In this paper entropy based methods are compared and used to measure structural diversity of an ensemble of 21 classifiers. This measure is mostly applied in ecology, whereby species counts are used as a measure of diversity. The measures used were Shannon entropy, Simpsons and the Berger Parker diversity indexes. As the diversity indexes increased so did the accuracy of the ensemble. An ensemble dominated by classifiers with the same structure produced poor accuracy. Uncertainty rule from information theory was also used to further define diversity. Genetic algorithms were used to find the optimal ensemble by using the diversity indices as the cost function. The method of voting was used to aggregate the decisions.
Korea Advanced Institute of Science and Technology（韩国科学技术院）
In this paper, sample-aware policy entropy regularization is proposed to enhance the conventional policy entropy regularization for better exploration. Exploiting the sample distribution obtainable from the replay buffer, the proposed sample-aware entropy regularization maximizes the entropy of the weighted sum of the policy action distribution and the sample action distribution from the replay buffer for sample-efficient exploration. A practical algorithm named diversity actor-critic (DAC) is developed by applying policy iteration to the objective function with the proposed sample-aware entro…
Nanjing University of Posts and Telecommunications（南京邮电大学）；Southeast University（东南大学）；Temple University（天普大学）
Entropy minimization has been widely used in unsupervised domain adaptation (UDA). However, existing works reveal that entropy minimization only may result into collapsed trivial solutions. In this paper, we propose to avoid trivial solutions by further introducing diversity maximization. In order to achieve the possible minimum target risk for UDA, we show that diversity maximization should be elaborately balanced with entropy minimization, the degree of which can be finely controlled with the use of deep embedded validation in an unsupervised manner. The proposed minimal-entropy diversity ma…
SPARKE: Scalable Prompt-Aware Diversity and Novelty Guidance in Diffusion Models via RKE Score
Department of Computer Science and Engineering, The Chinese University of Hong Kong（计算机科学与工程系，香港中文大学）；Department of Information Engineering, The Chinese University of Hong Kong（信息工程系，香港中文大学）
This paper aims to showcase the measure of structural diversity of an ensemble of 9 classifiers and then map a relationship between this structural diversity and accuracy. The structural diversity was induced by having different architectures or structures of the classifiers The Genetical Algorithms (GA) were used to derive the relationship between diversity and the classification accuracy by evolving the classifiers and then picking 9 classifiers out on an ensemble of 60 classifiers. It was found that as the ensemble became diverse the accuracy improved. However at a certain diversity measure…
Sequence-to-Sequence (Seq2Seq) models have achieved encouraging performance on the dialogue response generation task. However, existing Seq2Seq-based response generation methods suffer from a low-diversity problem: they frequently generate generic responses, which make the conversation less interesting. In this paper, we address the low-diversity problem by investigating its connection with model over-confidence reflected in predicted distributions. Specifically, we first analyze the influence of the commonly used Cross-Entropy (CE) loss function, and find that the CE loss function prefers hig…
Cross Entropy (CE) has an important role in machine learning and, in particular, in neural networks. It is commonly used in neural networks as the cost between the known distribution of the label and the Softmax/Sigmoid output. In this paper we present a new cost function called the Amended Cross Entropy (ACE). Its novelty lies in its affording the capability to train multiple classifiers while explicitly controlling the diversity between them. We derived the new cost by mathematical analysis and "reverse engineering" of the way we wish the gradients to behave, and produced a tailor-made, eleg…
This article reviews and evaluates models of network evolution based on the notion of structural diversity. We show that diversity is an underlying theme of three principles of network evolution: the preferential attachment model, connectivity and link prediction. We show that in all three cases, a dominant trend towards shrinking diversity is apparent, both theoretically and empirically. In previous work, many kinds of different data have been modeled as networks: social structure, navigational structure, transport infrastructure, communication, etc. Almost all these types of networks are not…
Beihang University（北京航空航天大学）；Macquarie University（麦考瑞大学）；Didi Chuxing（滴滴出行）；University of Illinois Chicago（伊利诺伊大学芝加哥分校）
Graph Neural Networks (GNNs) are de facto solutions to structural data learning. However, it is susceptible to low-quality and unreliable structure, which has been a norm rather than an exception in real-world graphs. Existing graph structure learning (GSL) frameworks still lack robustness and interpretability. This paper proposes a general GSL framework, SE-GSL, through structural entropy and the graph hierarchy abstracted in the encoding tree. Particularly, we exploit the one-dimensional structural entropy to maximize embedded information content when auxiliary neighbourhood attributes are f…
Influence-Directed Distillation: Solving the Diversity Bottleneck in Sampled-Token On-Policy Distillation
University of North Carolina at Chapel Hill（北卡罗来纳大学教堂山分校）；University of Science and Technology of China（中国科学技术大学）；Shanghai University of Finance and Economics（上海财经大学）
As a training and analysis strategy for convolutional neural networks (CNNs), we slice images into tiled segments and use, for training and prediction, segments that both satisfy a criterion of information diversity and contain sufficient content to support classification. In particular, we utilize image entropy as the diversity criterion. This ensures that each tile carries as much information diversity as the original image, and for many applications serves as an indicator of usefulness in classification. To make predictions, a probability aggregation framework is applied to probabilities as…
Diversity Curves for Graph Representation Learning
Helmholtz Munich（海德堡-慕尼黑研究所）；Technical University of Munich（慕尼黑技术大学）；Université de Fribourg（弗里堡大学）；Université de Montréal（蒙特利尔大学）；Mila - Quebec AI Institute（魁北克人工智能研究所）
DSDR: Dual-Scale Diversity Regularization for Exploration in LLM Reasoning
The Ohio State University, USA（俄亥俄州立大学）；Case Western Reserve University, USA（凯斯西储大学）；The Chinese University of Hong Kong, Hong Kong（香港中文大学）；Macquarie University, Australia（麦考瑞大学）；University of Michigan, USA（密歇根大学）；The University of Hong Kong, Hong Kong（香港大学）；University College London, UK（伦敦大学学院）
Deep Out-of-Distribution Uncertainty Quantification via Weight Entropy Maximization
Manufacture Française des pneumatiques Michelin（法国米其林轮胎制造公司）；Centre Borelli（博雷利中心）；Université Paris-Saclay（巴黎萨克雷大学）；CNRS（法国国家科学研究中心）；ENS Paris-Saclay（巴黎萨克雷高等师范学校）
Machine learning on graph-structured data has attracted high research interest due to the emergence of Graph Neural Networks (GNNs). Most of the proposed GNNs are based on the node homophily, i.e neighboring nodes share similar characteristics. However, in many complex networks, nodes that lie to distant parts of the graph share structurally equivalent characteristics and exhibit similar roles (e.g chemical properties of distant atoms in a molecule, type of social network users). A growing literature proposed representations that identify structurally equivalent nodes. However, most of the exi…
In complex networks, nodes that share similar structural characteristics often exhibit similar roles (e.g type of users in a social network or the hierarchical position of employees in a company). In order to leverage this relationship, a growing literature proposed latent representations that identify structurally equivalent nodes. However, most of the existing methods require high time and space complexity. In this paper, we propose VNEstruct, a simple approach for generating low-dimensional structural node embeddings, that is both time efficient and robust to perturbations of the graph stru…
Following the success of convolution on non-Euclidean space, the corresponding pooling approaches have also been validated on various tasks regarding graphs. However, because of the fixed compression quota and stepwise pooling design, these hierarchical pooling methods still suffer from local structure damage and suboptimal problem. In this work, inspired by structural entropy, we propose a hierarchical pooling approach, SEP, to tackle the two issues. Specifically, without assigning the layer-specific compression quota, a global optimization algorithm is designed to generate the cluster assign…
University of Illinois at Urbana-Champaign（伊利诺伊大学厄巴纳-香槟分校）
Colorizing a given gray-level image is an important task in the media and advertising industry. Due to the ambiguity inherent to colorization (many shades are often plausible), recent approaches started to explicitly model diversity. However, one of the most obvious artifacts, structural inconsistency, is rarely considered by existing methods which predict chrominance independently for every pixel. To address this issue, we develop a conditional random field based variational auto-encoder formulation which is able to achieve diversity while taking into account structural consistency. Moreover,…
Institut Charles Delaunay (CNRS)（夏尔·德拉吕研究所（法国国家科学研究中心））；Université de technologie de Troyes（特鲁瓦工程技术大学）
In signal analysis and synthesis, linear approximation theory considers a linear decomposition of any given signal in a set of atoms, collected into a so-called dictionary. Relevant sparse representations are obtained by relaxing the orthogonality condition of the atoms, yielding overcomplete dictionaries with an extended number of atoms. More generally than the linear decomposition, overcomplete kernel dictionaries provide an elegant nonlinear extension by defining the atoms through a mapping kernel function (e.g., the gaussian kernel). Models based on such kernel dictionaries are used in neu…
