Searcharxiv⌕ Search

arXiv subjects

Katarzyna Musial

Publications and source records attributed to Katarzyna Musial.

At least 37 records · Page 2Linked to original sources
arXiv2022

On Taking Advantage of Opportunistic Meta-knowledge to Reduce Configuration Spaces for Automated Machine Learning

The automated machine learning (AutoML) process can require searching through complex configuration spaces of not only machine learning (ML) components and their hyperparameters but also ways of composing them together, i.e. forming ML pipelines. Optimisation efficiency and the model accuracy attainable for a fixed time budget suffer if this pipeline configuration space is excessively large. A key research question is whether it is both possible and practical to preemptively avoid costly evaluations of poorly performing ML pipelines by leveraging their historical performance for various ML tasks, i.e. meta-knowledge. The previous experience comes in the form of classifier/regressor accuracy rankings derived from either (1) a substantial but non-exhaustive number of pipeline evaluations made during historical AutoML runs, i.e. 'opportunistic' meta-knowledge, or (2) comprehensive cross-validated evaluations of classifiers/regressors with default hyperparameters, i.e. 'systematic' meta-knowledge. Numerous experiments with the AutoWeka4MCPS package suggest that (1) opportunistic/systematic meta-knowledge can improve ML outcomes, typically in line with how relevant that meta-knowledge is, and (2) configuration-space culling is optimal when it is neither too conservative nor too radical. However, the utility and impact of meta-knowledge depend critically on numerous facets of its generation and exploitation, warranting extensive analysis; these are often overlooked/underappreciated within AutoML and meta-learning literature. In particular, we observe strong sensitivity to the `challenge' of a dataset, i.e. whether specificity in choosing a predictor leads to significantly better performance. Ultimately, identifying `difficult' datasets, thus defined, is crucial to both generating informative meta-knowledge bases and understanding optimal search-space reduction strategies.

cs.LG↗
arXiv2022

Automated Deep Learning: Neural Architecture Search Is Not the End

Deep learning (DL) has proven to be a highly effective approach for developing models in diverse contexts, including visual perception, speech recognition, and machine translation. However, the end-to-end process for applying DL is not trivial. It requires grappling with problem formulation and context understanding, data engineering, model development, deployment, continuous monitoring and maintenance, and so on. Moreover, each of these steps typically relies heavily on humans, in terms of both knowledge and interactions, which impedes the further advancement and democratization of DL. Consequently, in response to these issues, a new field has emerged over the last few years: automated deep learning (AutoDL). This endeavor seeks to minimize the need for human involvement and is best known for its achievements in neural architecture search (NAS), a topic that has been the focus of several surveys. That stated, NAS is not the be-all and end-all of AutoDL. Accordingly, this review adopts an overarching perspective, examining research efforts into automation across the entirety of an archetypal DL workflow. In so doing, this work also proposes a comprehensive set of ten criteria by which to assess existing work in both individual publications and broader research areas. These criteria are: novelty, solution quality, efficiency, stability, interpretability, reproducibility, engineering quality, scalability, generalizability, and eco-friendliness. Thus, ultimately, this review provides an evaluative overview of AutoDL in the early 2020s, identifying where future opportunities for progress may exist.

cs.LG↗
arXiv2022

AutonoML: Towards an Integrated Framework for Autonomous Machine Learning

Over the last decade, the long-running endeavour to automate high-level processes in machine learning (ML) has risen to mainstream prominence, stimulated by advances in optimisation techniques and their impact on selecting ML models/algorithms. Central to this drive is the appeal of engineering a computational system that both discovers and deploys high-performance solutions to arbitrary ML problems with minimal human interaction. Beyond this, an even loftier goal is the pursuit of autonomy, which describes the capability of the system to independently adjust an ML solution over a lifetime of changing contexts. However, these ambitions are unlikely to be achieved in a robust manner without the broader synthesis of various mechanisms and theoretical frameworks, which, at the present time, remain scattered across numerous research threads. Accordingly, this review seeks to motivate a more expansive perspective on what constitutes an automated/autonomous ML system, alongside consideration of how best to consolidate those elements. In doing so, we survey developments in the following research areas: hyperparameter optimisation, multi-component models, neural architecture search, automated feature engineering, meta-learning, multi-level ensembling, dynamic adaptation, multi-objective evaluation, resource constraints, flexible user involvement, and the principles of generalisation. We also develop a conceptual framework throughout the review, augmented by each topic, to illustrate one possible way of fusing high-level mechanisms into an autonomous ML system. Ultimately, we conclude that the notion of architectural integration deserves more discussion, without which the field of automated ML risks stifling both its technical advantages and general uptake.

cs.LG↗
arXiv2022

Towards Digital Twin Oriented Modelling of Complex Networked Systems and Their Dynamics: A Comprehensive Survey

This paper aims to provide a comprehensive critical overview on how entities and their interactions in Complex Networked Systems (CNS) are modelled across disciplines as they approach their ultimate goal of creating a Digital Twin (DT) that perfectly matches the reality. We propose a new framework to conceptually compare diverse existing modelling paradigms from different perspectives and create unified assessment criteria to assess their respective capabilities of reaching such an ultimate goal. Using the proposed criteria, we also appraise how far the reviewed current state-of-the-art approaches are from the idealised DTs. We also identify and propose potential directions and ways of building a DT-orientated CNS based on the convergence and integration of CNS and DT utilising a variety of cross-disciplinary techniques.

eess.SY↗
arXiv2021

Foundations and modelling of dynamic networks using Dynamic Graph Neural Networks: A survey

Dynamic networks are used in a wide range of fields, including social network analysis, recommender systems, and epidemiology. Representing complex networks as structures changing over time allow network models to leverage not only structural but also temporal patterns. However, as dynamic network literature stems from diverse fields and makes use of inconsistent terminology, it is challenging to navigate. Meanwhile, graph neural networks (GNNs) have gained a lot of attention in recent years for their ability to perform well on a range of network science tasks, such as link prediction and node classification. Despite the popularity of graph neural networks and the proven benefits of dynamic network models, there has been little focus on graph neural networks for dynamic networks. To address the challenges resulting from the fact that this research crosses diverse fields as well as to survey dynamic graph neural networks, this work is split into two main parts. First, to address the ambiguity of the dynamic network terminology we establish a foundation of dynamic networks with consistent, detailed terminology and notation. Second, we present a comprehensive survey of dynamic graph neural network models using the proposed terminology

cs.SI↗
arXiv2021

Exploring Opportunistic Meta-knowledge to Reduce Search Spaces for Automated Machine Learning

Machine learning (ML) pipeline composition and optimisation have been studied to seek multi-stage ML models, i.e. preprocessor-inclusive, that are both valid and well-performing. These processes typically require the design and traversal of complex configuration spaces consisting of not just individual ML components and their hyperparameters, but also higher-level pipeline structures that link these components together. Optimisation efficiency and resulting ML-model accuracy both suffer if this pipeline search space is unwieldy and excessively large; it becomes an appealing notion to avoid costly evaluations of poorly performing ML components ahead of time. Accordingly, this paper investigates whether, based on previous experience, a pool of available classifiers/regressors can be preemptively culled ahead of initiating a pipeline composition/optimisation process for a new ML problem, i.e. dataset. The previous experience comes in the form of classifier/regressor accuracy rankings derived, with loose assumptions, from a substantial but non-exhaustive number of pipeline evaluations; this meta-knowledge is considered 'opportunistic'. Numerous experiments with the AutoWeka4MCPS package, including ones leveraging similarities between datasets via the relative landmarking method, show that, despite its seeming unreliability, opportunistic meta-knowledge can improve ML outcomes. However, results also indicate that the culling of classifiers/regressors should not be too severe either. In effect, it is better to search through a 'top tier' of recommended predictors than to pin hopes onto one previously supreme performer.

cs.LG↗
arXiv2021

NATS-Bench: Benchmarking NAS Algorithms for Architecture Topology and Size

Neural architecture search (NAS) has attracted a lot of attention and has been illustrated to bring tangible benefits in a large number of applications in the past few years. Architecture topology and architecture size have been regarded as two of the most important aspects for the performance of deep learning models and the community has spawned lots of searching algorithms for both aspects of the neural architectures. However, the performance gain from these searching algorithms is achieved under different search spaces and training setups. This makes the overall performance of the algorithms to some extent incomparable and the improvement from a sub-module of the searching model unclear. In this paper, we propose NATS-Bench, a unified benchmark on searching for both topology and size, for (almost) any up-to-date NAS algorithm. NATS-Bench includes the search space of 15,625 neural cell candidates for architecture topology and 32,768 for architecture size on three datasets. We analyze the validity of our benchmark in terms of various criteria and performance comparison of all candidates in the search space. We also show the versatility of NATS-Bench by benchmarking 13 recent state-of-the-art NAS algorithms on it. All logs and diagnostic information trained using the same setup for each candidate are provided. This facilitates a much larger community of researchers to focus on developing better NAS algorithms in a more comparable and computationally cost friendly environment. All codes are publicly available at: https://xuanyidong.com/assets/projects/NATS-Bench.

cs.LG↗
arXiv2020

Measuring Quadrangle Formation in Complex Networks

The classic clustering coefficient and the lately proposed closure coefficient quantify the formation of triangles from two different perspectives, with the focal node at the centre or at the end in an open triad respectively. As many networks are naturally rich in triangles, they become standard metrics to describe and analyse networks. However, the advantages of applying them can be limited in networks, where there are relatively few triangles but which are rich in quadrangles, such as the protein-protein interaction networks, the neural networks and the food webs. This yields for other approaches that would leverage quadrangles in our journey to better understand local structures and their meaning in different types of networks. Here we propose two quadrangle coefficients, i.e., the i-quad coefficient and the o-quad coefficient, to quantify quadrangle formation in networks, and we further extend them to weighted networks. Through experiments on 16 networks from six different domains, we first reveal the density distribution of the two quadrangle coefficients, and then analyse their correlations with node degree. Finally, we demonstrate that at network-level, adding the average i-quad coefficient and the average o-quad coefficient leads to significant improvement in network classification, while at node-level, the i-quad and o-quad coefficients are useful features to improve link prediction.

cs.SI↗
arXiv2020

AutoWeka4MCPS-AVATAR: Accelerating Automated Machine Learning Pipeline Composition and Optimisation

Automated machine learning pipeline (ML) composition and optimisation aim at automating the process of finding the most promising ML pipelines within allocated resources (i.e., time, CPU and memory). Existing methods, such as Bayesian-based and genetic-based optimisation, which are implemented in Auto-Weka, Auto-sklearn and TPOT, evaluate pipelines by executing them. Therefore, the pipeline composition and optimisation of these methods frequently require a tremendous amount of time that prevents them from exploring complex pipelines to find better predictive models. To further explore this research challenge, we have conducted experiments showing that many of the generated pipelines are invalid in the first place, and attempting to execute them is a waste of time and resources. To address this issue, we propose a novel method to evaluate the validity of ML pipelines, without their execution, using a surrogate model (AVATAR). The AVATAR generates a knowledge base by automatically learning the capabilities and effects of ML algorithms on datasets' characteristics. This knowledge base is used for a simplified mapping from an original ML pipeline to a surrogate model which is a Petri net based pipeline. Instead of executing the original ML pipeline to evaluate its validity, the AVATAR evaluates its surrogate model constructed by capabilities and effects of the ML pipeline components and input/output simplified mappings. Evaluating this surrogate model is less resource-intensive than the execution of the original pipeline. As a result, the AVATAR enables the pipeline composition and optimisation methods to evaluate more pipelines by quickly rejecting invalid pipelines. We integrate the AVATAR into the sequential model-based algorithm configuration (SMAC). Our experiments show that when SMAC employs AVATAR, it finds better solutions than on its own.

cs.LG↗
arXiv2020

A Block-based Generative Model for Attributed Networks Embedding

Attributed network embedding has attracted plenty of interest in recent years. It aims to learn task-independent, low-dimensional, and continuous vectors for nodes preserving both topology and attribute information. Most of the existing methods, such as random-walk based methods and GCNs, mainly focus on the local information, i.e., the attributes of the neighbours. Thus, they have been well studied for assortative networks (i.e., networks with communities) but ignored disassortative networks (i.e., networks with multipartite, hubs, and hybrid structures), which are common in the real world. To enable model both assortative and disassortative networks, we propose a block-based generative model for attributed network embedding from a probability perspective. Specifically, the nodes are assigned to several blocks wherein the nodes in the same block share the similar linkage patterns. These patterns can define assortative networks containing communities or disassortative networks with the multipartite, hub, or any hybrid structures. To preserve the attribute information, we assume that each node has a hidden embedding related to its assigned block. We use a neural network to characterize the nonlinearity between node embeddings and node attributes. We perform extensive experiments on real-world and synthetic attributed networks. The results show that our proposed method consistently outperforms state-of-the-art embedding methods for both clustering and classification tasks, especially on disassortative networks.

cs.LG↗
arXiv2020

Multi-level Graph Convolutional Networks for Cross-platform Anchor Link Prediction

Cross-platform account matching plays a significant role in social network analytics, and is beneficial for a wide range of applications. However, existing methods either heavily rely on high-quality user generated content (including user profiles) or suffer from data insufficiency problem if only focusing on network topology, which brings researchers into an insoluble dilemma of model selection. In this paper, to address this problem, we propose a novel framework that considers multi-level graph convolutions on both local network structure and hypergraph structure in a unified manner. The proposed method overcomes data insufficiency problem of existing work and does not necessarily rely on user demographic information. Moreover, to adapt the proposed method to be capable of handling large-scale social networks, we propose a two-phase space reconciliation mechanism to align the embedding spaces in both network partitioning based parallel training and account matching across different social networks. Extensive experiments have been conducted on two large-scale real-life social networks. The experimental results demonstrate that the proposed method outperforms the state-of-the-art models with a big margin.

cs.SI↗
arXiv2020

AVATAR -- Machine Learning Pipeline Evaluation Using Surrogate Model

The evaluation of machine learning (ML) pipelines is essential during automatic ML pipeline composition and optimisation. The previous methods such as Bayesian-based and genetic-based optimisation, which are implemented in Auto-Weka, Auto-sklearn and TPOT, evaluate pipelines by executing them. Therefore, the pipeline composition and optimisation of these methods requires a tremendous amount of time that prevents them from exploring complex pipelines to find better predictive models. To further explore this research challenge, we have conducted experiments showing that many of the generated pipelines are invalid, and it is unnecessary to execute them to find out whether they are good pipelines. To address this issue, we propose a novel method to evaluate the validity of ML pipelines using a surrogate model (AVATAR). The AVATAR enables to accelerate automatic ML pipeline composition and optimisation by quickly ignoring invalid pipelines. Our experiments show that the AVATAR is more efficient in evaluating complex pipelines in comparison with the traditional evaluation approaches requiring their execution.

cs.LG↗
arXiv2020

Interacting spreading processes in multilayer networks

The world of network science is fascinating and filled with complex phenomena that we aspire to understand. One of them is the dynamics of spreading processes over complex networked structures. Building the knowledge-base in the field where we can face more than one spreading process propagating over a network that has more than one layer is a challenging task, as the complexity comes both from the environment in which the spread happens and from characteristics and interplay of spreads' propagation. As this cross-disciplinary field bringing together computer science, network science, biology and physics has rapidly grown over the last decade, there is a need to comprehensively review the current state-of-the-art and offer to the research community a roadmap that helps to organise the future research in this area. Thus, this survey is a first attempt to present the current landscape of the multi-processes spread over multilayer networks and to suggest the potential ways forward.

cs.SI↗
arXiv2019

Simulation and Augmentation of Social Networks for Building Deep Learning Models

A limitation of the Graph Convolutional Networks (GCNs) is that it assumes at a particular $l^{th}$ layer of the neural network model only the $l^{th}$ order neighbourhood nodes of a social network are influential. Furthermore, the GCN has been evaluated on citation and knowledge graphs, but not extensively on friendship-based social graphs. The drawback associated with the dependencies between layers and the order of node neighbourhood for the GCN can be more prevalent for friendship-based graphs. The evaluation of the full potential of the GCN on friendship-based social network requires openly available datasets in larger quantities. However, most available social network datasets are not complete. Also, the majority of the available social network datasets do not contain both the features and ground truth labels. In this work, firstly, we provide a guideline on simulating dynamic social networks, with ground truth labels and features, both coupled with the topology. Secondly, we introduce an open-source Python-based simulation library. We argue that the topology of the network is driven by a set of latent variables, termed as the social DNA (sDNA). We consider the sDNA as labels for the nodes. Finally, by evaluating on our simulated datasets, we propose four new variants of the GCN, mainly to overcome the limitation of dependency between the order of node-neighbourhood and a particular layer of the model. We then evaluate the performance of all the models and our results show that on 27 out of the 30 simulated datasets our proposed GCN variants outperform the original model.

cs.LG↗
arXiv2018

NetSim -- The framework for complex network generator

Networks are everywhere and their many types, including social networks, the Internet, food webs etc., have been studied for the last few decades. However, in real-world networks, it's hard to find examples that can be easily comparable, i.e. have the same density or even number of nodes and edges. We propose a flexible and extensible NetSim framework to understand how properties in different types of networks change with varying number of edges and vertices. Our approach enables to simulate three classical network models (random, small-world and scale-free) with easily adjustable model parameters and network size. To be able to compare different networks, for a single experimental setup we kept the number of edges and vertices fixed across the models. To understand how they change depending on the number of nodes and edges we ran over 30,000 simulations and analysed different network characteristics that cannot be derived analytically. Two of the main findings from the analysis are that the average shortest path does not change with the density of the scale-free network but changes for small-world and random networks; the apparent difference in mean betweenness centrality of the scale-free network compared with random and small-world networks.

cs.SI↗
arXiv2014

Extraction of Multi-layered Social Networks from Activity Data

The data gathered in all kind of web-based systems, which enable users to interact with each other, provides an opportunity to extract social networks that consist of people and relationships between them. The emerging structures are very complex due to the number and type of discovered connections. In webbased systems, the characteristic element of each interaction between users is that there is always an object that serves as a communication medium. This can be e.g. an email sent from one user to another or post at the forum authored by one user and commented by others. Based on these objects and activities that users perform towards them, different kinds of relationships can be identified and extracted. Additional challenge arises from the fact that hierarchies can exist between objects, e.g. a forum consists of one or more groups of topics, and each of them contains topics that finally include posts. In this paper, we propose a new method for creation of multi-layered social network based on the data about users activities towards different types of objects between which the hierarchy exists. Due to the flattening, preprocessing procedure new layers and new relationships in the multi-layered social network can be identified and analysed.

cs.SI↗
arXiv2013

Social Recommendations within the Multimedia Sharing Systems

The social recommender system that supports the creation of new relations between users in the multimedia sharing system is presented in the paper. To generate suggestions the new concept of the multirelational social network was introduced. It covers both direct as well as object-based relationships that reflect social and semantic links between users. The main goal of the new method is to create the personalized suggestions that are continuously adapted to users' needs depending on the personal weights assigned to each layer from the social network. The conducted experiments confirmed the usefulness of the proposed model.

cs.SI↗