Adaptive Entities Research Articles

Aspect-Aware Graph Attention Network for Heterogeneous Information Networks.

Graph Convolutional Networks (GCNs) derive inspiration from recent advances in computer vision, by stacking layers of first-order filters followed by a nonlinear activation function to learn entity or graph embeddings. Although GCNs have been shown to boost the performance of many network analysis tasks, they still face tremendous challenges in learning from Heterogeneous Information Networks (HINs), where relations play a decisive role in knowledge reasoning. What's more, there are multiaspect representations of entities in HINs, and a filter learned in one aspect do not necessarily apply to another. We address these challenges by proposing the Aspect-Aware Graph Attention Network (AGAT), a model that extends GCNs with alternative learnable filters to incorporate entity and relational information. Instead of focusing on learning the general entity embeddings, AGAT learns the adaptive entity embeddings based on prediction scenario. Experiments of link prediction and semi-supervised classification verify the effectiveness of our algorithm.

NURTURING INNOVATION AND CREATIVITY FOR BUSINESS SUCCESS.

This paper examines the role of Creativity and innovations are indispensable elements in the modern business environment, serving as catalysts for growth, adaptation, and competitive advantage. This abstract delves into the dynamic relationship between creativity and innovation within the business context, highlighting their pivotal roles in shaping organizational success. Creativity, characterized by the generation of novel and valuable ideas, lays the foundation for innovation—the process by which these ideas are translated into tangible and marketable solutions. Businesses that foster a culture of creativity empower employees to think beyond conventional boundaries, fostering an environment where diverse perspectives converge to ignite innovation. This abstract explores the interconnected nature of these concepts, emphasizing the need for organizations to embrace risk-taking, encourage cross-disciplinary collaboration, and prioritize a customer-centric approach. By understanding and leveraging the synergies between creativity and innovation, businesses can navigate the challenges of a rapidly evolving landscape and position themselves as trailblazers in their respective industries. This exploration underscores the transformative power of creativity and innovation, portraying them not merely as business strategies but as essential drivers of sustained success and relevance in an ever-changing world. By setting and achieving creativity and innovation objectives, businesses can position themselves as dynamic and adaptive entities, capable of navigating change, staying ahead of the competition, and delivering sustained value to customers and stakeholders

Data Warehousing Revolution: AI-driven Solutions

The contemporary landscape of data warehousing is undergoing a revolutionary transformation propelled by the integration of Artificial Intelligence (AI). This paper explores the intersection of AI and data warehousing, unraveling the dynamics that fuel this revolution and examining the profound implications for businesses and data management practices. The traditional paradigm of data warehousing has relied on structured data and predefined schemas, limiting its adaptability to the dynamic nature of modern datasets. The advent of AI injects a new dimension, enabling data warehouses to evolve into intelligent, adaptive entities capable of handling diverse data types, volumes, and velocities. This abstract encapsulates the essence of the research, delving into key themes that define the AI-driven revolution in data warehousing. The paper begins by surveying the historical trajectory of data warehousing, highlighting the challenges posed by the increasing complexity and heterogeneity of contemporary data sources. As businesses grapple with unstructured data, streaming data, and the need for real-time insights, the limitations of traditional data warehousing architectures become apparent. The introduction of AI-driven solutions revolutionizes data warehousing in several dimensions. Machine learning algorithms are harnessed for automating data integration, cleansing, and transformation processes, mitigating the manual labor associated with traditional ETL (Extract, Transform, Load) methods. Deep learning techniques, such as neural networks, unlock the potential to uncover complex patterns within massive datasets, enhancing predictive analytics and decision support capabilities. Moreover, the abstract explores the role of AI in enabling self-optimizing data warehouses. Adaptive query optimization, automated indexing, and real-time performance tuning emerge as pivotal components, ensuring that data warehouses evolve in response to changing workloads and user patterns. Ethical considerations and responsible AI practices within the context of data warehousing are also addressed. The abstract concludes by underlining the transformative impact of AI-driven solutions on the efficiency, agility, and strategic value of data warehousing, offering a glimpse into the future where intelligent data warehouses play a central role in shaping data-driven enterprises.

Archaeology, rapid climate changes in the Holocene, and adaptive strategies

The article presents the concepts of repeating cycles of rapid climate variability in the Holocene, including rapid cooling cycles, cold events, ice-rafting events, and rapid climate change recorded in palaeoclimate archives. It also discusses the concepts of adaptation strategies embedded in the catastrophic scenarios of collapse on the one hand, and panarchy, resilience, and adaptation cycle on the other, i.e. the processes of transforming social hierarchical structures into dynamic, adaptive entities. In the rapid climate change series we focus on the 9.2 ka and 8.2 ka climate events associated with the Neolithisation process and the transition to farming. The 5.9 IRD event and/or period of rapid climate change from 6000–5200 cal yr BP are associated with the cultural, economic, and demographic collapse of the Early Neolithic Linear Pottery culture in central and western Europe. We also discuss the triad of recent weakening of North Atlantic ocean circulation, decreased solar activity, and the hypothesised transition to a cold period, the well-known historical scenario associated with the transition to Little Ice Age between 1450 and 1850.

METABODY AS PERFORMANCE IN DON DELILLO’S THE BODY ARTIST, 2001

The article delves into Don DeLillo’s novel “The Body Artist” (2001), presenting it as a pioneering work that introduces a novel perspective on the concept of the body in literature. Central to the analysis is the notion of the meta-body, characterized by its dynamic and flexible nature. The study posits that the portrayal of the body undergoes a transformation, evolving from a static entity in the reader’s consciousness to a dynamic force responsive to shifts in perception and newly acquired information. The meta-body is portrayed as a fresh phenomenon, its understanding facilitated through the rejection of biases and the evaluation of the likelihood of sensations in specific contexts.A pivotal aspect of the exploration is the meta-body’s emancipation from traditional stereotypes and assumptions. It is underscored that the meta-body increasingly relies on the reader’s capacity to assess the probability of sensations in diverse circumstances, challenging preconceived notions and enriching the literary portrayal of the body as an adaptive entity within contemporary discourse.The article further scrutinizes the concept of the meta-body from various analytical perspectives within the novel. Firstly, it examines the meta-body through the collapse of distance, elucidating how spatiotemporal experiences are altered. The second perspective investigates the meta-body through the lens of material artifacts, encompassing mechanical devices such as dictaphones, radios, and webcams. Additionally, the communication-dialogical nature of family relationships is explored, emphasizing the interplay between silence and sound, verbalized and unspoken dialogues among members of a marital couple.Noteworthy is the analysis of the meta-body through the perspective of bodily performance.In summary, the article positions “The Body Artist” as a literary milestone that introduces the concept of the meta-body, portraying the body as a dynamic and adaptive entity. It goes beyond conventional literary portrayals, encouraging readers to reassess their preconceptions and engage with the body in diverse contexts, offering a nuanced understanding of its multifaceted nature within contemporary literature.

THE SCIENTIFIC BASIS, SOME RESULTS, AND PERSPECTIVES OF MODELING EVOLUTIONARILY CONDITIONED NOOGENESIS OF ARTIFICIAL CREATURES IN VIRTUAL BIOCENOSES

This research aimed to gain a profound understanding of virtual biocenoses intricate digital ecosystems, with the goal of elucidating and replicating the emergence and evolution of intelligence in artificial creatures – referred to as noogenesis. A comprehensive analysis of existing studies within virtual biocenoses was undertaken to glean valuable insights into the complexities of modeling dynamic ecosystems where artificial agents engaged in intricate interactions. The pivotal role of neural networks in shaping the adaptive behaviors of artificial creatures within these environments was underscored. A meticulous investigation into neural networks' evolution methodologies revealed the evolution of their architecture complexity over time, culminating in the facilitation of flexible and intelligent behaviors. However, a lack of study existed in the domain of nurturing evolutionary-based communication and cooperation capabilities within virtual biocenoses. In response to this gap, a model was introduced and substantiated through simulation experiments. The simulation results vividly illustrated the model's remarkable capacity to engender adaptive creatures endowed with the capability to efficiently respond to dynamic environmental changes. These adaptive entities displayed efficient optimization of energy consumption and resource acquisition. Moreover, they manifested both intellectual and physical transformations attributed to the evolution and encoding principles inspired by the NeuroEvolution of Augmented Topologies. Significantly, it became apparent that the evolutionary processes intrinsic to the model were inextricably linked to the environment itself, thus harmonizing seamlessly with the overarching goal of this research. Future research directions in this field were outlined. These pathways provided a foundation for further exploration into the evolution of artificial creatures in virtual biocenoses and the emergence of advanced communication and cooperation capabilities. These advancements hold the potential to move artificial life and artificial intelligence to new levels of understanding and capability.

Rigorous engineering of collective adaptive systems – 2nd special section

An adaptive system is able to adapt at runtime to dynamically changing environments and to new requirements. Adaptive systems can be single adaptive entities or collective ones that consist of several collaborating entities. Rigorous engineering requires appropriate methods and tools that help guaranteeing that an adaptive system lives up to its intended purpose. This paper introduces the special section on “Rigorous Engineering of Collective Adaptive Systems.” It presents the 11 contributions of the section categorizing them into five distinct research lines: correctness by design and synthesis, computing with bio-inspired communication, new system models, machine learning, and programming and analyzing ensembles.

A neighborhood-aware graph self-attention mechanism-based pre-training model for Knowledge Graph Reasoning

Knowledge Graph Reasoning (KGR) is an effective method to ameliorate incompleteness and sparsity problems, which infers new knowledge based on existing knowledge. The Graph Neural Network (GNN)-based approaches can obtain advanced effectiveness. However, it still suffers from some problems such as obtaining insufficient graph features, introducing noises, ignoring path connectivity, and acquiring incomplete neighborhood information. This paper proposes a neighborhood-aware (NA) graph self-attention mechanism-based pre-training model for KGR, namely NA-KGR. The proposed model is composed of two phases. The first phase is an enhanced graph attention network, which can use the weighted characteristics of its neighbors to represent and encode the entities that are most likely to have a positive effect on reasoning. The second phase is a neighborhood-aware self-attention mechanism, which makes the model more able to obtain information from the neighbor entities for inference by increasing an adaptive entity similarity matrix when calculating the attention score. Moreover, we propose a pre-training pattern based on neighborhood-aware random walk sampling and general subgraph structure sampling to improve NA-KGR's generalization ability. Extensive comparison and ablation experimental results on various benchmarks unambiguously demonstrate that the proposed NA-KGR model can obtain the state-of-the-art results of current GNN-based methods.

Hierarchical graph attention network for temporal knowledge graph reasoning

Temporal knowledge graphs (TKGs) reasoning has attracted increasing research interest in recent years. However, most of the existing TKGs reasoning models aim to learn a dynamic entity representation by binding timestamps information with the entities, neglecting to learn adaptive entity representation that is valuable to the query from relevant historical facts. To this end, we propose a Hierarchical Graph Attention neTwork (HGAT) for the TKGs reasoning task. Specifically, we design a hierarchical neighbor encoder to model the time-oriented and task-oriented roles of the entities. The time-aware mechanism is developed in the first layer to differentiate the contributions of query-relevant historical facts at different timestamps to the query. The designed relation-aware attention is used in the second layer to discern the contributions of the structural neighbors of an entity. Through this hierarchical encoder, our model can absorb valuable knowledge effectively from the relevant historical facts, and thus learn more expressive adaptive entity representation for the query. Finally, we evaluate our model performance on four TKGs datasets and justify its superiority against vaerious state-of-the-art baselines.

CD-GAN: Commonsense-Driven Generative Adversarial Network with Hierarchical Refinement for Text-to-Image Synthesis

Synthesizing vivid images with descriptive texts is gradually emerging as a frontier cross-domain generation task. However, it is obviously inadequate to generate the high-quality image with one single sentence accurately due to the information asymmetry between modalities, which needs external knowledge to balance the process. Moreover, the limited description of the entities in the sentence cannot guarantee the semantic consistency between text and generated image, causing the deficiency of details in foreground and background. Here, we propose a commonsense-driven generative adversarial network to generate photo-realistic images depending on entity-related commonsense knowledge. Commonsense-driven generative adversarial network contains 2 key commonsense-based modules: (a) Entity semantic augment is designed to enhance entity semantics with common sense for abating the information asymmetry, and (b) adaptive entity refinement is used to generate the high-resolution image guided by various commonsense knowledges in multistage for keeping text-image consistency. We demonstrated extensive synthetic cases on the widely used CUB-birds (Caltech-UCSD Birds-200-2011) dataset, where our model achieves competitive results compared to the other state-of-the-art models.

Adaptive Fine-Grained Predicates Learning for Scene Graph Generation.

The performance of current Scene Graph Generation (SGG) models is severely hampered by hard-to-distinguish predicates, e.g., "woman-on/standing on/walking on-beach". As general SGG models tend to predict head predicates and re-balancing strategies prefer tail categories, none of them can appropriately handle hard-to-distinguish predicates. To tackle this issue, inspired by fine-grained image classification, which focuses on differentiating hard-to-distinguish objects, we propose an Adaptive Fine-Grained Predicates Learning (FGPL-A) which aims at differentiating hard-to-distinguish predicates for SGG. First, we introduce an Adaptive Predicate Lattice (PL-A) to figure out hard-to-distinguish predicates, which adaptively explores predicate correlations in keeping with model's dynamic learning pace. Practically, PL-A is initialized from SGG dataset, and gets refined by exploring model's predictions of current mini-batch. Utilizing PL-A, we propose an Adaptive Category Discriminating Loss (CDL-A) and an Adaptive Entity Discriminating Loss (EDL-A), which progressively regularize model's discriminating process with fine-grained supervision concerning model's dynamic learning status, ensuring balanced and efficient learning process. Extensive experimental results show that our proposed model-agnostic strategy significantly boosts performance of benchmark models on VG-SGG and GQA-SGG datasets by up to 175% and 76% on Mean Recall@100, achieving new state-of-the-art performance. Moreover, experiments on Sentence-to-Graph Retrieval and Image Captioning tasks further demonstrate practicability of our method.

Revisiting Embedding-based Entity Alignment: A Robust and Adaptive Method

Entity alignment—the discovery of identical entities across different knowledge graphs (KGs)—is a critical task in data fusion. In this paper, we revisit existing entity alignment methods in practical and challenging scenarios. Our empirical studies show that current work has a low level of robustness to long-tail entities and the lack of entity names or relation triples. We aim to develop a robust and adaptive entity alignment method, and the availability of relations, attributes, or names is not required. Our method consists of an attribute encoder and a relation encoder, representing an entity by aggregating its attributes or relational neighbors using the attention mechanisms that can highlight the useful attributes and relations in end-to-end learning. To let the encoders complement each other and produce a coherent representation space, we propose adaptive embedding fusion via a gating mechanism. We consider four evaluation settings, i.e., the conventional setting with both relation and attribute triples, as well as three challenging settings without attributes, without relations, without both relations and names, respectively. Results show that our method can achieve state-of-the-art performance. Even in the most challenging setting without relations and names, our method can still achieve promising results while existing methods fail.

A Leader-Follower Game Theoretic Approach to Arrest Cascading Failure in Smart Grid

The Smart Grid System (SGS) is a joint network comprising the power and the communication network. In this paper, the underlying intra-and-interdependencies between entities for a given SGS is captured using a dependency model called Modified Implicative Interdependency Model (MIIM) [1]. Given an integer K, the K-contingency list problem gives the list of K-most critical entities, failure of which maximizes the network damage at the current time. The problem being NP complete [2] and owing to the higher running time of the given Integer Linear Programming (ILP) based solution [3], a much faster heuristic solution to generate an event driven self-updating K-contingency list [4] is also given in this paper. Based on the contingency lists obtained from both the solutions, this paper proposes an adaptive entity hardening technique based on a leader-follower game theoretic approach that arrests the cascading failure of entities in the SGS after an initial failure of entities. The validation of the work is done by comparing the contingency lists using both types of solutions, obtained for different K values using the MIIM model on a smart grid of IEEE 14-Bus system with that obtained by simulating the smart grid using a co-simulation system formed by MATPOWER and Java Network Simulator (JNS). The K-contingency list obtained for a smart grid of IEEE 14-Bus system also indicate that the network damage predicted by both the ILP based solution and heuristic solution using MIIM are more realistic compared to that obtained using another dependency model called Implicative Interdependency Model (IIM) [2]. Advantage of using the MIIM based heuristic solution is also shown in this paper when larger SGS of IEEE 118-Bus is considered. Finally, it is shown how the adaptive hardening helps in improving the network performance.

Rigorous engineering of collective adaptive systems: special section

An adaptive system is able to adapt at runtime to dynamically changing environments and to new requirements. Adaptive systems can be single adaptive entities or collective ones that consist of several collaborating entities. Rigorous engineering requires appropriate methods and tools that help guaranteeing that an adaptive system lives up to its intended purpose. This paper introduces the special section on “Rigorous Engineering of Collective Adaptive Systems.” It presents the seven contributions of the section and gives a short overview of the field of rigorously engineering collective adaptive systems by structuring it according to three topics: systematic development, methods and theories for modelling and analysis, and techniques for programming and operating collective adaptive systems.

Atheism and Unbelief: Different Ways to Apply the Evolutionary Framework

Abstract Religion has been intensely studied in the last years inside an evolutionary frame, trying to discern to what extent it contributes to fitness or becomes an adaptive entity in its own. A similar heuristic can be tried regarding the opposite tendency: unbelief and atheism, since these cultural phenomena could help to better adapt to some social settings or become an adaptive socio-cultural niche on its own. The present paper examines some scenarios in which that question makes sense: the tradition of sociology of religion, with its different strands, including recent studies on ‘non-religious’; the cognitive; and the philosophical-theological reflection. The proposed venues show to what extent the evolutionary model might reveal neglected aspects in the study of unbelief, and at the same time its limits or the open questions that such application raise.

Harmony and Resilience: US Democracy Promotion's Basic Premises

AbstractScholarship on US foreign policy regularly claims that US democracy promotion policy is informed by a coherent and harmonious set of basic premises. In this article, I first examine the validity of this claim for US post–Cold War administrations. I find operational in US foreign policy rhetoric three stable premises: that democracy is a universal(ly aspired to) principle, that external democracy promoters are legitimately involving themselves in another country's political affairs, and that this policy endeavor is in the best interest of all involved stakeholders. Following theoretical expectations that culture and cultural aspects are relatively stable and adaptable entities and promote stability in behavior, I then pursue the question of how these premises have fared in an environment particularly challenging to their validity, namely in the case of US democracy promotion in Egypt. I show how, even in light of contradictory evidence, the basic premises remain resilient and function as a discursive structure that enables and constrains policy options.

Unicist Artificial Intelligence to Emulate and Manage Complex Adaptive Systems

Unicist artificial intelligence was researched and developed to manage complex adaptive systems and environments dealing with the root causes and root drivers of their functionality. The first development was an intelligent system named “STRAT”, in 1986, that used a unicist ontological approach with mathematical resolution. Unicist AI allows monitoring adaptive solutions by using the unicist double dialectical logic that emulates the intelligence that underlies nature. The unicist AI allows building monitors to emulate and develop adaptive systems in social, economic and business environments. Unicist AI is based on the ontogenetic maps of the functions of the adaptive systems or environments that are being managed. These ontogenetic maps describe the underlying concepts and fundamentals that define the root causes of the functionality of an adaptive system. They are an emulation of the triadic ontogenetic intelligence of nature and define the structure of the unicist artificial intelligence. Unicist AI emulates the reflection process of human intelligence to apprehend the unified field of complex adaptive entities, using two functions to make this possible: The learning function and the decision function. The ontogenetic maps define the different objects that integrate the adaptive system that allow developing the necessary pilot tests that drive the learning process. The decision making function of a Unicist AI approach to reality, allows making automated decisions that work as conscious decisions based on the recycling though the learning function.

The Narrow and Broad Approaches to Evolutionary Modeling in Economics

:Some models in evolutionary economics rely on direct analogies to genetic evolution, assuming a population of firms with routines, technologies, and strategies on which forces of diversity generation and selection act. This narrow conception can build upon previous findings from evolutionary biology. Broader concepts of evolution allow many or just one adaptive entity, instead of necessarily requiring a population. Thus, an institution or a society can also be understood as an evolutionary entity. Both the narrow and broad approaches have been extensively used in the literature, albeit in different literature traditions. I provide an overview of the conception and development of both approaches to evolutionary modeling, and argue that a generalization is needed to realize the full potential of evolutionary modeling.

Structured Memetic Automation for Online Human-Like Social Behavior Learning

Meme automaton is an adaptive entity that autonomously acquires an increasing level of capability and intelligence through embedded memes evolving independently or via social interactions. This paper begins a study on memetic multiagent system (MeMAS) toward human-like social agents with memetic automaton. We introduce a potentially rich meme-inspired design and operational model, with Darwin’s theory of natural selection and Dawkins’ notion of a meme as the principal driving forces behind interactions among agents, whereby memes form the fundamental building blocks of the agents’ mind universe. To improve the efficiency and scalability of MeMAS, we propose memetic agents with structured memes in this paper. Particularly, we focus on meme selection design where the commonly used elitist strategy is further improved by assimilating the notion of like-attracts-like in the human learning. We conduct experimental study on multiple problem domains and show the performance of the proposed MeMAS on human-like social behavior.

Unicist Theory: The Unicist Paradigm Shift in Sciences that Explains the Dynamics and Evolution of Living Beings and Complex Adaptive Entities.

The paradigm shift of the Unicist Theory is based on the discovery of the ontogenetic intelligence of nature, which is the intelligence that underlies nature. It establishes the basic structures of behavior in nature. The understanding of the unicist paradigm shift is necessary to accept the validity of the resulting applied technologies.Giving Birth to Complexity Sciences:The final goal of the Scientific Research developed at The Unicist Research Institute was find a structural solution for complexity as a universal problem. The Unicist Theory gave birth to Complexity Sciences, providing both their epistemological structure and their integration with Systemic Sciences. This allowed developing a scientific approach to adaptive environments.At an operational level the objective was to deal with complex adaptive systems. These systems might be natural systems or artificial complex adaptive systems like cultures, institutions or information systems.This drove to the development of the Unicist Theory and the shift it generated in sciences. This approach allowed integrating systemic sciences with complexity sciences. Dealing with Living Beings and Complex Adaptive Entities:The Unicist Theory explains the dynamics and evolution of living beings and complex adaptive entities. It substituted empiricism by a pragmatic, structuralist and functionalist approach and replaced knowledge falsification processes with destructive testing processes.The four pillars of the paradigm shift are:1. The unicist theory, which explains the dynamics and evolution of living beings and complex adaptive entities.2. The unicist theory of evolution, which allows developing future research.3. The epistemological structure of complexity sciences, which allows managing the complex aspects of reality.4. The unicist theory of the unified field in nature, which allows managing the unified field of complex adaptive systems.The paradigm shift of the Unicist Theory allowed the emulation of nature in the field of complex adaptive systems and allowed integrating the “know why” with the “know how”.