arXiv subjects

Hui He

Publications and source records attributed to Hui He.

At least 37 records · Page 2Linked to original sources

arXiv2024

Towards Bridging the Cross-modal Semantic Gap for Multi-modal Recommendation

Multi-modal recommendation greatly enhances the performance of recommender systems by modeling the auxiliary information from multi-modality contents. Most existing multi-modal recommendation models primarily exploit multimedia information propagation processes to enrich item representations and directly utilize modal-specific embedding vectors independently obtained from upstream pre-trained models. However, this might be inappropriate since the abundant task-specific semantics remain unexplored, and the cross-modality semantic gap hinders the recommendation performance. Inspired by the recent progress of the cross-modal alignment model CLIP, in this paper, we propose a novel \textbf{CLIP} \textbf{E}nhanced \textbf{R}ecommender (\textbf{CLIPER}) framework to bridge the semantic gap between modalities and extract fine-grained multi-view semantic information. Specifically, we introduce a multi-view modality-alignment approach for representation extraction and measure the semantic similarity between modalities. Furthermore, we integrate the multi-view multimedia representations into downstream recommendation models. Extensive experiments conducted on three public datasets demonstrate the consistent superiority of our model over state-of-the-art multi-modal recommendation models.

cs.IR↗

arXiv2024

Distributional Drift Adaptation with Temporal Conditional Variational Autoencoder for Multivariate Time Series Forecasting

Due to the non-stationary nature, the distribution of real-world multivariate time series (MTS) changes over time, which is known as distribution drift. Most existing MTS forecasting models greatly suffer from distribution drift and degrade the forecasting performance over time. Existing methods address distribution drift via adapting to the latest arrived data or self-correcting per the meta knowledge derived from future data. Despite their great success in MTS forecasting, these methods hardly capture the intrinsic distribution changes, especially from a distributional perspective. Accordingly, we propose a novel framework temporal conditional variational autoencoder (TCVAE) to model the dynamic distributional dependencies over time between historical observations and future data in MTSs and infer the dependencies as a temporal conditional distribution to leverage latent variables. Specifically, a novel temporal Hawkes attention mechanism represents temporal factors subsequently fed into feed-forward networks to estimate the prior Gaussian distribution of latent variables. The representation of temporal factors further dynamically adjusts the structures of Transformer-based encoder and decoder to distribution changes by leveraging a gated attention mechanism. Moreover, we introduce conditional continuous normalization flow to transform the prior Gaussian to a complex and form-free distribution to facilitate flexible inference of the temporal conditional distribution. Extensive experiments conducted on six real-world MTS datasets demonstrate the TCVAE's superior robustness and effectiveness over the state-of-the-art MTS forecasting baselines. We further illustrate the TCVAE applicability through multifaceted case studies and visualization in real-world scenarios.

cs.LG↗

arXiv2024

Deep Coupling Network For Multivariate Time Series Forecasting

Multivariate time series (MTS) forecasting is crucial in many real-world applications. To achieve accurate MTS forecasting, it is essential to simultaneously consider both intra- and inter-series relationships among time series data. However, previous work has typically modeled intra- and inter-series relationships separately and has disregarded multi-order interactions present within and between time series data, which can seriously degrade forecasting accuracy. In this paper, we reexamine intra- and inter-series relationships from the perspective of mutual information and accordingly construct a comprehensive relationship learning mechanism tailored to simultaneously capture the intricate multi-order intra- and inter-series couplings. Based on the mechanism, we propose a novel deep coupling network for MTS forecasting, named DeepCN, which consists of a coupling mechanism dedicated to explicitly exploring the multi-order intra- and inter-series relationships among time series data concurrently, a coupled variable representation module aimed at encoding diverse variable patterns, and an inference module facilitating predictions through one forward step. Extensive experiments conducted on seven real-world datasets demonstrate that our proposed DeepCN achieves superior performance compared with the state-of-the-art baselines.

cs.LG↗

arXiv2024

Multitier Service Migration Framework Based on Mobility Prediction in Mobile Edge Computing

Mobile edge computing (MEC) pushes computing resources to the edge of the network and distributes them at the edge of the mobile network. Offloading computing tasks to the edge instead of the cloud can reduce computing latency and backhaul load simultaneously. However, new challenges incurred by user mobility and limited coverage of MEC server service arise. Services should be dynamically migrated between multiple MEC servers to maintain service performance due to user movement. Tackling this problem is nontrivial because it is arduous to predict user movement, and service migration will generate service interruptions and redundant network traffic. Service interruption time must be minimized, and redundant network traffic should be reduced to ensure service quality. In this paper, the container lives migration technology based on prediction is studied, and an online prediction method based on map data that does not rely on prior knowledge such as user trajectories is proposed to address this challenge in terms of mobility prediction accuracy.

cs.NI↗

arXiv2024

Masked AutoEncoder for Graph Clustering without Pre-defined Cluster Number k

Graph clustering algorithms with autoencoder structures have recently gained popularity due to their efficient performance and low training cost. However, for existing graph autoencoder clustering algorithms based on GCN or GAT, not only do they lack good generalization ability, but also the number of clusters clustered by such autoencoder models is difficult to determine automatically. To solve this problem, we propose a new framework called Graph Clustering with Masked Autoencoders (GCMA). It employs our designed fusion autoencoder based on the graph masking method for the fusion coding of graph. It introduces our improved density-based clustering algorithm as a second decoder while decoding with multi-target reconstruction. By decoding the mask embedding, our model can capture more generalized and comprehensive knowledge. The number of clusters and clustering results can be output end-to-end while improving the generalization ability. As a nonparametric class method, extensive experiments demonstrate the superiority of \textit{GCMA} over state-of-the-art baselines.

cs.LG↗

arXiv2023

Frequency-domain MLPs are More Effective Learners in Time Series Forecasting

Time series forecasting has played the key role in different industrial, including finance, traffic, energy, and healthcare domains. While existing literatures have designed many sophisticated architectures based on RNNs, GNNs, or Transformers, another kind of approaches based on multi-layer perceptrons (MLPs) are proposed with simple structure, low complexity, and {superior performance}. However, most MLP-based forecasting methods suffer from the point-wise mappings and information bottleneck, which largely hinders the forecasting performance. To overcome this problem, we explore a novel direction of applying MLPs in the frequency domain for time series forecasting. We investigate the learned patterns of frequency-domain MLPs and discover their two inherent characteristic benefiting forecasting, (i) global view: frequency spectrum makes MLPs own a complete view for signals and learn global dependencies more easily, and (ii) energy compaction: frequency-domain MLPs concentrate on smaller key part of frequency components with compact signal energy. Then, we propose FreTS, a simple yet effective architecture built upon Frequency-domain MLPs for Time Series forecasting. FreTS mainly involves two stages, (i) Domain Conversion, that transforms time-domain signals into complex numbers of frequency domain; (ii) Frequency Learning, that performs our redesigned MLPs for the learning of real and imaginary part of frequency components. The above stages operated on both inter-series and intra-series scales further contribute to channel-wise and time-wise dependency learning. Extensive experiments on 13 real-world benchmarks (including 7 benchmarks for short-term forecasting and 6 benchmarks for long-term forecasting) demonstrate our consistent superiority over state-of-the-art methods.

cs.LG↗

arXiv2023

FourierGNN: Rethinking Multivariate Time Series Forecasting from a Pure Graph Perspective

Multivariate time series (MTS) forecasting has shown great importance in numerous industries. Current state-of-the-art graph neural network (GNN)-based forecasting methods usually require both graph networks (e.g., GCN) and temporal networks (e.g., LSTM) to capture inter-series (spatial) dynamics and intra-series (temporal) dependencies, respectively. However, the uncertain compatibility of the two networks puts an extra burden on handcrafted model designs. Moreover, the separate spatial and temporal modeling naturally violates the unified spatiotemporal inter-dependencies in real world, which largely hinders the forecasting performance. To overcome these problems, we explore an interesting direction of directly applying graph networks and rethink MTS forecasting from a pure graph perspective. We first define a novel data structure, hypervariate graph, which regards each series value (regardless of variates or timestamps) as a graph node, and represents sliding windows as space-time fully-connected graphs. This perspective considers spatiotemporal dynamics unitedly and reformulates classic MTS forecasting into the predictions on hypervariate graphs. Then, we propose a novel architecture Fourier Graph Neural Network (FourierGNN) by stacking our proposed Fourier Graph Operator (FGO) to perform matrix multiplications in Fourier space. FourierGNN accommodates adequate expressiveness and achieves much lower complexity, which can effectively and efficiently accomplish the forecasting. Besides, our theoretical analysis reveals FGO's equivalence to graph convolutions in the time domain, which further verifies the validity of FourierGNN. Extensive experiments on seven datasets have demonstrated our superior performance with higher efficiency and fewer parameters compared with state-of-the-art methods.

cs.LG↗

arXiv2023

Learning Informative Representation for Fairness-aware Multivariate Time-series Forecasting: A Group-based Perspective

Performance unfairness among variables widely exists in multivariate time series (MTS) forecasting models since such models may attend/bias to certain (advantaged) variables. Addressing this unfairness problem is important for equally attending to all variables and avoiding vulnerable model biases/risks. However, fair MTS forecasting is challenging and has been less studied in the literature. To bridge such significant gap, we formulate the fairness modeling problem as learning informative representations attending to both advantaged and disadvantaged variables. Accordingly, we propose a novel framework, named FairFor, for fairness-aware MTS forecasting. FairFor is based on adversarial learning to generate both group-independent and group-relevant representations for the downstream forecasting. The framework first leverages a spectral relaxation of the K-means objective to infer variable correlations and thus to group variables. Then, it utilizes a filtering&fusion component to filter the group-relevant information and generate group-independent representations via orthogonality regularization. The group-independent and group-relevant representations form highly informative representations, facilitating to sharing knowledge from advantaged variables to disadvantaged variables to guarantee fairness. Extensive experiments on four public datasets demonstrate the effectiveness of our proposed FairFor for fair forecasting and significant performance improvement.

cs.LG↗

arXiv2023

Efficient and Secure Federated Learning for Financial Applications

The conventional machine learning (ML) and deep learning approaches need to share customers' sensitive information with an external credit bureau to generate a prediction model that opens the door to privacy leakage. This leakage risk makes financial companies face an enormous challenge in their cooperation. Federated learning is a machine learning setting that can protect data privacy, but the high communication cost is often the bottleneck of the federated systems, especially for large neural networks. Limiting the number and size of communications is necessary for the practical training of large neural structures. Gradient sparsification has received increasing attention as a method to reduce communication cost, which only updates significant gradients and accumulates insignificant gradients locally. However, the secure aggregation framework cannot directly use gradient sparsification. This article proposes two sparsification methods to reduce communication cost in federated learning. One is a time-varying hierarchical sparsification method for model parameter update, which solves the problem of maintaining model accuracy after high ratio sparsity. It can significantly reduce the cost of a single communication. The other is to apply the sparsification method to the secure aggregation framework. We sparse the encryption mask matrix to reduce the cost of communication while protecting privacy. Experiments show that under different Non-IID experiment settings, our method can reduce the upload communication cost to about 2.9% to 18.9% of the conventional federated learning algorithm when the sparse rate is 0.01.

cs.LG↗

arXiv2023

Pruning, cut trees, and the reconstruction problem

We consider a pruning of the inhomogeneous continuum random trees, as well as the cut trees that encode the genealogies of the fragmentations that come with the pruning. We propose a new approach to the reconstruction problem, which has been treated for the Brownian CRT in [Electron. J. Probab. vol. 22, 2017] and for the stable trees in [Ann. IHP B, vol 55, 2019]. Our approach does not rely upon self-similarity and can potentially apply to general Lévy trees as well.

math.PR↗

arXiv2022

Edge-Varying Fourier Graph Networks for Multivariate Time Series Forecasting

The key problem in multivariate time series (MTS) analysis and forecasting aims to disclose the underlying couplings between variables that drive the co-movements. Considerable recent successful MTS methods are built with graph neural networks (GNNs) due to their essential capacity for relational modeling. However, previous work often used a static graph structure of time-series variables for modeling MTS failing to capture their ever-changing correlations over time. To this end, a fully-connected supra-graph connecting any two variables at any two timestamps is adaptively learned to capture the high-resolution variable dependencies via an efficient graph convolutional network. Specifically, we construct the Edge-Varying Fourier Graph Networks (EV-FGN) equipped with Fourier Graph Shift Operator (FGSO) which efficiently performs graph convolution in the frequency domain. As a result, a high-efficiency scale-free parameter learning scheme is derived for MTS analysis and forecasting according to the convolution theorem. Extensive experiments show that EV-FGN outperforms state-of-the-art methods on seven real-world MTS datasets.

cs.LG↗

arXiv2021

Crowd-sensing Enhanced Parking Patrol using Trajectories of Sharing Bikes

Illegal vehicle parking is a common urban problem faced by major cities in the world, as it incurs traffic jams, which lead to air pollution and traffic accidents. The government highly relies on active human efforts to detect illegal parking events. However, such an approach is extremely ineffective to cover a large city since the police have to patrol over the entire city roads. The massive and high-quality sharing bike trajectories from Mobike offer us a unique opportunity to design a ubiquitous illegal parking detection approach, as most of the illegal parking events happen at curbsides and have significant impact on the bike users. The detection result can guide the patrol schedule, i.e. send the patrol policemen to the region with higher illegal parking risks, and further improve the patrol efficiency. Inspired by this idea, three main components are employed in the proposed framework: 1)~{\em trajectory pre-processing}, which filters outlier GPS points, performs map-matching, and builds trajectory indexes; 2)~{\em illegal parking detection}, which models the normal trajectories, extracts features from the evaluation trajectories, and utilizes a distribution test-based method to discover the illegal parking events; and 3)~{\em patrol scheduling}, which leverages the detection result as reference context, and models the scheduling task as a multi-agent reinforcement learning problem to guide the patrol police. Finally, extensive experiments are presented to validate the effectiveness of illegal parking detection, as well as the improvement of patrol efficiency.

cs.LG↗

arXiv2021

POI Alias Discovery in Delivery Addresses using User Locations

People often refer to a place of interest (POI) by an alias. In e-commerce scenarios, the POI alias problem affects the quality of the delivery address of online orders, bringing substantial challenges to intelligent logistics systems and market decision-making. Labeling the aliases of POIs involves heavy human labor, which is inefficient and expensive. Inspired by the observation that the users' GPS locations are highly related to their delivery address, we propose a ubiquitous alias discovery framework. Firstly, for each POI name in delivery addresses, the location data of its associated users, namely Mobility Profile are extracted. Then, we identify the alias relationship by modeling the similarity of mobility profiles. Comprehensive experiments on the large-scale location data and delivery address data from JD logistics validate the effectiveness.

cs.SI↗

arXiv2020

Quality of Service (QoS): Measurements of Video Streaming

Nowadays video streaming is growing over the social clouds, where end-users always want to share High Definition (HD) videos among friends. Mostly videos were recorded via smartphones and other HD devices and short time videos have a big file size. The big file size of videos required high bandwidth to upload and download on the Internet and also required more time to load in a web page for play. So avoiding this problem social cloud compress videos during the upload for smooth play and fast loading in a web page. Compression decreases the video quality which also decreases the quality of experience of end users. In this paper we measure the QoS of different standard video file formats on social clouds; they varied from each other in resolution, audio/video bitrate, and storage size.

cs.MM↗

arXiv2020

Branching Brownian motion conditioned on small maximum

We consider a standard binary branching Brownian motion on the real line. It is known that the maximal position $M_t$ among all particles alive at time $t$, shifted by $m_t = \sqrt{2} t - \frac{3}{2\sqrt{2}} \log t$ converges in law to a randomly shifted Gumbel variable. Derrida and Shi (2017) conjectured the precise asymptotic behaviour of the corresponding lower deviation probability $\mathbb{P}(M_t \leq \sqrt{2}αt)$ for $α< 1$. We verify their conjecture, and describe the law of the branching Brownian motion conditioned on having a small maximum.

math.PR↗

arXiv2020

Some properties of stationary continuous state branching processes

We consider the genealogical tree of a stationary continuous state branching process with immigration. For a sub-critical stable branching mechanism, we consider the genealogical tree of the extant population at some fixed time and prove that, up to a deterministic time-change, it is distributed as a continuous-time Galton-Watson process with immigration. We obtain similar results for a critical stable branching mechanism when only looking at immigrants arriving in some fixed time-interval. For a general sub-critical branching mechanism, we consider the number of individuals that give descendants in the extant population. The associated processes (forward or backward in time) are pure-death or pure-birth Markov processes, for which we compute the transition rates.

math.PR↗

arXiv2018

Lower deviation and moderate deviation probabilities for maximum of a branching random walk

Given a super-critical branching random walk on $\mathbb R$ started from the origin, let $M_n$ be the maximal position of individuals at the $n$-th generation. Under some mild conditions, it is known from \cite{A13} that as $n\rightarrow\infty$, $M_n-x^*n+\frac{3}{2θ^*}\log n$ converges in law for some suitable constants $x^*$ and $θ^*$. In this work, we investigate its moderate deviation, in other words, the convergence rates of $$\mathbb{P}\left(M_n\leq x^*n-\frac{3}{2θ^*}\log n-\ell_n\right),$$ for any positive sequence $(\ell_n)$ such that $\ell_n=O(n)$ and $\ell_n\uparrow\infty$. As a by-product, we also obtain lower deviation of $M_n$; i.e., the convergence rate of \[ \mathbb{P}(M_n\leq xn), \] for $x<x^*$ in Böttcher case where the offspring number is at least two. Finally, we apply our techniques to study the small ball probability of limit of derivative martingale.

math.PR↗

arXiv2017

A tree-valued Markov processes associated with an admissible family of branching mechanisms

By studying an admissible family of branching mechanisms introduced in Li (2014), we obtain a pruning procedure on Lévy trees. Then we could construct a decreasing Lévy-CRT-valued process $\{{\mathcal T}_t\}$ by pruning Lévy trees and an analogous process $\{{\mathcal T}^*_t\}$ by pruning a critical Lévy tree conditioned to be infinite. Under a regular condition on the admissible family of branching mechanisms, we show that the law of $\{{\mathcal T}_t\}$ at the ascension time can be represented by $\{{\mathcal T}^*_t\}$. The results generalize those studied in Abraham and Delmas (2012).

math.PR↗