Large Language Models (LLMs) have demonstrated strong adaptation to unseen tasks. However, their performance in Information Extraction (IE) under unseen schemas remains limited. Actually, IE requires both general abilities for understanding natural language and semantic concepts, and specialized abilities for aligning extracted information to various human-defined schemas. Training an LLM jointly on multiple schemas, or adapting it to a specific schema, often results in performance drops on datasets with other schemas, especially when conflicts arise between schemas. We refer to this phenomenon as the schema alignment tax in this paper. To alleviate this, we propose a schema-adaptive three-phase framework, Identify–Conceptualize–Align (ICA), which enables LLMs to focus on general abilities such as identifying entity and trigger spans and assigning corresponding concepts to them, while delegating schema-specific alignment to lightweight models. Specifically, in the Identification phase, we train an LLM to identify entity and trigger spans on multiple datasets, with cross-dataset annotation to boost span recall. In the Conceptualization phase, the LLM is used to assign semantic concepts to each span. In the Alignment phase, we train different lightweight alignment models to map these concepts to different human-defined schemas. The first two phases are fully reusable across tasks, so adapting to a new schema requires retraining only the alignment model. We evaluate ICA on entity recognition and event detection on 26 commonly adopted datasets with diverse schemas. Experimental results show that our method not only surpasses state-of-the-art approaches under supervised settings, achieving an average F1 improvement of 1.6%, but also attains a remarkable 11.5% average F1 gain on NER and ED in the 10-shot setting.

Jizhao Zhu, Akang Shi, Zixuan Li, Long Bai, Xiaolong Jin, Jiafeng Guo, Xueqi Cheng. Proceedings of the 63rd Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers). 2025.

Event Relation Extraction (ERE) aims to extract various types of relations between different events within texts. Although Large Language Models (LLMs) have demonstrated impressive capabilities in many natural language processing tasks, existing ERE methods based on LLMs still face three key challenges: (1) Time Inefficiency: The existing pairwise method of combining events and determining their relations is time-consuming for LLMs. (2) Low Coverage: When dealing with numerous events in a document, the limited generation length of fine-tuned LLMs restricts the coverage of their extraction results. (3) Lack of Rationale: Essential rationales concerning the results that could enhance the reasoning ability of the model are overlooked. To address these challenges, we propose LLMERE, an LLM-based approach with rationales for the ERE task. LLMERE transforms ERE into a question-and-answer task that may have multiple answers. By extracting all events related to a specified event at once, LLMERE reduces time complexity from O(n^2) to O(n), compared to the pairwise method. Subsequently, LLMERE enhances the coverage of extraction results by employing a partitioning strategy that highlights only a portion of the events in the document at a time. In addition to the extracted results, LLMERE is also required to generate corresponding rationales/reasons behind them, in terms of event coreference information or transitive chains of event relations. Experimental results on three widely used datasets show that LLMERE achieves significant improvements over baseline methods.

N-ary Knowledge Graphs (NKGs), where a fact can involve more than two entities, have gained increasing attention. Link Prediction in NKGs (LPN) aims to predict missing elements in facts to facilitate the completion of NKGs. Current LPN methods implicitly operate under a closed-world assumption, meaning that the sets of entities and roles are fixed. These methods focus on predicting missing elements within facts composed of entities and roles seen during training. However, in reality, new facts involving unseen entities and roles frequently emerge, requiring completing these facts. Thus, this paper proposes a new task, Inductive Link Prediction in NKGs (ILPN), which aims to predict missing elements in facts involving unseen entities and roles in emerging NKGs. To address this task, we propose a Meta-learning-based N-ary knowledge Inductive Reasoner (MetaNIR), which employs a graph neural network with meta-learning mechanisms to embed unseen entities and roles adaptively. The obtained embeddings are used to predict missing elements in facts involving unseen elements. Since no existing dataset supports this task, three datasets are constructed to evaluate the effectiveness of MetaNIR. Extensive experimental results demonstrate that MetaNIR consistently outperforms representative models across all datasets.

Developing a general-purpose system that can extract events with massive types is a longstanding target in Event Extraction (EE).In doing so, the basic challenge comes from the absence of an efficient and effective annotation framework to construct the corresponding datasets.In this paper, we propose an LLM-based collaborative annotation framework.Through collaboration among multiple LLMs and a subsequent voting process, it refines annotations of triggers from distant supervision and then carries out argument annotation.Finally, we create EEMT, the largest EE dataset to date, featuring over 200,000 samples, 3,465 event types, and 6,297 role types.Evaluation on the human-annotated test set demonstrates that the proposed framework achieves the F1 scores of 90.1% and 85.3% for event detection and argument extraction, strongly validating its effectiveness.Besides, to alleviate the excessively long prompts caused by massive types, we propose an LLM-based Partitioning method for EE called LLM-PEE.It first recalls candidate event types and then splits them into multiple partitions for LLMs to extract.After fine-tuning on the EEMT training set, the distilled LLM-PEE with 7B parameters outperforms state-of-the-art methods by 5.4% and 6.1% in event detection and argument extraction.Besides, it also surpasses mainstream LLMs by 12.9% on the unseen datasets, which strongly demonstrates the event diversity of the EEMT dataset and the generalization capabilities of the LLM-PEE method.

N-ary Knowledge Graphs (NKGs) are a specialized type of knowledge graph designed to efficiently represent complex real-world facts.Unlike traditional knowledge graphs, where a fact typically involves two entities, NKGs can capture n-ary facts containing more than two entities.Link prediction in NKGs aims to predict missing elements within these n-ary facts, which is essential for completing NKGs and improving the performance of downstream applications.This task has recently gained significant attention.In this paper, we present the first comprehensive survey of link prediction in NKGs, providing an overview of the field, systematically categorizing existing methods, and analyzing their performance and application scenarios.We also outline promising directions for future research.

Zixuan Li, Yutao Zeng, Yuxin Zuo, Weicheng Ren, Wenxuan Liu, Miao Su, Yucan Guo, Yantao Liu, Xiang Li, Zhilei Hu, Long Bai, Wei Li, Yidan Liu, Pan Yang, Xiaolong Jin, Jiafeng Guo, Xueqi Cheng. Proceedings of the 62nd Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers). 2024.

Sparse Knowledge Graphs (KGs), frequently encountered in real-world applications, contain fewer facts in the form of (head entity, relation, tail entity) compared to more populated KGs. The sparse KG completion task, which reasons answers for given queries in the form of (head entity, relation, ?) for sparse KGs, is particularly challenging due to the necessity of reasoning missing facts based on limited facts. Path-based models, known for excellent explainability, are often employed for this task. However, existing path-based models typically rely on external models to fill in missing facts and subsequently perform path reasoning. This approach introduces unexplainable factors or necessitates meticulous rule design. In light of this, this paper proposes an alternative approach by looking inward instead of seeking external assistance. We introduce a two-stage path reasoning model called LoGRe (Look Globally and Reason) over sparse KGs. LoGRe constructs a relation-path reasoning schema by globally analyzing the training data to alleviate the sparseness problem. Based on this schema, LoGRe then aggregates paths to reason out answers. Experimental results on five benchmark sparse KG datasets demonstrate the effectiveness of the proposed LoGRe model.

Temporal Knowledge Graph Question Answering (TKGQA) aims to answer questions with temporal intent over Temporal Knowledge Graphs (TKGs). The core challenge of this task lies in understanding the complex semantic information regarding multiple types of time constraints (e.g., before, first) in questions. Existing end-to-end methods implicitly model the time constraints by learning time-aware embeddings of questions and candidate answers, which is far from understanding the question comprehensively. Motivated by semantic-parsing-based approaches that explicitly model constraints in questions by generating logical forms with symbolic operators, we design fundamental temporal operators for time constraints and introduce a novel self-improvement Programming method for TKGQA (Prog-TQA). Specifically, Prog-TQA leverages the in-context learning ability of Large Language Models (LLMs) to understand the combinatory time constraints in the questions and generate corresponding program drafts with a few examples given. Then, it aligns these drafts to TKGs with the linking module and subsequently executes them to generate the answers. To enhance the ability to understand questions, Prog-TQA is further equipped with a self-improvement strategy to effectively bootstrap LLMs using high-quality self-generated drafts. Extensive experiments demonstrate the superiority of the proposed Prog-TQA on MultiTQ and CronQuestions datasets, especially in the Hits@1 metric.

Temporal Knowledge Graph (TKG), which characterizes temporally evolving facts in the form of (subject, relation, object, timestamp), has attracted much attention recently. TKG reasoning aims to predict future facts based on given historical ones. However, existing TKG reasoning models are unable to abstain from predictions they are uncertain, which will inevitably bring risks in real-world applications. Thus, in this paper, we propose an abstention mechanism for TKG reasoning, which helps the existing models make selective, instead of indiscriminate, predictions. Specifically, we develop a confidence estimator, called Confidence Estimator with History (CEHis), to enable the existing TKG reasoning models to first estimate their confidence in making predictions, and then abstain from those with low confidence. To do so, CEHis takes two kinds of information into consideration, namely, the certainty of the current prediction and the accuracy of historical predictions. Experiments with representative TKG reasoning models on two benchmark datasets demonstrate the effectiveness of the proposed CEHis.

Nested Event Extraction (NEE) aims to extract complex event structures where an event contains other events as its arguments recursively. Nested events involve a kind of Pivot Elements (PEs) that simultaneously act as arguments of outer-nest events and as triggers of inner-nest events, and thus connect them into nested structures. This special characteristic of PEs brings challenges to existing NEE methods, as they cannot well cope with the dual identities of PEs. Therefore, this paper proposes a new model, called PerNee, which extracts nested events mainly based on recognizing PEs. Specifically, PerNee first recognizes the triggers of both inner-nest and outer-nest events and further recognizes the PEs via classifying the relation type between trigger pairs. The model uses prompt learning to incorporate information from both event types and argument roles for better trigger and argument representations to improve NEE performance. Since existing NEE datasets (e.g., Genia11) are limited to specific domains and contain a narrow range of event types with nested structures, we systematically categorize nested events in the generic domain and construct a new NEE dataset, called ACE2005-Nest. Experimental results demonstrate that PerNee consistently achieves state-of-the-art performance on ACE2005-Nest, Genia11, and Genia13. The ACE2005-Nest dataset and the code of the PerNee model are available at https://github.com/waysonren/PerNee.

Hyper-relational facts, which consist of a primary triple (head entity, relation, tail entity) and auxiliary attribute-value pairs, are widely present in real-world Knowledge Graphs (KGs). Link Prediction on Hyper-relational Facts (LPHFs) is to predict a missing element in a hyper-relational fact, which helps populate and enrich KGs. However, existing LPHFs studies usually require an amount of high-quality data. They overlook few-shot relations, which have limited instances, yet are common in real-world scenarios. Thus, we introduce a new task, Few-Shot Link Prediction on Hyper-relational Facts (FSLPHFs). It aims to predict a missing entity in a hyper-relational fact with limited support instances. To tackle FSLPHFs, we propose MetaRH, a model that learns Meta Relational information in Hyper-relational facts. MetaRH comprises three modules: relation learning, support-specific adjustment, and query inference. By capturing meta relational information from limited support instances, MetaRH can accurately predict the missing entity in a query. As there is no existing dataset available for this new task, we construct three datasets to validate the effectiveness of MetaRH. Experimental results on these datasets demonstrate that MetaRH significantly outperforms existing representative models.

Event detection is one of the fundamental tasks in information extraction and knowledge graph. However, a realistic event detection system often needs to deal with new event classes constantly. These new classes usually have only a few labeled instances as it is time-consuming and labor-intensive to annotate a large number of unlabeled instances. Therefore, this paper proposes a new task, called class-incremental few-shot event detection. Nevertheless, there are two problems (i.e., old knowledge forgetting and new class overfitting) in this task. To solve these problems, this paper further presents a novel knowledge distillation and prompt learning based method, called Prompt-KD. Specifically, to reduce the forgetting issue about old knowledge, Prompt-KD develops an attention based multi-teacher knowledge distillation framework, where the ancestor teacher model pre-trained on base classes is reused in all learning sessions, and the father teacher model derives the current student model via adaptation. On the other hand, in order to cope with the few-shot learning scenario and alleviate the corresponding new class overfitting problem, Prompt-KD is also equipped with a prompt learning mechanism. Extensive experiments on two benchmark datasets, i.e., FewEvent and MAVEN, demonstrate the state-of-the-art performance of Prompt-KD.

Conventional Knowledge Graph Reasoning (KGR) models learn the embeddings of KG components over the structure of KGs, but their performances are limited when the KGs are severely incomplete.Recent LLM-enhanced KGR models input KG structural information into LLMs.However, they require fine-tuning on open-source LLMs and are not applicable to closed-source LLMs.Therefore, in this paper, to leverage the knowledge in LLMs without fine-tuning to assist and enhance conventional KGR models, we propose a new three-stage pipeline, including knowledge alignment, KG reasoning and entity reranking.Specifically, in the alignment stage, we propose three strategies to align the knowledge in LLMs to the KG schema by explicitly associating unconnected nodes with semantic relations.Based on the enriched KGs, we train structure-aware KGR models to integrate aligned knowledge to original knowledge existing in KGs.In the reranking stage, after obtaining the results of KGR models, we rerank the top-scored entities with LLMs to recall correct answers further.Experiments show our pipeline can enhance the KGR performance in both incomplete and general situations.

Script is a kind of structured knowledge extracted from texts, which contains a sequence of events. Based on such knowledge, script event prediction aims to predict the subsequent event. To do so, two aspects should be considered for events, namely, event description (i.e., what the events should contain) and event encoding (i.e., how they should be encoded). Most existing methods describe an event by a verb together with a few core arguments (i.e., subject, object, and indirect object), which are not precise enough. In addition, existing event encoders are limited to a fixed number of arguments, which are not flexible enough to deal with extra information. Thus, in this paper, we propose the Rich Event Prediction (REP) framework for script event prediction. Fundamentally, it is based on the proposed rich event description, which enriches the existing ones with three kinds of important information, namely, the senses of verbs, extra semantic roles, and types of participants. REP contains an event extractor to extract such information from texts. Based on the extracted rich information, a predictor then selects the most probable subsequent event. The core component of the predictor is a transformer-based event encoder that integrates the above information flexibly. Experimental results on the widely used Gigaword Corpus show the effectiveness of the proposed framework.

Zhilei Hu, Zixuan Li, Xiaolong Jin, Long Bai, Saiping Guan, Jiafeng Guo, Xueqi Cheng. Proceedings of the 61st Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers). 2023.

Besides entity-centric knowledge, usually organized as Knowledge Graph (KG), events are also an essential kind of knowledge in the world, which trigger the spring up of event-centric knowledge representation form like Event KG (EKG). It plays an increasingly important role in many downstream applications, such as search, question-answering, recommendation, financial quantitative investments, and text generation. This paper provides a comprehensive survey of EKG from history, ontology, instance, and application views. Specifically, to characterize EKG thoroughly, we focus on its history, definitions, schema induction, acquisition, related representative graphs/systems, and applications. The development processes and trends are studied therein. We further summarize prospective directions to facilitate future research on EKG.

With the overwhelming popularity of Knowledge Graphs (KGs), researchers have poured attention to link prediction to fill in missing facts for a long time. However, they mainly focus on link prediction on binary relational data, where facts are usually represented as triples in the form of (head entity, relation, tail entity). In practice, n-ary relational facts are also ubiquitous. When encountering such facts, existing studies usually decompose them into triples by introducing a multitude of auxiliary virtual entities and additional triples. These conversions result in the complexity of carrying out link prediction on n-ary relational data. It has even proven that they may cause loss of structure information. To overcome these problems, in this paper, we represent each n-ary relational fact as a set of its role and role-value pairs. We then propose a method called NaLP to conduct link prediction on n-ary relational data, which explicitly models the relatedness of all the role and role-value pairs in an n-ary relational fact. We further extend NaLP by introducing type constraints of roles and role-values without any external type-specific supervision, and proposing a more reasonable negative sampling mechanism. Experimental results validate the effectiveness and merits of the proposed methods.

Due to the lack of labeled data in many realistic scenarios, a number of few-shot learning methods for text classification have been proposed, among which the meta learning based ones have recently attracted much attention. Such methods usually consist of a learner as the classifier and a meta learner for specializing the learner to different tasks. For the learner, learning rate is crucial to its performance. However, existing methods treat it as a hyper parameter and adjust it manually, which is time-consuming and laborious. Intuitively, for different tasks and neural network layers, the learning rates should be different and self-adaptive. For the meta learner, it requires a good generalization ability so as to quickly adapt to new tasks. Motivated by these issues, we propose a novel meta learning framework, called MetaSLRCL, for few-shot text classification. Specifically, we present a novel meta learning mechanism to obtain different learning rates for different tasks and neural network layers so as to enable the learner to quickly adapt to new training data. Moreover, we propose a task-oriented curriculum learning mechanism to help the meta learner achieve a better generalization ability by learning from different tasks with increasing difficulties. Extensive experiments on three benchmark datasets demonstrate the effectiveness of MetaSLRCL.

Zixuan Li, Xiaolong Jin, Saiping Guan, Wei Li, Jiafeng Guo, Yuanzhuo Wang, Xueqi Cheng. Proceedings of the 59th Annual Meeting of the Association for Computational Linguistics and the 11th International Joint Conference on Natural Language Processing (Volume 1: Long Papers). 2021.

Scripts are structured sequences of events together with the participants, which are extracted from the texts.Script event prediction aims to predict the subsequent event given the historical events in the script.Two kinds of information facilitate this task, namely, the event-level information and the script-level information.At the event level, existing studies view an event as a verb with its participants, while neglecting other useful properties, such as the state of the participants.At the script level, most existing studies only consider a single event sequence corresponding to one common protagonist.In this paper, we propose a Transformer-based model, called M-CPredictor, which integrates deep event-level and script-level information for script event prediction.At the event level, MCPredictor utilizes the rich information in the text to obtain more comprehensive event semantic representations.At the script-level, it considers multiple event sequences corresponding to different participants of the subsequent event.The experimental results on the widely-used New York Times corpus demonstrate the effectiveness and superiority of the proposed model.

Knowledge Graph (KG) reasoning that predicts missing facts for incomplete KGs has been widely explored. However, reasoning over Temporal KG (TKG) that predicts facts in the future is still far from resolved. The key to predict future facts is to thoroughly understand the historical facts. A TKG is actually a sequence of KGs corresponding to different timestamps, where all concurrent facts in each KG exhibit structural dependencies and temporally adjacent facts carry informative sequential patterns. To capture these properties effectively and efficiently, we propose a novel Recurrent Evolution network based on Graph Convolution Network (GCN), called RE-GCN, which learns the evolutional representations of entities and relations at each timestamp by modeling the KG sequence recurrently. Specifically, for the evolution unit, a relation-aware GCN is leveraged to capture the structural dependencies within the KG at each timestamp. In order to capture the sequential patterns of all facts in parallel, the historical KG sequence is modeled auto-regressively by the gate recurrent components. Moreover, the static properties of entities, such as entity types, are also incorporated via a static graph constraint component to obtain better entity representations. Fact prediction at future timestamps can then be realized based on the evolutional entity and relation representations. Extensive experiments demonstrate that the RE-GCN model obtains substantial performance and efficiency improvement for the temporal reasoning tasks on six benchmark datasets. Especially, it achieves up to 11.46% improvement in MRR for entity prediction with up to 82 times speedup compared to the state-of-the-art baseline.

Distantly Supervised Relation Extraction (DSRE) has been widely studied, since it can automatically extract relations from very large corpora. However, existing DSRE methods only use little semantic information about entities, such as the information of entity type. Thus, in this paper, we propose a method for integrating entity type information into a neural network based DSRE model. It also adopts two attention mechanisms, namely, sentence attention and type attention. The former selects the representative sentences for a sentence bag, while the latter selects appropriate type information for entities. Experimental comparison with existing methods on a benchmark dataset demonstrates its merits.

Link prediction in knowledge graphs (KGs) aims at predicting potential links between entities in KGs. Existing knowledge graph embedding (KGE) based methods represent individual entities and links in KGs as vectors in low-dimension space. However, these methods focus mainly on the link prediction of individual entities, yet neglect that between group entities, which exist widely in real-world KGs. In this paper, we propose a KGE based method, called GTransA, for link prediction between group entities in a heterogeneous network by integrating individual entity links into group entity links during prediction. Experiments show that GTransA decreases mean rank by 5.4%, compared to TransA.

Knowledge inference on knowledge graph has attracted extensive attention, which aims to find out connotative valid facts in knowledge graph and is very helpful for improving the performance of many downstream applications.However, researchers have mainly poured attention to knowledge inference on binary facts.The studies on n-ary facts are relatively scarcer, although they are also ubiquitous in the real world.Therefore, this paper addresses knowledge inference on n-ary facts.We represent each n-ary fact as a primary triple coupled with a set of its auxiliary descriptive attribute-value pair(s).We further propose a neural network model, NeuInfer, for knowledge inference on n-ary facts.Besides handling the common task to infer an unknown element in a whole fact, NeuInfer can cope with a new type of task, flexible knowledge inference.It aims to infer an unknown element in a partial fact consisting of the primary triple coupled with any number of its auxiliary description(s).Experimental results demonstrate the remarkable superiority of NeuInfer.

Knowledge Graph Question Answering aims to automatically answer natural language questions via well-structured relation information between entities stored in knowledge graphs. When faced with a complex question with compositional semantics, query graph generation is a practical semantic parsing-based method. But existing works rely on heuristic rules with limited coverage, making them impractical on more complex questions. This paper proposes a Director-Actor-Critic framework to overcome these challenges. Through options over a Markov Decision Process, query graph generation is formulated as a hierarchical decision problem. The Director determines which types of triples the query graph needs, the Actor generates corresponding triples by choosing nodes and edges, and the Critic calculates the semantic similarity between the generated triples and the given questions. Moreover, to train from weak supervision, we base the framework on hierarchical Reinforcement Learning with intrinsic motivation. To accelerate the training process, we pre-train the Critic with high-reward trajectories generated by hand-crafted rules, and leverage curriculum learning to gradually increase the complexity of questions during query graph generation. Extensive experiments conducted over widely-used benchmark datasets demonstrate the effectiveness of the proposed framework.

Event coreference resolution aims to classify all event mentions that refer to the same real-world event into the same group, which is necessary to information aggregation and many downstream applications.To resolve event coreference, existing methods usually calculate the similarities between event mentions and between specific kinds of event arguments.However, they fail to accurately identify paraphrase relations between events and may suffer from error propagation while extracting event components (i.e., event mentions and their arguments).Therefore, we propose a new model based on Event-specific Paraphrases and Argument-aware Semantic Embeddings, thus called EPASE, for event coreference resolution.EPASE recognizes deep paraphrase relations in an event-specific context of sentences and can cover event paraphrases of more situations, bringing about a better generalization.Additionally, the embeddings of argument roles are encoded into event embedding without relying on a fixed number and type of arguments, which results in the better scalability of EPASE.Experiments on both within-and cross-document event coreference demonstrate its consistent and significant superiority compared to existing methods.

Knowledge Graph Question Answering aims to automatically answer natural language questions via well-structured relation information between entities stored in knowledge graphs. When faced with a multi-relation question, existing embedding-based approaches take the whole topic-entity-centric subgraph into account, resulting in high time complexity. Meanwhile, due to the high cost for data annotations, it is impractical to exactly show how to answer a complex question step by step, and only the final answer is labeled, as weak supervision. To address these challenges, this paper proposes a neural method based on reinforcement learning, namely Stepwise Reasoning Network, which formulates multi-relation question answering as a sequential decision problem. The proposed model performs effective path search over the knowledge graph to obtain the answer, and leverages beam search to reduce the number of candidates significantly. Meanwhile, based on the attention mechanism and neural networks, the policy network can enhance the unique impact of different parts of a given question over triple selection. Moreover, to alleviate the delayed and sparse reward problem caused by weak supervision, we propose a potential-based reward shaping strategy, which can accelerate the convergence of the training algorithm and help the model perform better. Extensive experiments conducted over three benchmark datasets well demonstrate the effectiveness of the proposed model, which outperforms the state-of-the-art approaches.

Haoran Yan, Xiaolong Jin, Xiangbin Meng, Jiafeng Guo, Xueqi Cheng. Proceedings of the 2019 Conference on Empirical Methods in Natural Language Processing and the 9th International Joint Conference on Natural Language Processing (EMNLP-IJCNLP). 2019.

Knowledge graphs have recently been extensively applied in many different areas (e.g., disaster management and relief, disease diagnosis). For example, event-centric knowledge graphs have been developed to improve decision making in disaster management and relief. This paper focuses on the task of event detection, which is the precondition of event extraction for constructing event-centric knowledge graphs. Event detection identifies trigger words of events in the sentences of a document and further classifies the types of events. It is straightforward that context information is useful for event detection. Therefore, the feature-based methods adopt cross-sentence information. However, they suffer from the complication of human-designed features. On the other hand, the representation-based methods learn document-level embeddings, which, however, contain much noise caused by unsupervised learning. To overcome these problems, in this paper we propose a new model based on Semi-supervised Auto-Encoder, which learns Context information to Enhance Event Detection, thus called SAE-CEED. This model first applies large-scale unlabeled texts to pre-train an auto-encoder, so that the embeddings of segments learned by the encoder contain the semantic and order information of the original text. It then uses the decoder to extract the context embeddings and fine-tunes them to enhance a bidirectional neural network model to identify event triggers and their types in sentences. Through experiments on the benchmark ACE-2005 dataset, we demonstrate the effectiveness of the proposed SAE-CEED model. In addition, we systematically conduct a series of experiments to verify the impact of different lengths of text segments in the pre-training of the auto-encoder on event detection.

With the overwhelming popularity of Knowledge Graphs (KGs), researchers have poured attention to link prediction to complete KGs for a long time. However, they mainly focus on promoting the performance on binary relational data, where facts are usually represented as triples in the form of (head entity, relation, tail entity). In practice, n-ary relational facts are also ubiquitous. When encountering such facts, existing studies usually decompose them into triples by introducing a multitude of auxiliary virtual entities and additional triples. These conversions result in the complexity of carrying out link prediction concerning more than two arities. It has even proven that they may cause loss of structural information. To overcome these problems, in this paper, without decomposition, we represent each n-ary relational fact as a set of its role-value pairs. We further propose a method to conduct Link Prediction on N-ary relational data, thus called NaLP, which explicitly models the relatedness of all the role-value pairs in the same n-ary relational fact. Experimental results validate the effectiveness and merits of the proposed NaLP method.

After entering the big data era, a new term of `big knowledge' has been coined to deal with challenges in mining a mass of knowledge from big data. While researchers used to explore the basic characteristics of big data, we have not seen any studies on the general and essential properties of big knowledge. To fill this gap, this paper studies the concepts of big knowledge, big-knowledge system, and big-knowledge engineering. Ten massiveness characteristics for big knowledge and big-knowledge systems, including massive concepts, connectedness, clean data resources, cases, confidence, capabilities, cumulativeness, concerns, consistency, and completeness, are defined and explored. Based on these characteristics, a comprehensive investigation is conducted on some large-scale knowledge engineering projects, including the Fifth Comprehensive Traffic Survey in Shanghai, the China's Xia-Shang-Zhou Chronology Project, the Troy and Trojan War Project, and the International Human Genome Project, as well as the online free encyclopedia Wikipedia. We also investigate the recent research efforts on knowledge graphs, where they are analyzed to determine which ones can be considered as big knowledge and big-knowledge systems. Further, a definition of big-knowledge engineering and its life cycle paradigm is presented. All of these projects are accordingly checked to determine whether they belong to big-knowledge engineering projects. Finally, the perspectives of big knowledge research are discussed.

Knowledge Graphs (KGs) have facilitated many real-world applications (e.g., vertical search and intelligent question answering). However, they are usually incomplete, which affects the performance of such KG based applications. To alleviate this problem, a number of Knowledge Graph Completion (KGC) methods have been developed to predict those implicit triples. Tensor/matrix based methods and translation based methods have attracted great attention for a long time. Recently, neural network has been introduced into KGC due to its extensive superiority in many fields (e.g., natural language processing and computer vision), and achieves promising results. In this paper, we propose a Shared Embedding based Neural Network (SENN) model for KGC. It integrates the prediction tasks of head entities, relations and tail entities into a neural network based framework with shared embeddings of entities and relations, while explicitly considering the differences among these prediction tasks. Moreover, we propose an adaptively weighted loss mechanism, which dynamically adjusts the weights of losses according to the mapping properties of relations, and the prediction tasks. Since relation prediction usually performs better than head and tail entity predictions, we further extend SENN to SENN+ by employing it to assist head and tail entity predictions. Experiments on benchmark datasets validate the effectiveness and merits of the proposed SENN and SENN+ methods. The shared embeddings and the adaptively weighted loss mechanism are also testified to be effective.

A knowledge graph is a graph with entities of different types as nodes and various relations among them as edges. The construction of knowledge graphs in the past decades facilitates many applications, such as link prediction, web search analysis, question answering, and so on. Knowledge graph embedding aims to represent entities and relations in a large-scale knowledge graph as elements in a continuous vector space. Existing methods, for example, TransE, TransH, and TransR, learn the embedding representation by defining a global margin-based loss function over the data. However, the loss function is determined during experiments whose parameters are examined among a closed set of candidates. Moreover, embeddings over two knowledge graphs with different entities and relations share the same set of candidates, ignoring the locality of both graphs. This leads to the limited performance of embedding related applications. In this article, a locally adaptive translation method for knowledge graph embedding, called TransA, is proposed to find the loss function by adaptively determining its margin over different knowledge graphs. Then the convergence of TransA is verified from the aspect of its uniform stability. To make the embedding methods up-to-date when new vertices and edges are added into the knowledge graph, the incremental algorithm for TransA, called iTransA, is proposed by adaptively adjusting the optimal margin over time. Experiments on four benchmark data sets demonstrate the superiority of the proposed method, as compared to the state-of-the-art ones.

Data sparsity is one of the most challenging problems for recommender systems. One promising solution to this problem is cross-domain recommendation, i.e., leveraging feedbacks or ratings from multiple domains to improve recommendation performance in a collective manner. In this paper, we propose an Embedding and Mapping framework for Cross-Domain Recommendation, called EMCDR. The proposed EMCDR framework distinguishes itself from existing cross-domain recommendation models in two aspects. First, a multi-layer perceptron is used to capture the nonlinear mapping function across domains, which offers high flexibility for learning domain-specific features of entities in each domain. Second, only the entities with sufficient data are used to learn the mapping function, guaranteeing its robustness to noise caused by data sparsity in single domain. Extensive experiments on two cross-domain recommendation scenarios demonstrate that EMCDR significantly outperforms state-of-the-art cross-domain recommendation methods.

Link inference, i.e., inferring links between vertices in a heterogeneous information network with heterogeneous vertices and edges, has been extensively studied in recent years. So far, many machine learning-based methods have been proposed for link inference, which can be classified into two categories, namely, supervised and unsupervised. Supervised methods perform well but highly rely on feature selection and training data. Although unsupervised methods are inferior to supervised ones, they work in a relatively simple way without considering the class distribution of the training data. In this paper, we investigate the link inference problem in heterogeneous information networks by proposing a knapsack-constrained inference method. Specifically, we integrate dynamic information into the heterogeneous information network and further formalize the link inference problem as a knapsack-like problem. We then solve it by the virtue of a 0-1 knapsack analogous optimization approach and investigate the time complexity of the proposed approach. Finally, experimental results show that the proposed unsupervised method can obtain high performance comparable to supervised method for some cases.

Knowledge graph embedding aims to represent entities and relations in a large-scale knowledge graph as elements in a continuous vector space. Existing methods, e.g., TransE and TransH, learn embedding representation by defining a global margin-based loss function over the data. However, the optimal loss function is determined during experiments whose parameters are examined among a closed set of candidates. Moreover, embeddings over two knowledge graphs with different entities and relations share the same set of candidate loss functions, ignoring the locality of both graphs. This leads to the limited performance of embedding related applications. In this paper, we propose a locally adaptive translation method for knowledge graph embedding, called TransA, to find the optimal loss function by adaptively determining its margin over different knowledge graphs. Experiments on two benchmark data sets demonstrate the superiority of the proposed method, as compared to the-state-of-the-art ones.

Sentiment classification aims to determine the sentiment polarity expressed in a text. In online customer reviews, the sentiment polarities of words are usually dependent on the corresponding aspects. For instance, in mobile phone reviews, we may expect the long battery time but not enjoy the long response time of the operating system. Therefore, it is necessary and appealing to consider aspects when conducting sentiment classification. Probabilistic topic models that jointly detect aspects and sentiments have gained much success recently. However, most of the existing models are designed to work well in a language with rich resources. Directly applying those models on poor-quality corpora often leads to poor results. Consequently, a potential solution is to use the cross-lingual topic model to improve the sentiment classification for a target language by leveraging data and knowledge from a source language. However, the existing cross-lingual topic models are not suitable for sentiment classification because sentiment factors are not considered therein. To solve these problems, we propose for the first time a novel cross-lingual topic model framework which can be easily combined with the state-of-the-art aspect/sentiment models. Extensive experiments in different domains and multiple languages demonstrate that our model can significantly improve the accuracy of sentiment classification in the target language.

In social networks, predicting a user’s location mainly depends on those of his/her friends, where the key lies in how to select his/her most influential friends. In this article, we analyze the theoretically maximal accuracy of location prediction based on friends’ locations and compare it with the practical accuracy obtained by the state-of-the-art location prediction methods. Upon observing a big gap between the theoretical and practical accuracy, we propose a new strategy for selecting influential friends in order to improve the practical location prediction accuracy. Specifically, several features are defined to measure the influence of the friends on a user’s location, based on which we put forth a sequential random-walk-with-restart procedure to rank the friends of the user in terms of their influence. By dynamically selecting the top N most influential friends of the user per time slice, we develop a temporal-spatial Bayesian model to characterize the dynamics of friends’ influence for location prediction. Finally, extensive experimental results on datasets of real social networks demonstrate that the proposed influential friend selection method and temporal-spatial Bayesian model can significantly improve the accuracy of location prediction.

With the coming of the era of big data, it is most urgent to establish the knowledge computational engine for the purpose of discovering implicit and valuable knowledge from the huge, rapidly dynamic, and complex network data. In this paper, we first survey the mainstream knowledge computational engines from four aspects and point out their deficiency. To cover these shortages, we propose the open knowledge network (OpenKN), which is a self-adaptive and evolutionable knowledge computational engine for network big data. To the best of our knowledge, this is the first work of designing the end-to-end and holistic knowledge processing pipeline in regard with the network big data. Moreover, to capture the evolutionable computing capability of OpenKN, we present the evolutionable knowledge network for knowledge representation. A case study demonstrates the effectiveness of the evolutionable computing of OpenKN.

Populating a knowledge base with new entity mentions extracted from unstructured text can help enhance its coverage and freshness. It naturally consists of two subtasks, namely, fine-grained entity classification and entity linking. Existing studies often focus on one of these two subtasks and they usually populate entity mentions in the same text by implicitly assuming that they are independent. However, these entity mentions are often semantically related to each other and it would be better to populate them into the knowledge base collectively. For solving these problems, in this paper we propose an interdependence graph based and unified collective inference approach, called CIIGA, to populating a knowledge base with collective entities, which can jointly determine the proper locations of all entity mentions in the same text by exploiting their interdependence relationships. Experimental results show that this approach can achieve significant accuracy improvement, as compared to the baseline approach, APOLLO, on the task of knowledge base population with multiple entities.

Sentiment analysis in various languages has been a research hotspot with many applications. However, sentiment resources (e.g., labeled corpora, sentiment lexicons) of different languages are unbalanced in terms of quality and quantity, which arouses interests in cross-lingual sentiment analysis aiming at using the resources in a source language to improve sentiment analysis in a target language. Nevertheless, many existing cross-lingual related works rely on a certain machine translation system to directly adapt the labeled data from the source language to the target language, which usually suffers from inaccurate results generated by the machine translation system. On the other hand, most sentiment analysis studies focus on document-level sentiment classification that cannot solve the aspect dependency problem of sentiment words. For instance, in the reviews on a cell phone, long is positive for the lifespan of its battery, but negative for the response time of its operating system. To solve these problems, this paper develops a novel Cross-Lingual Joint Aspect/Sentiment (CLJAS) model to carry out aspect-specific sentiment analysis in a target language using the knowledge learned from a source language. Specifically, the CLJAS model jointly detects aspects and sentiments of two languages simultaneously by incorporating sentiments into a cross-lingual topic model framework. Extensive experiments on different domains and different languages demonstrate that the proposed model can significantly improve the accuracy of sentiment classification in the target language.

Carrier Aggregation (CA) has emerged as a promising technique for Long-Term Evolution Advanced (LTE-A) wireless communications to satisfy the ever-increasing bandwidth requirements. However, this technical envisagement puts forward new challenges on radio resource allocation such as serious unbalanced loads among different Component Carriers (CCs). To alleviate this problem, a novel QoS-aware resource allocation scheme, termed as Cross-CC User Migration (CUM) scheme, is proposed in this paper to support real-time services, taking into consideration the system throughput, user fairness and QoS constraints. The experiment results show that the proposed scheme outperforms the well-known Two-Level scheduling scheme in terms of packet loss probability, average queue length and throughput per user.

ABSTRACT Traffic anomalies caused by Distributed Denial‐of‐Service (DDoS) attacks are major threats to both network service providers and legitimate customers. The DDoS attacks regularly consume and exhaust the resources of victims and hence result in abnormal bursty traffic through end‐user systems. Additionally, malicious traffic aggregated into normal traffic often show dramatic changes in the traffic nature and statistical features. This study focuses on early detection of traffic anomalies caused by DDoS attacks in light of analyzing the network traffic behavior. Key statistical features including variance, autocorrelation, and self‐similarity are employed to characterize the network traffic. Further, artificial neural network and support vector machine subject to the performance metrics are employed to predict and classify the abnormal traffic. The proposed diagnosis mechanism is validated through experiments where the datasets consist of two groups. The first group is the Massachusetts Institute of Technology Lincoln Laboratory dataset containing labeled DoS attack. The second group collected from DDoS attack simulation experiments covers three representative traffic shapes resulting from the dynamic attack rate configuration, namely, constant intensity, ramp‐up behavior, and pulsing behavior. The experimental results demonstrate that the developed mechanism can effectively and precisely alert the abnormal traffic within short response period. Copyright © 2013 John Wiley & Sons, Ltd.

Traffic congestion in communication networks can dramatically deteriorate user-perceived Quality-of-Service (QoS). The integration of the Random Early Detection (RED) and priority scheduling mechanisms is a promising scheme for congestion control and provisioning of differentiated QoS required by multimedia applications. Although analytical modelling of RED congestion control has received significant research efforts, the performance models reported in the current literature were primarily restricted to the RED algorithm only without consideration of traffic scheduling scheme for QoS differentiation. Moreover, for analytical tractability, these models were developed under the simplified assumption that the traffic follows Short-Range-Dependent (SRD) arrival processes (e.g., Poisson or Markov processes), which are unable to capture the self-similar nature (i.e., scale-invariant burstiness) of multimedia traffic in modern communication networks. To fill these gaps, this paper presents a new analytical model of RED congestion control for prioritized multi-class self-similar traffic. The closed-form expressions for the loss probability of individual traffic classes are derived. The effectiveness and accuracy of the model are validated through extensive comparison between analytical and simulation results. To illustrate its application, the model is adopted as a cost-effective tool to investigate the optimal threshold configuration and minimize the required buffer space with congestion control.

Multimedia applications in wireless networks are usually categorized into various classes according to their traffic patterns and differentiated Quality-of-Service (QoS) requirements. The traffic of heterogeneous multimedia applications often exhibits Long-Range Dependent (LRD) and Short-Range Dependent (SRD) properties, respectively. The integrated scheduling scheme that combines Priority Queuing (PQ) and Generalized Processor Sharing (GPS) within a hierarchical structure, referred to as PQ-GPS, has been identified as an efficient mechanism for QoS differentiation in wireless networks and attracted significant research efforts. However, due to the high complexity and interdependent relationship among traffic flows, modelling of the integrated scheduling scheme poses great challenges. To address this challenging and important research problem, we develop an original analytical model for PQ-GPS systems under heterogeneous LRD and SRD traffic. A cost-effective flow decomposition approach is proposed to equivalently divide the integrated scheduling system into a group of Single-Server Single-Queue (SSSQ) systems. The expressions for calculating the queue length distribution and loss probability of individual traffic flows are further derived. After validating its accuracy, the developed model is adopted as an efficient performance tool to investigate the important issues of resource allocation and call admission control in the integrated scheduling system under QoS constraints.

Distributed Denial-of-Service (DDoS) attacks are critical threats to both network service providers and legitimate network users. DDoS attacks often overwhelm or exhaust the resources of victims and typically result in abnormal bursty traffic passing through victim systems. In this paper, we develop a mechanism for diagnosing traffic anomalies caused by DDoS attacks on the basis of analyzing the behaviour of network traffic. The traffic in communication networks has been shown to exhibit statistical self-similar phenomena that can be characterized by the so-called Hurst parameter. Therefore, in the proposed mechanism the Hurst parameter coupled by variance and autocorrelation are employed as the key performance metrics to spot the anomalies of network traffic. The proposed diagnosis mechanism is validated through experiments where the datasets consist of two groups. The first group is obtained from the MIT Lincoln Laboratory DOS attack dataset. The second group is collected from our DDoS attack simulation experiments, which cover three representative traffic shapes resulting from three different DDoS attack behaviours, namely, constant intensity, ramp-up behaviour and pulse behaviour. The experimental results show that the developed mechanism can alert the DDoS attack schemes within short respond time.

Word-of-mouth has proven an effective strategy for promoting products through social relations. Particularly, existing studies have convincingly demonstrated that word-of-mouth recommendations can boost users' prior expectation and hence encourage them to adopt a certain innovation, such as buying a book or watching a movie. However, less attention has been paid to studying the posterior effect of word-of-mouth recommendations, i.e., whether or not word-of-mouth recommendations can influence users' posterior evaluation on the products or services recommended to them, the answer to which is critical to estimating user satisfaction when proposing a word-of-mouth marketing strategy. In order to fill this gap, in this paper we empirically study the above issue and verify that word-of-mouth recommendations are strongly associated with users' posterior evaluation. Through elaborately designed statistical hypothesis tests we prove the causality that word-of-mouth recommendations directly prompt the posterior evaluation of receivers. Finally, we propose a method for investigating users' social influence, namely, their ability to affect followers' posterior evaluation via word-of-mouth recommendations, by examining the number of their followers and their sensitivity of discovering good items. The experimental results on real datasets show that our method can successfully identify 78% influential friends with strong social influence.

Many high-quality measurement studies have demonstrated that wireless network traffic exhibits the noticeable Long-Range-Dependent (LRD) property. Moreover, the fading nature of wireless channels can lead to variable service capacity. Due to the inherent difficulty and high complexity of modelling the fractal-like LRD traffic, existing analytical models of queuing systems with LRD arrival processes have been primarily limited to the simplified scenarios where the service capacity is assumed to be constant. Given the time-varying nature of wireless channels in the real-world working environments, it is very important and necessary to investigate system performance in the presence of variable service capacity. To this end, this paper presents a comprehensive analytical model for queuing systems subject to LRD traffic and variable service capacity. We extend the application of a Large Deviation Principle and derive the closed-form expressions of Quality-of-Service (QoS) metrics. The accuracy of the model validated through extensive simulation experiments makes it a cost-effective evaluation tool for performance analysis of communication networks. To illustrate its applications, the model is adopted to investigate the effects of LRD traffic and variable service capacity on the system performance and resource configuration.

The growing proliferation of wireless devices in contemporary wireless networks requires more spectrum usage. As a consequence, spectrum bands are pressingly getting congested. However, a number of frequency bands licensed to operators are under utilized for transmission. Cognitive Radio (CR), as a promising technique for improving spectrum utilization, can dynamically allocate spectrum. In this paper, we investigate the performance of a CR network composed of a primary/licensed user and a number of secondary/unlicensed users, which are subject to self-similar traffic flows and contend for a unique channel. An analytical model is developed to isolate the primary and secondary users from the original networks. Further, we address the queueing performance of individual secondary users by employing a decomposition approach. The comparison between analytical and simulation results validates the accuracy of the developed model.

Abstract The provisioning of fairness to various network applications is an important Quality‐of‐Service demand and has thus become a challenging research issue in contemporary communication networks. Deficit Round Robin (DRR) is a promising fair scheduling mechanism owing to its low complexity and excellent ability of achieving a good degree of fairness in terms of throughput. On the other hand, self‐similar traffic was found to be pervasively present in communication networks and has great impact on the performance of scheduling systems. However, to the best of our knowledge, there has not been any analytical model reported in the open literature for the DRR mechanism in the presence of self‐similar traffic. To fill this gap, this paper analytically investigates the queueing performance of DRR and develops a new analytical model for deriving the upper and lower bounds of the queue length distributions of individual traffic flows in DRR scheduling systems subject to self‐similar traffic. Extensive comparison between simulation and analytical results validates the accuracy of the developed model. To demonstrate its applications, the analytical model is used to investigate the effects of packet size on the performance of the queueing system. The developed model is further applied to study the configuration of weights of individual traffic flows. Copyright © 2010 John Wiley & Sons, Ltd.

The Guard Channel (GC) scheme is an extensively deployed handover prioritization policy in wireless mobile networks due to its appealing properties of easy implementation and flexible control. Self-similar traffic has been demonstrated to be a ubiquitous phenomenon in modern communication networks and many measurement studies have demonstrated that the call holding times in wireless mobile networks follow heavy-tailed lognormal distributions. However, existing analytical models for the handover scheme usually assume that both new and handover calls can be modelled by traditional Markovian arrival processes and call holding times can be characterized by exponential distributions. In order to obtain a deep understanding of the performance behaviour of the GC-based handover scheme under more realistic working conditions, this paper presents a new analytical model for this scheme in the presence of self-similar new call and handover call arrivals and heavy-tailed lognormal call holding times. We derive the blocking probability of new calls and the dropping probability of handover calls. Extensive simulation experiments are conducted to validate the accuracy of the developed model.

Weighted fair queueing (WFQ) is a practical scheduling discipline for supporting differentiated quality-of-service (QoS) in computer networks and communication systems. Analytical models are important tools for system performance evaluation and resource optimization. However, there is not any comprehensive model reported in the open literature for analytically investigating the performance behaviors of WFQ subject to multiple self-similar traffic flows. To fill this gap, this paper develops such a model and derives the upper bounds for the distributions of several important QoS performance metrics including queue length, packet delay and loss of traffic flows in the WFQ system. The comparison between analytical and simulation results using the traffic parameters obtained from real-world MPEG frame traces validates the accuracy of the developed model which can be used for investigating the performance behavior of WFQ systems with multi-class self- similar traffic under realistic working conditions.

Traffic self-similarity has been discovered to be a ubiquitous phenomenon in communication networks and multimedia systems. Due to its fractal-like nature, performance modelling of self-similar traffic poses greater challenges and exhibits more complexity than that of traditional non-bursty traffic. As a result, most existing studies on analytical modelling of priority queueing systems with self-similar inputs have been restricted to a simplified scenario where only two traffic flows are taken into account. This study contributes to performance modelling of priority queueing systems by proposing a novel queue-decomposition approach, which offers several potential advantages and unique innovations. Specifically, we extend the well-known empty buffer approximation (EBA) method to model priority queueing systems with multiple traffic flows and decompose the original priority queueing system into a group of single-server single-queue systems, which can make the challenging performance modelling problem tractable. We further develop an analytical model to investigate the queue length distributions of individual traffic flows. The validity and accuracy of the model demonstrated through extensive simulation experiments make it a practical and cost-effective evaluation tool for quantitatively evaluating the performance behavior of priority queueing systems with multi-class self-similar traffic under various working conditions.

Call admission control plays a significant role in the provisioning of differentiated Quality-of-Service (QoS) to new calls and handover calls in wireless mobile networks. Due to its cost-effectiveness, the Guard Channel (GC) call admission control scheme has been widely deployed. Existing studies on modelling and analysis of this scheme have been usually focused on the working conditions where both new and handover calls are modelled by traditional Markovian arrival processes (e.g., Poisson processes). However, many recent measurement studies have revealed that realistic network traffic exhibits statistically self-similar nature, which is significantly different from the properties of the traditional Markovian traffic. Therefore, the existing performance models of the GC-based call admission scheme are no longer adequate to capture the self-similar call arrivals. To fill this gap, this paper presents a novel analytical model for the GC-based call admission control scheme in the presence of self-similar new call and handover call arrivals. We derive the blocking probability of new calls and the dropping probability of handover calls and validate the accuracy of the developed model through comparison between analytical and simulation results. The model is then used to investigate the optimal number of guard channels required in wireless networks such that the loss probabilities of new calls and handover calls meet their corresponding QoS requirements.

Many measurement studies have shown that telecommunication traffic usually exhibits self-similar nature and the service times of packets often follow heavy-tailed distributions. However, due to the high complexity of modelling the fractal self-similar properties and heavy-tailed distributions, most existing studies on analytical modelling of queuing systems have been confined to investigate the effects of either traffic self-similarity or heavy-tailed service times only. To fill this gap, in this paper we develop a new analytical model for a single server queuing system in the presence of self-similar inputs and heavy-tailed service time distributions. Specifically, we derive the closed-form expressions for three important quality-of-service (QoS) metrics, namely, the tail distributions of queue length, packet loss, and packet delay of the queuing systems where traffic arrivals follow the fractional Brownian motion (fBm) model and the packet sizes have lognormal or Pareto distributions. We validate the accuracy of the developed model through comparing analytical results to those obtained from experimental simulations.

Since the finding of long-range-dependent (LRD) traffic as a ubiquitous phenomenon in communication networks, analytical modelling of queuing systems subject to such type of traffic has attracted tremendous research interests. Due to the inherent difficulty and complexity of modelling fractal-like LRD traffic, existing studies have usually focused on queuing systems with constant service capacity. Given the fading nature of wireless channels under realistic working environments, it is very necessary to investigate the performance behavior of queuing systems with variable service capacity. To this end, this paper presents a new analytical model for single server queuing systems with LRD input traffic and variable service capacity. Specifically, we derive the close-form expressions for calculating the upper and lower bounds of the tail distribution of queue length in the queuing system. Resorting to extensive comparisons between analytical bounds and simulation results, we validate the effectiveness and accuracy of the model. We further adopt the model to analyze the effects of variable service capacity on the system performance.

Active Queue Management (AQM) has been proposed as an efficient policy of congestion control to achieve high system utilization and low packet delay. Many recent high-quality measurement studies have demonstrated that realistic traffic in multimedia communication systems exhibits self-similar nature, which has a significant impact on network performance and user-perceived Quality-of-Service (QoS). Performance modelling of congestion control for self-similar traffic is a challenging and important research issue. In this paper, we present a new analytical model for the AQM congestion control policy based on the well-known Random Early Detection (RED) scheme in the presence of multi-class self-similar traffic. The system buffer is partitioned by a number of thresholds in order to provide differentiated loss priorities to individual traffic classes. We derive the closed-form expressions for calculating the loss probabilities of different traffic classes. By comparing analytical and simulation results, we demonstrate the effectiveness and accuracy of the developed model.

The hybrid scheduling mechanism that integrates the well-known priority queueing (PQ) and generalized processor sharing (GPS) has been suggested as a highly- promising scheme for the provisioning and implementation of differentiated quality-of-service. Analytical modelling and performance evaluation of the fundamental PQ and GPS have drawn tremendous interests and received significant research efforts. However, to the best of our knowledge, there is not any analytical model reported for the hybrid mechanism. To fill this gap, this paper develops a novel analytical performance model for the hybrid PQ and GPS scheduling system subject to long-range dependent (LRD) traffic. The validity of the analytical model is demonstrated by comparing analytical results to those obtained through extensive simulation experiments.

This paper presents an analytical model for the hybrid PQ-GPS scheduling scheme that integrates priority queueing (PQ) and generalized processor sharing (GPS) in a hierarchical manner for the provisioning of differentiated quality-of-service. To capture the heterogeneous traffic properties in multi-service networks, the Markov-modulated Poisson process (MMPP) and the self-similar fractional Brownian motion (fBm) are used to model short-range dependent (SRD) and long-range dependent (LRD) traffic, respectively. We propose an efficient flow-decomposition method and derive the queue length distributions and loss probabilities of individual traffic flows in the hybrid scheduling system. The comparison between analytical and simulation results validates the accuracy of the analytical model. To illustrate its application, we employ this model as an efficient tool to study the resource allocation issue under the constraint of loss probability.

Traffic self-similarity has been discovered to be a ubiquitous phenomenon in modern communication networks and multimedia systems. Due to its scale-invariant bursty nature, performance modelling of self-similar traffic poses greater challenges and exhibits more complexity than that of traditional non-bursty traffic. As a result, most existing studies on analytical modelling of priority queueing systems with self-similar inputs have been restricted to a simplified scenario where only two traffic flows are taken into account. This study contributes to performance modelling and analysis of priority queueing systems by proposing a novel and efficient queue-decomposition approach to handle multi-class self-similar traffic. Specifically, we extend the well-known method of empty buffer approximation in order to decompose the priority queueing system equivalently into a group of single-server single-queue systems. We further obtain the analytical upper and lower bounds of the queue length distributions for individual traffic flows.

Generalized processor sharing (GPS) is an efficient and flexible scheduling mechanism for sharing server capacity and providing differentiated quality-of-service (QoS) owing to its appealing properties of fairness, traffic isolation, and work conservation. This paper analytically investigates the loss probabilities of individual traffic flows in GPS systems subject to heterogeneous long-range dependent (LRD) and short-range dependent (SRD) traffic, which have not been studied in the open literature. We derive and validate the closed-form expressions of the loss probabilities of both traffic flows. We then evaluate the effects of Hurst parameter of LRD traffic on the performance of GPS systems in terms of traffic loss probability.

The priority queueing discipline plays a crucial role in the differentiated services (DiffServ) architecture. Analytical modelling and performance evaluation of priority queueing systems have received significant research efforts in the telecommunication community. However, most existing studies have primarily focused on the analysis of such systems under either short range dependent (SRD) or long range dependent (LRD) traffic only. With the aim of investigating the impact of heterogeneous traffic on the design and performance of telecommunication networks, this paper presents an analytical model for priority queueing systems subject to heterogeneous LRD self-similar and SRD Poisson traffic. We extend the application of the generalized Schilder's theorem to deal with heterogeneous traffic and further develop the analytical upper and lower bounds for the queue length distributions of individual traffic flows. Through extensive comparisons between analytical bounds and simulation results, we validate the effectiveness and accuracy of the developed model.

Performance modelling of generalized processor sharing (GPS) systems in the presence of self-similar traffic has attracted significant research efforts. To simplify the interdependent relationships between traffic flows in GPS systems, most existing studies have been confined to the unrealistic scenarios where only two traffic flows are taken into account. This paper develops an analytical model for investigating both queue length distributions and loss probabilities of GPS systems subject to multi-class self-similar traffic. To this end, we present an efficient approach to decompose the complicated system based on the notion of feasible ordering of GPS systems and the empty buffer approximation. Through extensive comparisons between analytical and simulation results, we investigate the correctness of the decomposition approach and validate the accuracy of the analytical performance results.