arXiv subjects

Yongjun Xu

Publications and source records attributed to Yongjun Xu.

At least 91 records · Page 5Linked to original sources

arXiv2023

AdapTraj: A Multi-Source Domain Generalization Framework for Multi-Agent Trajectory Prediction

Multi-agent trajectory prediction, as a critical task in modeling complex interactions of objects in dynamic systems, has attracted significant research attention in recent years. Despite the promising advances, existing studies all follow the assumption that data distribution observed during model learning matches that encountered in real-world deployments. However, this assumption often does not hold in practice, as inherent distribution shifts might exist in the mobility patterns for deployment environments, thus leading to poor domain generalization and performance degradation. Consequently, it is appealing to leverage trajectories from multiple source domains to mitigate such discrepancies for multi-agent trajectory prediction task. However, the development of multi-source domain generalization in this task presents two notable issues: (1) negative transfer; (2) inadequate modeling for external factors. To address these issues, we propose a new causal formulation to explicitly model four types of features: domain-invariant and domain-specific features for both the focal agent and neighboring agents. Building upon the new formulation, we propose AdapTraj, a multi-source domain generalization framework specifically tailored for multi-agent trajectory prediction. AdapTraj serves as a plug-and-play module that is adaptable to a variety of models. Extensive experiments on four datasets with different domains demonstrate that AdapTraj consistently outperforms other baselines by a substantial margin.

cs.AI↗

arXiv2023

Dynamic Frequency Domain Graph Convolutional Network for Traffic Forecasting

Complex spatial dependencies in transportation networks make traffic prediction extremely challenging. Much existing work is devoted to learning dynamic graph structures among sensors, and the strategy of mining spatial dependencies from traffic data, known as data-driven, tends to be an intuitive and effective approach. However, Time-Shift of traffic patterns and noise induced by random factors hinder data-driven spatial dependence modeling. In this paper, we propose a novel dynamic frequency domain graph convolution network (DFDGCN) to capture spatial dependencies. Specifically, we mitigate the effects of time-shift by Fourier transform, and introduce the identity embedding of sensors and time embedding when capturing data for graph learning since traffic data with noise is not entirely reliable. The graph is combined with static predefined and self-adaptive graphs during graph convolution to predict future traffic data through classical causal convolutions. Extensive experiments on four real-world datasets demonstrate that our model is effective and outperforms the baselines.

cs.LG↗

arXiv2023

DSformer: A Double Sampling Transformer for Multivariate Time Series Long-term Prediction

Multivariate time series long-term prediction, which aims to predict the change of data in a long time, can provide references for decision-making. Although transformer-based models have made progress in this field, they usually do not make full use of three features of multivariate time series: global information, local information, and variables correlation. To effectively mine the above three features and establish a high-precision prediction model, we propose a double sampling transformer (DSformer), which consists of the double sampling (DS) block and the temporal variable attention (TVA) block. Firstly, the DS block employs down sampling and piecewise sampling to transform the original series into feature vectors that focus on global information and local information respectively. Then, TVA block uses temporal attention and variable attention to mine these feature vectors from different dimensions and extract key information. Finally, based on a parallel structure, DSformer uses multiple TVA blocks to mine and integrate different features obtained from DS blocks respectively. The integrated feature information is passed to the generative decoder based on a multi-layer perceptron to realize multivariate time series long-term prediction. Experimental results on nine real-world datasets show that DSformer can outperform eight existing baselines.

cs.LG↗

arXiv2023

Categories of Response-Based, Feature-Based, and Relation-Based Knowledge Distillation

Deep neural networks have achieved remarkable performance for artificial intelligence tasks. The success behind intelligent systems often relies on large-scale models with high computational complexity and storage costs. The over-parameterized networks are often easy to optimize and can achieve better performance. However, it is challenging to deploy them over resource-limited edge-devices. Knowledge Distillation (KD) aims to optimize a lightweight network from the perspective of over-parameterized training. The traditional offline KD transfers knowledge from a cumbersome teacher to a small and fast student network. When a sizeable pre-trained teacher network is unavailable, online KD can improve a group of models by collaborative or mutual learning. Without needing extra models, Self-KD boosts the network itself using attached auxiliary architectures. KD mainly involves knowledge extraction and distillation strategies these two aspects. Beyond KD schemes, various KD algorithms are widely used in practical applications, such as multi-teacher KD, cross-modal KD, attention-based KD, data-free KD and adversarial KD. This paper provides a comprehensive KD survey, including knowledge categories, distillation schemes and algorithms, as well as some empirical studies on performance comparison. Finally, we discuss the open challenges of existing KD works and prospect the future directions.

cs.CV↗

arXiv2023

Modeling Dual Period-Varying Preferences for Takeaway Recommendation

Takeaway recommender systems, which aim to accurately provide stores that offer foods meeting users' interests, have served billions of users in our daily life. Different from traditional recommendation, takeaway recommendation faces two main challenges: (1) Dual Interaction-Aware Preference Modeling. Traditional recommendation commonly focuses on users' single preferences for items while takeaway recommendation needs to comprehensively consider users' dual preferences for stores and foods. (2) Period-Varying Preference Modeling. Conventional recommendation generally models continuous changes in users' preferences from a session-level or day-level perspective. However, in practical takeaway systems, users' preferences vary significantly during the morning, noon, night, and late night periods of the day. To address these challenges, we propose a Dual Period-Varying Preference modeling (DPVP) for takeaway recommendation. Specifically, we design a dual interaction-aware module, aiming to capture users' dual preferences based on their interactions with stores and foods. Moreover, to model various preferences in different time periods of the day, we propose a time-based decomposition module as well as a time-aware gating mechanism. Extensive offline and online experiments demonstrate that our model outperforms state-of-the-art methods on real-world datasets and it is capable of modeling the dual period-varying preferences. Moreover, our model has been deployed online on Meituan Takeaway platform, leading to an average improvement in GMV (Gross Merchandise Value) of 0.70%.

cs.IR↗

arXiv2023

Growth of nonsymmetric operads

The paper concerns the Gelfand-Kirillov dimension and the generating series of nonsymmetric operads. An analogue of Bergman's gap theorem is proved, namely, no finitely generated locally finite nonsymmetric operad has Gelfand-Kirillov dimension strictly between $1$ and $2$. For every $r\in \{0\}\cup \{1\}\cup [2,\infty)$ or $r=\infty$, we construct a single-element generated nonsymmetric operad with Gelfand-Kirillov dimension $r$. We also provide counterexamples to two expectations of Khoroshkin and Piontkovski about the generating series of operads.

math.RA↗

arXiv2023

Exploiting Constructive Interference for Backscatter Communication Systems

Backscatter communication (BackCom), one of the core technologies to realize zero-power communication, is expected to be a pivotal paradigm for the next generation of the Internet of Things (IoT). However, the "strong" direct link (DL) interference (DLI) is traditionally assumed to be harmful, and generally drowns out the "weak" backscattered signals accordingly, thus deteriorating the performance of BackCom. In contrast to the previous efforts to eliminate the DLI, in this paper, we exploit the constructive interference (CI), in which the DLI contributes to the backscattered signal. To be specific, our objective is to maximize the received signal power by jointly optimizing the receive beamforming vectors and tag selection factors, which is, however, non-convex and difficult to solve due to constraints on the Kullback-Leibler (KL) divergence. In order to solve this problem, we first decompose the original problem, and then propose two algorithms to solve the sub-problem with beamforming design via a change of variables and semi-definite programming (SDP) and a greedy algorithm to solve the sub-problem with tag selection. In order to gain insight into the CI, we consider a special case with the single-antenna reader to reveal the channel angle between the backscattering link (BL) and the DL, in which the DLI will become constructive. Simulation results show that significant performance gain can always be achieved in the proposed algorithms compared with the traditional algorithms without the DL in terms of the strength of the received signal. The derived constructive channel angle for the BackCom system with the single-antenna reader is also confirmed by simulation results.

cs.IT↗

arXiv2023

Attacking Pre-trained Recommendation

Recently, a series of pioneer studies have shown the potency of pre-trained models in sequential recommendation, illuminating the path of building an omniscient unified pre-trained recommendation model for different downstream recommendation tasks. Despite these advancements, the vulnerabilities of classical recommender systems also exist in pre-trained recommendation in a new form, while the security of pre-trained recommendation model is still unexplored, which may threaten its widely practical applications. In this study, we propose a novel framework for backdoor attacking in pre-trained recommendation. We demonstrate the provider of the pre-trained model can easily insert a backdoor in pre-training, thereby increasing the exposure rates of target items to target user groups. Specifically, we design two novel and effective backdoor attacks: basic replacement and prompt-enhanced, under various recommendation pre-training usage scenarios. Experimental results on real-world datasets show that our proposed attack strategies significantly improve the exposure rates of target items to target users by hundreds of times in comparison to the clean model.

cs.IR↗

arXiv2023

Hopf PBW-deformations of a new type quantum group

In this paper, we mainly focus on a new type quantum group $U_{q}(\mathfrak{sl}^{*}_2)$ and its Hopf PBW-deformations $U_{q}(\mathfrak{sl}^{*}_2,κ)$ in which $U_{q}(\mathfrak{sl}^{*}_2,0) = U_{q}(\mathfrak{sl}^{*}_2)$ and the classical Drinfeld-Jimbo quantum group $U_{q}(\mathfrak{sl}_2)$ is included. The category of finite dimensional $U_{q}(\mathfrak{sl}^{*}_2)$-modules is proved to be non-semisimple. We establish a uniform block decomposition of the category $U_{q}(\mathfrak{sl}^{*}_2,κ){\mbox -}{\rm \bf mod}_{\rm wt}$ of finite dimensional weight modules for each $U_{q}(\mathfrak{sl}^{*}_2,κ)$, and reduce the investigation on $U_{q}(\mathfrak{sl}^{*}_2,κ){\mbox -}{\rm \bf mod}_{\rm wt}$ to its principle block(s). We introduce the notion of primitive object in $U_{q}(\mathfrak{sl}^{*}_2,κ){\mbox -}{\rm \bf mod}_{\rm wt}$ which affords a new and elementary way to verify the semisimplicity of the category of finite dimensional $U_{q}(\mathfrak{sl}_2)$-modules. As the core of this present paper, a tensor equivalence between the principal block(s) of $U_{q}(\mathfrak{sl}^{*}_2,κ){\mbox -}{\rm \bf mod}_{\rm wt}$ and the category of finite dimensional representations of (deformed) preprojective algebras of Dynkin type $\A$ is obtained.

math.QA↗

arXiv2023

eTag: Class-Incremental Learning with Embedding Distillation and Task-Oriented Generation

Class-Incremental Learning (CIL) aims to solve the neural networks' catastrophic forgetting problem, which refers to the fact that once the network updates on a new task, its performance on previously-learned tasks drops dramatically. Most successful CIL methods incrementally train a feature extractor with the aid of stored exemplars, or estimate the feature distribution with the stored prototypes. However, the stored exemplars would violate the data privacy concerns, while the stored prototypes might not reasonably be consistent with a proper feature distribution, hindering the exploration of real-world CIL applications. In this paper, we propose a method of \textit{e}mbedding distillation and \textit{Ta}sk-oriented \textit{g}eneration (\textit{eTag}) for CIL, which requires neither the exemplar nor the prototype. Instead, eTag achieves a data-free manner to train the neural networks incrementally. To prevent the feature extractor from forgetting, eTag distills the embeddings of the network's intermediate blocks. Additionally, eTag enables a generative network to produce suitable features, fitting the needs of the top incremental classifier. Experimental results confirmed that our proposed eTag considerably outperforms the state-of-the-art methods on CIFAR-100 and ImageNet-sub\footnote{Our code is available in the Supplementary Materials.

cs.CV↗

arXiv2023

Online Knowledge Distillation via Mutual Contrastive Learning for Visual Recognition

The teacher-free online Knowledge Distillation (KD) aims to train an ensemble of multiple student models collaboratively and distill knowledge from each other. Although existing online KD methods achieve desirable performance, they often focus on class probabilities as the core knowledge type, ignoring the valuable feature representational information. We present a Mutual Contrastive Learning (MCL) framework for online KD. The core idea of MCL is to perform mutual interaction and transfer of contrastive distributions among a cohort of networks in an online manner. Our MCL can aggregate cross-network embedding information and maximize the lower bound to the mutual information between two networks. This enables each network to learn extra contrastive knowledge from others, leading to better feature representations, thus improving the performance of visual recognition tasks. Beyond the final layer, we extend MCL to intermediate layers and perform an adaptive layer-matching mechanism trained by meta-optimization. Experiments on image classification and transfer learning to visual recognition tasks show that layer-wise MCL can lead to consistent performance gains against state-of-the-art online KD approaches. The superiority demonstrates that layer-wise MCL can guide the network to generate better feature representations. Our code is publicly avaliable at https://github.com/winycg/L-MCL.

cs.CV↗

arXiv2022

Heterogeneous Graph Neural Network with Multi-view Representation Learning

Graph neural networks for heterogeneous graph embedding is to project nodes into a low-dimensional space by exploring the heterogeneity and semantics of the heterogeneous graph. However, on the one hand, most of existing heterogeneous graph embedding methods either insufficiently model the local structure under specific semantic, or neglect the heterogeneity when aggregating information from it. On the other hand, representations from multiple semantics are not comprehensively integrated to obtain versatile node embeddings. To address the problem, we propose a Heterogeneous Graph Neural Network with Multi-View Representation Learning (named MV-HetGNN) for heterogeneous graph embedding by introducing the idea of multi-view representation learning. The proposed model consists of node feature transformation, view-specific ego graph encoding and auto multi-view fusion to thoroughly learn complex structural and semantic information for generating comprehensive node representations. Extensive experiments on three real-world heterogeneous graph datasets show that the proposed MV-HetGNN model consistently outperforms all the state-of-the-art GNN baselines in various downstream tasks, e.g., node classification, node clustering, and link prediction.

cs.LG↗

arXiv2022

Joint Optimization of Active and Passive Beamforming in Multi-IRS Aided mmWave Communications

Intelligent reflecting surface (IRS) has been considered as a promising technology to alleviate the blockage effect and enhance coverage in millimeter wave (mmWave) communication. To explore the impact of IRS on the performance of mmWave communication, we investigate a multi-IRS assisted mmWave communication network and formulate a sum rate maximization problem by jointly optimizing the active and passive beamforming and the set of IRSs for assistance. The optimization problem is intractable due to the lack of convexity of the objective function and the binary nature of the IRS selection variables. To tackle the complex non-convex problem, an alternating iterative approach is proposed. In particular, utilizing the fractional programming method to optimize the active and passive beamforming and the optimization of IRS selection is solved by enumerating. Simulation results demonstrate the performance gain of our proposed approach.

eess.SP↗

arXiv2022

Gain without Pain: Recycling Reflected Energy from Wireless Powered RIS-aided Communications

In this paper, we investigate and analyze energy recycling for a reconfigurable intelligent surface (RIS)-aided wireless-powered communication network. As opposed to the existing works where the energy harvested by Internet of things (IoT) devices only come from the power station, IoT devices are also allowed to recycle energy from other IoT devices. In particular, we propose group switching- and user switching-based protocols with time-division multiple access to evaluate the impact of energy recycling on system performance. Two different optimization problems are respectively formulated for maximizing the sum throughput by jointly optimizing the energy beamforming vectors, the transmit power, the transmission time, the receive beamforming vectors, the grouping factors, and the phase-shift matrices, where the constraints of the minimum throughput, the harvested energy, the maximum transmit power, the phase shift, the grouping, and the time allocation are taken into account. In light of the intractability of the above problems, we respectively develop two alternating optimization-based iterative algorithms by combining the successive convex approximation method and the penalty-based method to obtain corresponding sub-optimal solutions. Simulation results verify that the energy recycling-based mechanism can assist in enhancing the performance of IoT devices in terms of energy harvesting and information transmission. Besides, we also verify that the group switching-based algorithm can improve more sum throughput of IoT devices, and the user switching-based algorithm can harvest more energy.

cs.IT↗

arXiv2022

Decoupled Dynamic Spatial-Temporal Graph Neural Network for Traffic Forecasting

We all depend on mobility, and vehicular transportation affects the daily lives of most of us. Thus, the ability to forecast the state of traffic in a road network is an important functionality and a challenging task. Traffic data is often obtained from sensors deployed in a road network. Recent proposals on spatial-temporal graph neural networks have achieved great progress at modeling complex spatial-temporal correlations in traffic data, by modeling traffic data as a diffusion process. However, intuitively, traffic data encompasses two different kinds of hidden time series signals, namely the diffusion signals and inherent signals. Unfortunately, nearly all previous works coarsely consider traffic signals entirely as the outcome of the diffusion, while neglecting the inherent signals, which impacts model performance negatively. To improve modeling performance, we propose a novel Decoupled Spatial-Temporal Framework (DSTF) that separates the diffusion and inherent traffic information in a data-driven manner, which encompasses a unique estimation gate and a residual decomposition mechanism. The separated signals can be handled subsequently by the diffusion and inherent modules separately. Further, we propose an instantiation of DSTF, Decoupled Dynamic Spatial-Temporal Graph Neural Network (D2STGNN), that captures spatial-temporal correlations and also features a dynamic graph learning module that targets the learning of the dynamic characteristics of traffic networks. Extensive experiments with four real-world traffic datasets demonstrate that the framework is capable of advancing the state-of-the-art.

cs.LG↗

arXiv2022

Spatial-Temporal Identity: A Simple yet Effective Baseline for Multivariate Time Series Forecasting

Multivariate Time Series (MTS) forecasting plays a vital role in a wide range of applications. Recently, Spatial-Temporal Graph Neural Networks (STGNNs) have become increasingly popular MTS forecasting methods due to their state-of-the-art performance. However, recent works are becoming more sophisticated with limited performance improvements. This phenomenon motivates us to explore the critical factors of MTS forecasting and design a model that is as powerful as STGNNs, but more concise and efficient. In this paper, we identify the indistinguishability of samples in both spatial and temporal dimensions as a key bottleneck, and propose a simple yet effective baseline for MTS forecasting by attaching Spatial and Temporal IDentity information (STID), which achieves the best performance and efficiency simultaneously based on simple Multi-Layer Perceptrons (MLPs). These results suggest that we can design efficient and effective models as long as they solve the indistinguishability of samples, without being limited to STGNNs.

cs.LG↗

arXiv2022

Pre-training Enhanced Spatial-temporal Graph Neural Network for Multivariate Time Series Forecasting

Multivariate Time Series (MTS) forecasting plays a vital role in a wide range of applications. Recently, Spatial-Temporal Graph Neural Networks (STGNNs) have become increasingly popular MTS forecasting methods. STGNNs jointly model the spatial and temporal patterns of MTS through graph neural networks and sequential models, significantly improving the prediction accuracy. But limited by model complexity, most STGNNs only consider short-term historical MTS data, such as data over the past one hour. However, the patterns of time series and the dependencies between them (i.e., the temporal and spatial patterns) need to be analyzed based on long-term historical MTS data. To address this issue, we propose a novel framework, in which STGNN is Enhanced by a scalable time series Pre-training model (STEP). Specifically, we design a pre-training model to efficiently learn temporal patterns from very long-term history time series (e.g., the past two weeks) and generate segment-level representations. These representations provide contextual information for short-term time series input to STGNNs and facilitate modeling dependencies between time series. Experiments on three public real-world datasets demonstrate that our framework is capable of significantly enhancing downstream STGNNs, and our pre-training model aptly captures temporal patterns.

cs.LG↗

arXiv2022

MixSKD: Self-Knowledge Distillation from Mixup for Image Recognition

Unlike the conventional Knowledge Distillation (KD), Self-KD allows a network to learn knowledge from itself without any guidance from extra networks. This paper proposes to perform Self-KD from image Mixture (MixSKD), which integrates these two techniques into a unified framework. MixSKD mutually distills feature maps and probability distributions between the random pair of original images and their mixup images in a meaningful way. Therefore, it guides the network to learn cross-image knowledge by modelling supervisory signals from mixup images. Moreover, we construct a self-teacher network by aggregating multi-stage feature maps for providing soft labels to supervise the backbone classifier, further improving the efficacy of self-boosting. Experiments on image classification and transfer learning to object detection and semantic segmentation demonstrate that MixSKD outperforms other state-of-the-art Self-KD and data augmentation methods. The code is available at https://github.com/winycg/Self-KD-Lib.

cs.CV↗