interactions. In this paper, we develop the first deep-learning based method, called dCMF, for unsupervised learning of multiple…
In this article we propose a new supervised ensemble learning method called Data Shared Adaptive Bootstrap Aggregated (AdaBag) Lasso for capturing low dimensional useful features for word based sentiment analysis and mining problems. The literature on ensemble methods is very rich in both statistics and machine learning. The algorithm is a substantial upgrade of the Data Shared Lasso uplift algorithm. The most significant conceptual addition to the existing literature lies in the final selection of bag of predictors through a special bootstrap aggregation scheme. We apply the algorithm to one …
Indian Institute of Technology, Madras（马德拉斯印度理工学院）
Deep Neural Networks can generalize despite being significantly overparametrized. Recent research has tried to examine this phenomenon from various view points and to provide bounds on the generalization error or measures predictive of the generalization gap based on these viewpoints, such as norm-based, PAC-Bayes based, and margin-based analysis. In this work, we provide an interpretation of generalization from the perspective of quality of internal representations of deep neural networks, based on neuroscientific theories of how the human visual system creates invariant and untangled object …
We demonstrate a first example for employing deep learning in predicting frame errors for a Collaborative Intelligent Radio Network (CIRN) using a dataset collected during participation in the final scrimmages of the DARPA SC2 challenge. Four scenarios are considered based on randomizing or fixing the strategy for bandwidth and channel allocation, and either training and testing with different links or using a pilot phase for each link to train the deep neural network. We also investigate the effect of latency constraints, and uncover interesting characteristics of the predictor over different…
Matrix factorization has found incredible success and widespread application as a collaborative filtering based approach to recommendations. Unfortunately, incorporating additional sources of evidence, especially ones that are incomplete and noisy, is quite difficult to achieve in such models, however, is often crucial for obtaining further gains in accuracy. For example, additional information about businesses from reviews, categories, and attributes should be leveraged for predicting user preferences, even though this information is often inaccurate and partially-observed. Instead of creatin…
IMT Atlantique（IMT大西洋高等矿业电信学院）；Université Fédérale de Toulouse（图卢兹联邦大学）
Measuring the generalization performance of a Deep Neural Network (DNN) without relying on a validation set is a difficult task. In this work, we propose exploiting Latent Geometry Graphs (LGGs) to represent the latent spaces of trained DNN architectures. Such graphs are obtained by connecting samples that yield similar latent representations at a given layer of the considered DNN. We then obtain a generalization score by looking at how strongly connected are samples of distinct classes in LGGs. This score allowed us to rank 3rd on the NeurIPS 2020 Predicting Generalization in Deep Learning (P…
Cisco Systems（思科系统）；CHRIST (Deemed to be University)（基督大学）；IIIT Delhi（德里印度理工学院）
This paper describes our proposed system for the AAAI-CAD21 shared task: Predicting Emphasis in Presentation Slides. In this specific task, given the contents of a slide we are asked to predict the degree of emphasis to be laid on each word in the slide. We propose 2 approaches to this problem including a BiLSTM-ELMo approach and a transformers based approach based on RoBERTa and XLNet architectures. We achieve a score of 0.518 on the evaluation leaderboard which ranks us 3rd and 0.543 on the post-evaluation leaderboard which ranks us 1st at the time of writing the paper.
Charles University（查理大学）；Faculty Of Mathematics and Physics（数学与物理学院）
Eye-Tracking data is a very useful source of information to study cognition and especially language comprehension in humans. In this paper, we describe our systems for the CMCL 2022 shared task on predicting eye-tracking information. We describe our experiments with pretrained models like BERT and XLM and the different ways in which we used those representations to predict four eye-tracking features. Along with analysing the effect of using two different kinds of pretrained multilingual language models and different ways of pooling the tokenlevel representations, we also explore how contextual…
Is network fragmentation a useful complexity measure?
Faculty of Engineering, North-West University（西北大学工程学院）；Centre for Artificial Intelligence Research（人工智能研究中心）；South African National Space Agency（南非国家太空局）；National Institute for Theoretical and Computational Sciences（理论与计算科学国家研究所）
University of Goettingen（哥廷根大学）；Qatar Computing Research Institute, HBKU（哈马德·本·哈利法大学卡塔尔计算研究所）；University Medical Center Goettingen（哥廷根大学医学中心）
Control strategies for active prostheses or orthoses use sensor inputs to recognize the user's locomotive intention and generate corresponding control commands for producing the desired locomotion. In this paper, we propose a learning-based shared model for predicting ankle-joint motion for different locomotion modes like level-ground walking, stair ascent, stair descent, slope ascent, and slope descent without the need to classify between them. Features extracted from hip and knee joint angular motion are used to continuously predict the ankle angles and moments using a Feed-Forward Neural Ne…
Institute of Information Science and Technologies, Italian National Research Council（意大利国家研究委员会信息科学与技术研究所）；School of Business, Maynooth University（梅努斯大学商学院）
The global electric car sales in 2020 continued to exceed the expectations climbing to over 3 millions and reaching a market share of over 4%. However, uncertainty of generation caused by higher penetration of renewable energies and the advent of Electrical Vehicles (EV) with their additional electricity demand could cause strains to the power system, both at distribution and transmission levels. Demand response aggregation and load control will enable greater grid stability and greater penetration of renewable energies into the grid. The present work fits this context in supporting charging o…
Beihang University（北京航空航天大学）；University of Tennessee（田纳西大学）；Rutgers University（罗格斯大学）
Given a sequence of sets, where each set contains an arbitrary number of elements, the problem of temporal sets prediction aims to predict the elements in the subsequent set. In practice, temporal sets prediction is much more complex than predictive modelling of temporal events and time series, and is still an open problem. Many possible existing methods, if adapted for the problem of temporal sets prediction, usually follow a two-step strategy by first projecting temporal sets into latent representations and then learning a predictive model with the latent representations. The two-step approa…
Predicting Alignment Generalization with Value Representations
Carnegie Mellon University（卡内基梅隆大学）；Mila - Quebec AI Institute（米拉-魁北克人工智能研究所）；McGill University（麦吉尔大学）；ETH Zurich（苏黎世联邦理工学院）；ETH AI Center（苏黎世联邦理工学院人工智能中心）；University of British Columbia（不列颠哥伦比亚大学）；Vector Institute（矢量研究所）
