arXiv subjects

Xinyu Fu

Publications and source records attributed to Xinyu Fu.

27 records · Page 2Linked to original sources

arXiv2024

Perfect Simulation of Las Vegas Algorithms via Local Computation

The notion of Las Vegas algorithms was introduced by Babai (1979) and can be defined in two ways: * In Babai's original definition, a randomized algorithm is called Las Vegas if it has a finitely bounded running time and certifiable random failure. * Another definition widely accepted today is that Las Vegas algorithms refer to zero-error randomized algorithms with random running times. The equivalence between the two definitions is straightforward. Specifically, for randomized algorithms with certifiable failures, repeatedly running the algorithm until no failure is encountered allows for faithful simulation of the correct output when it executes successfully. We show that a similar perfect simulation can also be achieved in distributed local computation. Specifically, in the LOCAL model, with polylogarithmic overhead in time complexity, any Las Vegas algorithm with finitely bounded running time and locally certifiable failures can be converted to a zero-error Las Vegas algorithm. This transformed algorithm faithfully reproduces the correct output of the original algorithm in successful executions.

cs.DS↗

arXiv2023

MECCH: Metapath Context Convolution-based Heterogeneous Graph Neural Networks

Heterogeneous graph neural networks (HGNNs) were proposed for representation learning on structural data with multiple types of nodes and edges. To deal with the performance degradation issue when HGNNs become deep, researchers combine metapaths into HGNNs to associate nodes closely related in semantics but far apart in the graph. However, existing metapath-based models suffer from either information loss or high computation costs. To address these problems, we present a novel Metapath Context Convolution-based Heterogeneous Graph Neural Network (MECCH). MECCH leverages metapath contexts, a new kind of graph structure that facilitates lossless node information aggregation while avoiding any redundancy. Specifically, MECCH applies three novel components after feature preprocessing to extract comprehensive information from the input graph efficiently: (1) metapath context construction, (2) metapath context encoder, and (3) convolutional metapath fusion. Experiments on five real-world heterogeneous graph datasets for node classification and link prediction show that MECCH achieves superior prediction accuracy compared with state-of-the-art baselines with improved computational efficiency.

cs.LG↗

arXiv2023

FedHGN: A Federated Framework for Heterogeneous Graph Neural Networks

Heterogeneous graph neural networks (HGNNs) can learn from typed and relational graph data more effectively than conventional GNNs. With larger parameter spaces, HGNNs may require more training data, which is often scarce in real-world applications due to privacy regulations (e.g., GDPR). Federated graph learning (FGL) enables multiple clients to train a GNN collaboratively without sharing their local data. However, existing FGL methods mainly focus on homogeneous GNNs or knowledge graph embeddings; few have considered heterogeneous graphs and HGNNs. In federated heterogeneous graph learning, clients may have private graph schemas. Conventional FL/FGL methods attempting to define a global HGNN model would violate schema privacy. To address these challenges, we propose FedHGN, a novel and general FGL framework for HGNNs. FedHGN adopts schema-weight decoupling to enable schema-agnostic knowledge sharing and employs coefficients alignment to stabilize the training process and improve HGNN performance. With better privacy preservation, FedHGN consistently outperforms local training and conventional FL methods on three widely adopted heterogeneous graph datasets with varying client numbers. The code is available at https://github.com/cynricfu/FedHGN .

cs.LG↗

arXiv2023

Locally-iterative $(Δ+1)$-Coloring in Sublinear (in $Δ$) Rounds

Distributed graph coloring is one of the most extensively studied problems in distributed computing. There is a canonical family of distributed graph coloring algorithms known as the locally-iterative coloring algorithms, first formalized in the seminal work of [Szegedy and Vishwanathan, STOC'93]. In such algorithms, every vertex iteratively updates its own color according to a predetermined function of the current coloring of its local neighborhood. Due to the simplicity and naturalness of its framework, locally-iterative coloring algorithms are of great significance both in theory and practice. In this paper, we give a locally-iterative $(Δ+1)$-coloring algorithm with $O(Δ^{3/4}\logΔ)+\log^*n$ running time. This is the first locally-iterative $(Δ+1)$-coloring algorithm with sublinear-in-$Δ$ running time, and answers the main open question raised in a recent breakthrough [Barenboim, Elkin, and Goldberg, JACM'21]. A key component of our algorithm is a locally-iterative procedure that transforms an $O(Δ^2)$-coloring to a $(Δ+O(Δ^{3/4}\logΔ))$-coloring in $o(Δ)$ time. Inside this procedure we work on special proper colorings that encode (arb)defective colorings, and reduce the number of used colors quadratically in a locally-iterative fashion. As a main application of our result, we also give a self-stabilizing distributed algorithm for $(Δ+1)$-coloring with $O(Δ^{3/4}\logΔ)+\log^*n$ stabilization time. To the best of our knowledge, this is the first self-stabilizing algorithm for $(Δ+1)$-coloring with sublinear-in-$Δ$ stabilization time.

cs.DS↗

arXiv2022

Modelling Hospital Strategies in City-Scale Ambulance Dispatching

The optimisation in the ambulance dispatching process is significant for patients who need early treatments. However, the problem of dynamic ambulance redeployment for destination hospital selection has rarely been investigated. The paper proposes an approach to model and simulate the ambulance dispatching process in multi-agents healthcare environments of large cities. The proposed approach is based on using the coupled game-theoretic (GT) approach to identify hospital strategies (considering hospitals as players within a non-cooperative game) and performing discrete-event simulation (DES) of patient delivery and provision of healthcare services to evaluate ambulance dispatching (selection of target hospital). Assuming the collective nature of decisions on patient delivery, the approach assesses the influence of the diverse behaviours of hospitals on system performance with possible further optimisation of this performance. The approach is studied through a series of cases starting with a simplified 1D model and proceeding with a coupled 2D model and real-world application. The study considers the problem of dispatching ambulances to patients with the ACS directed to the PCI in the target hospital. A real-world case study of data from Saint Petersburg (Russia) is analysed showing the better conformity of the global characteristics (mortality rate) of the healthcare system with the proposed approach being applied to discovering the agents' diverse behaviour.

cs.CY↗

arXiv2020

Retrieving and ranking short medical questions with two stages neural matching model

Internet hospital is a rising business thanks to recent advances in mobile web technology and high demand of health care services. Online medical services become increasingly popular and active. According to US data in 2018, 80 percent of internet users have asked health-related questions online. Numerous data is generated in unprecedented speed and scale. Those representative questions and answers in medical fields are valuable raw data sources for medical data mining. Automated machine interpretation on those sheer amount of data gives an opportunity to assist doctors to answer frequently asked medical-related questions from the perspective of information retrieval and machine learning approaches. In this work, we propose a novel two-stage framework for the semantic matching of query-level medical questions.

cs.CL↗

arXiv2020

MAGNN: Metapath Aggregated Graph Neural Network for Heterogeneous Graph Embedding

A large number of real-world graphs or networks are inherently heterogeneous, involving a diversity of node types and relation types. Heterogeneous graph embedding is to embed rich structural and semantic information of a heterogeneous graph into low-dimensional node representations. Existing models usually define multiple metapaths in a heterogeneous graph to capture the composite relations and guide neighbor selection. However, these models either omit node content features, discard intermediate nodes along the metapath, or only consider one metapath. To address these three limitations, we propose a new model named Metapath Aggregated Graph Neural Network (MAGNN) to boost the final performance. Specifically, MAGNN employs three major components, i.e., the node content transformation to encapsulate input node attributes, the intra-metapath aggregation to incorporate intermediate semantic nodes, and the inter-metapath aggregation to combine messages from multiple metapaths. Extensive experiments on three real-world heterogeneous graph datasets for node classification, node clustering, and link prediction show that MAGNN achieves more accurate prediction results than state-of-the-art baselines.

cs.SI↗

arXiv2017

CRNN: A Joint Neural Network for Redundancy Detection

This paper proposes a novel framework for detecting redundancy in supervised sentence categorisation. Unlike traditional singleton neural network, our model incorporates character-aware convolutional neural network (Char-CNN) with character-aware recurrent neural network (Char-RNN) to form a convolutional recurrent neural network (CRNN). Our model benefits from Char-CNN in that only salient features are selected and fed into the integrated Char-RNN. Char-RNN effectively learns long sequence semantics via sophisticated update mechanism. We compare our framework against the state-of-the-art text classification algorithms on four popular benchmarking corpus. For instance, our model achieves competing precision rate, recall ratio, and F1 score on the Google-news data-set. For twenty-news-groups data stream, our algorithm obtains the optimum on precision rate, recall ratio, and F1 score. For Brown Corpus, our framework obtains the best F1 score and almost equivalent precision rate and recall ratio over the top competitor. For the question classification collection, CRNN produces the optimal recall rate and F1 score and comparable precision rate. We also analyse three different RNN hidden recurrent cells' impact on performance and their runtime efficiency. We observe that MGU achieves the optimal runtime and comparable performance against GRU and LSTM. For TFIDF based algorithms, we experiment with word2vec, GloVe, and sent2vec embeddings and report their performance differences.

cs.CL↗

arXiv2016

An Improved System for Sentence-level Novelty Detection in Textual Streams

Novelty detection in news events has long been a difficult problem. A number of models performed well on specific data streams but certain issues are far from being solved, particularly in large data streams from the WWW where unpredictability of new terms requires adaptation in the vector space model. We present a novel event detection system based on the Incremental Term Frequency-Inverse Document Frequency (TF-IDF) weighting incorporated with Locality Sensitive Hashing (LSH). Our system could efficiently and effectively adapt to the changes within the data streams of any new terms with continual updates to the vector space model. Regarding miss probability, our proposed novelty detection framework outperforms a recognised baseline system by approximately 16% when evaluating a benchmark dataset from Google News.

cs.IR↗