Retrieval-Augmented Generation (RAG) effectively enhances Large Language Models (LLMs) by incorporating retrieved external knowledge into the generation process. Reasoning models improve LLM performance in multi-hop QA tasks, which require integrating and reasoning over multiple pieces of evidence across different documents to answer a complex question. However, they often introduce substantial computational costs, including increased token consumption and inference latency. To better understand and mitigate this trade-off, we conduct a comprehensive study of reasoning strategies for reasoning models in RAG multi-hop QA tasks. Our findings reveal that reasoning models adopt structured strategies to integrate retrieved and internal knowledge, primarily following two modes: Context-Grounded Reasoning, which relies directly on retrieved content, and Knowledge-Reconciled Reasoning, which resolves conflicts or gaps using internal knowledge. To this end, we propose a novel Lightweight Rerank Reasoning Strategy Framework for RAG (LiR³AG) to enable non-reasoning models to transfer reasoning strategies by restructuring retrieved evidence into coherent reasoning chains. LiR³AG significantly reduce the average 98% output tokens overhead and 58.6% inferencing time while improving 8B non-reasoning model's F1 performance ranging from 6.2% to 22.5% to surpass the performance of 32B reasoning model in RAG, offering a practical and efficient path forward for RAG systems.

Temporal graph neural networks (T-GNNs) have emerged as an effective paradigm for learning dynamic node representations by modeling the temporal evolution of graph structures. Among them, personalized PageRank (PPR)-based T-GNNs have recently gained increasing attention due to their strong empirical performance and theoretical grounding. Nevertheless, existing PPR-based T-GNN methods suffer from two fundamental limitations. First, their aggregation mechanisms are typically restricted to lower order neighborhoods, which hinders the capture of higher order temporal dependences and leads to degraded performance. Second, feature propagation and feature transformation are often tightly coupled, resulting in limited scalability on large temporal graphs. To overcome these challenges, we propose temporal personalized PageRank with spectral sparsification (TPPSS), a novel framework that seamlessly incorporates temporal information into the PPR formulation while decoupling propagation from transformation through a polynomial spectral sparsification. A key technical contribution ofTPPSSlies in a unified matrix-based formulation that replaces the conventional rowwise computation of PPR-like scores, enabling efficient and scalable. Moreover, by leveraging spectral sparsification,TPPSSconstructs a sparse computational graph that effectively suppresses noise and redundancy. Extensive experiments on six datasets showcase the effectiveness, efficiency, and scalability of our solutions compared to eight competitors.

Identifying locally dense communities closely connected to the user-initiated query node is crucial for a wide range of applications. Existing approaches either solely depend on rule based constraints or exclusively utilize deep learning technologies to identify target communities. Therefore, an important question is proposed: can deep learning be integrated with rule-based constraints to elevate the quality of community search? In this paper, we affirmatively address this question by introducing a novel approach called Neural Community Search via Attribute augmented Conductance, abbreviated as NCSAC. Specifically, NCSAC first proposes a novel concept of attribute-augmented conductance, which harmoniously blends the (internal and ex ternal) structural proximity and the attribute similarity. Then, NCSAC extracts a coarse candidate community of satisfactory quality using the proposed attribute-augmented conductance. Subsequently, NCSAC frames the community search as a graph optimization task, refining the candidate community through sophisticated reinforcement learning techniques, thereby producing high-quality results. Extensive experiments on six real world graphs and ten competitors demonstrate the superiority of our solutions in terms of accuracy, efficiency, and scalability. Notably, the proposed solution outperforms state-of-the-art methods, achieving an impressive F1-score improvement ranging from 5.3% to 42.4%. For reproducibility purposes, the source code is available at https://github.com/longlonglin/ncsac.

Recommendation systems have become indispensable in various online platforms, from e-commerce to streaming services. A fundamental challenge in this domain is learning effective embeddings from sparse user-item interactions. While contrastive learning has recently emerged as a promising solution to this issue, generating augmented views for contrastive learning through most existing random data augmentation methods often leads to the alteration of original semantic information. In this paper, we propose a novel framework, GDA4Rec (Generative Data Augmentation in graph contrastive learning for Recommendation) to generate high-quality augmented views and provide robust self-supervised signals. Specifically, we employ a noise generation module that leverages deep generative models to approximate the distribution of original data for data augmentation. Additionally, GDA4Rec further extracts an item complement matrix to characterize the latent correlations between items and provide additional self-supervised signals. Lastly, a joint objective that integrates recommendation, data augmentation and contrastive learning is used to enforce the model to learn more effective and informative embeddings. Extensive experiments are conducted on three public datasets to demonstrate the superiority of the model. The code is available at: https://github.com/MrYansong/GDA4Rec.

Design patterns are powerful tools that provide standardized solutions to common problems in the software design process. Detecting design patterns in software systems can greatly facilitate software maintenance and code understanding, but manual detection is a complex and challenging task. In recent years, with the development of deep learning techniques, researchers have proposed automatic design pattern detection methods that utilize code features and machine learning classifiers. However, these approaches typically focus on either code semantic features or structural features, lacking the integration of both. To address this issue, in this paper, we propose a novel design pattern detection method with multi-feature fusion, DPDMF2, which effectively fuses code semantic features and software network structural features for design pattern detection. Specifically, we first represent software as a CSN (Class-level Software Network) to capture its topology, including classes, their relationships, and the types of these relationships. Concurrently, we utilize code representation learning techniques to obtain semantic features of the code, which are then used as node attribute features within the network. Finally, we utilize graph neural networks (GNNs) to fuse these two types of features, generating a vector representation that encapsulates both semantic and structural information for design pattern detection task. Experimental results on public datasets show that DPDMF2achieves 81.7% precision and 82.1% recall, validating the overall effectiveness of our method.

Graph Neural Networks (GNNs) have garnered substantial attention due to their remarkable capability in learning graph representations. However, real-world graphs often exhibit substantial noise and incompleteness, which severely degrades the performance of GNNs. Existing methods typically address this issue through single-dimensional augmentation, focusing either on refining topology structures or perturbing node attributes, thereby overlooking the deeper interplays between the two. To bridge this gap, this paper presents CoATA, a dual-channel GNN framework specifically designed for the Co-Augmentation of Topology and Attribute. Specifically, CoATA first propagates structural signals to enrich and denoise node attributes. Then, it projects the enhanced attribute space into a node-attribute bipartite graph for further refinement or reconstruction of the underlying structure. Subsequently, CoATA introduces contrastive learning, leveraging prototype alignment and consistency constraints, to facilitate mutual corrections between the augmented and original graphs. Finally, extensive experiments on seven benchmark datasets demonstrate that the proposed CoATA outperforms eleven state-of-the-art baseline methods, showcasing its effectiveness in capturing the synergistic relationship between topology and attributes.

Functional brain network (FBN) modeling often relies on local pairwise interactions, whose limitation in capturing high-order dependencies is theoretically analyzed in this paper. Meanwhile, the computational burden and heuristic nature of current hypergraph modeling approaches hinder end-to-end learning of FBN structures directly from data distributions. To address this, we propose to extract high-order FBN structures under global constraints, and implement this as a Global Constraints oriented Multi-resolution (GCM) FBN structure learning framework. It incorporates 4 types of global constraint (signal synchronization, subject identity, expected edge numbers, and data labels) to enable learning FBN structures for 4 distinct levels (sample/subject/group/project) of modeling resolution. Experimental results demonstrate that GCM achieves up to a 30.6% improvement in relative accuracy and a 96.3% reduction in computational time across 5 datasets and 2 task settings, compared to 9 baselines and 10 state-of-the-art methods. Extensive experiments validate the contributions of individual components and highlight the interpretability of GCM. This work offers a novel perspective on FBN structure learning and provides a foundation for interdisciplinary applications in cognitive neuroscience. Code is publicly available on https://github.com/lzhan94swu/GCM.

Community search is a widely studied semi-supervised graph clustering problem, retrieving a high-quality connected subgraph containing the user-specified query vertex. However, existing methods primarily focus on cohesiveness within the community but ignore the sparsity outside the community, obtaining sub-par results. Inspired by this, we adopt the well-knownconductancemetric to measure the quality of a community and introduce a novel problem ofconductance-based community search (CCS).CCSaims at finding a subgraph with the smallestconductanceamong all connected subgraphs that contain the query vertex. We prove that theCCSproblem is NP-hard. To efficiently queryCCS, a four-stagesubgraph-conductance-based community search algorithm,SCCS, is proposed. Specifically, we first greatly reduce the entire graph using local sampling techniques. Then, a three-stage local optimization strategy is employed to continuously refine the community quality. Namely, we first utilize a seeding strategy to obtain an initial community to enhance its internal cohesiveness. Then, we iteratively add qualified vertices in the expansion stage to guarantee the internal cohesiveness and external sparsity of the community. Finally, we gradually remove unqualified vertices during the verification stage. Extensive experiments on real-world datasets containing one billion-scale graph and synthetic datasets show the effectiveness, efficiency, and scalability of our solutions.

In modern society, software systems are integral to various aspects of life. Finding an efficient vulnerability identification approach is crucial for ensuring security and preventing malicious attacks. In recent years, many deep learning-based methods have shown outstanding performance in the vulnerability detection task. However, these methods still have limitations. Some methods consider code input as token sequences and apply architectures typically used in natural language processing. They fail to utilize the structural information from various code components' interactions, which limits these models' performance. Other methods based on graph neural networks, although better at learning structural information, treat each node equally and fail to emphasize key elements. To overcome these limitations, we propose CTGGSG, an effective vulnerability detection approach over Code Token Graph (CTG) based on GCN with score gate. In our model, we use PLE-CG-SE module to represent the source code samples as the CTGs, effectively utilizing the high-quality feature representation of PL-PLM (Pre-trained Language Model based on Program Languages) and retaining structural information from the source code. During the graph learning process, we combine GCN convolution and score gate mechanism to make the model focus more on the key nodes within the graph and increase the receptive field of the nodes. To comprehensively evaluate the performance and scalability of our model, we conducted experiments on two real-world datasets: CodeX Glue,which contains balanced sample labels, and Re-veal, which contains imbalanced sample labels. These datasets contain 27,318 and 22,734 function-level samples, respectively, derived from large-scale, popular real-world projects. Compared to existing advanced vulnerability detection methods, our model achieved state-of-the-art performance overall.

Network embedding has numerous practical applications and has received extensive attention in graph learning, which aims at mapping vertices into a low-dimensional and continuous dense vector space by preserving the underlying structural properties of the graph. Many network embedding methods have been proposed, among which factorization of the Personalized PageRank (PPR for short) matrix has been empirically and theoretically well supported recently. However, several fundamental issues cannot be addressed. (1) Existing methods invoke a seminal Local Push subroutine to approximate a single row or column of the PPR matrix. Thus, they have to execute n (n is the number of nodes) Local Push subroutines to obtain a provable PPR matrix, resulting in prohibitively high computational costs for large n. (2) The PPR matrix has limited power in capturing the structural similarity between vertices, leading to performance degradation. To overcome these dilemmas, we propose PSNE, an efficient spectral sParsification method for Scaling Network Embedding, which can fast obtain the embedding vectors that retain strong structural similarities. Specifically, PSNE first designs a matrix polynomial sparser to accelerate the calculation of the PPR matrix, which has a theoretical guarantee in terms of the Frobenius norm. Subsequently, PSNE proposes a simple but effective multiple-perspective strategy to enhance further the representation power of the obtained approximate PPR matrix. Finally, PSNE applies a randomized singular value decomposition algorithm on the sparse and multiple-perspective PPR matrix to get the target embedding vectors. Experimental evaluation of real-world and synthetic datasets shows that our solutions are indeed more efficient, effective, and scalable compared with ten competitors.

Higher-order graph clustering aims to partition the graph using frequently occurring subgraphs (i.e., motifs), instead of the lower-order edges, as the atomic clustering unit, which has been recognized as the state-of-the-art solution in ground truth community detection and knowledge discovery. Motif conductance is one of the most promising higher-order graph clustering models due to its strong interpretability. However, existing motif conductance based graph clustering algorithms are mainly limited by a seminal two-stage reweighting computing framework, needing to enumerate all motif instances to obtain an edge-weighted graph for partitioning. However, such a framework has two-fold vital defects: (1) It can only provide a quadratic bound for the motif with three vertices, and whether there is provable clustering quality for other motifs is still an open question. (2) The enumeration procedure of motif instances incurs prohibitively high costs against large motifs or large dense graphs due to combinatorial explosions. Besides, expensive spectral clustering or local graph diffusion on the edge-weighted graph also makes existing methods unable to handle massive graphs with millions of nodes. To overcome these dilemmas, we propose a Provable and Scalable Motif Conductance algorithm PSMC, which has a fixed and motif-independent approximation ratio for any motif. Specifically, PSMC first defines a new vertex metric Motif Resident based on the given motif, which can be computed locally. Then, it iteratively deletes the vertex with the smallest motif resident value very efficiently using novel dynamic update technologies. Finally, it outputs the locally optimal result during the above iterative process. To further boost efficiency, we propose several effective bounds to estimate the motif resident value of each vertex, which can greatly reduce computational costs. Empirical results on real-life and synthetic demonstrate that our proposed algorithms achieve 3.2-32 times speedup and improve the quality by at least 12 times than the state-of-the art baselines.

Graph Neural Networks (GNNs) have achieved remarkable performance in various applications, including social media analysis, computer vision, and natural language processing. Decoupled GNNs are a ubiquitous framework because of their high efficiency. However, existing decoupled GNNs suffer from the following several defects. (1) Their studies on GNN feature propagation are isolated, with each study emphasizing a user-specified propagation matrix. (2) They still have high computation costs to achieve provable performance on massive graphs with millions of nodes and billions of edges. (3) Their feature propagation steps are uniform, which makes it difficult for them to escape the dilemmas of over-smoothing. In this paper, we propose GSD-GNN, a Generalized and Scalable Decoupled GNN framework based on the spectral graph theory, which offers the following advantages. Firstly, through minor parameter adjustments, it can degenerate into most existing Decoupled GNNs, such as APPNP, GDC, SGC, etc. Secondly, it efficiently computes an arbitrary propagation matrix with near-linear time complexity and theoretical guarantees. Thirdly, it customizes the adaptive feature propagation mechanism for each node to mitigate the over-smoothing dilemma. Finally, extensive experiments on massive graphs demonstrate that the proposed GSD-GNN indeed is effective, scalable, and flexible.

Temporal community search is an important task in graph analysis, which has been widely used in many practical applications. However, existing methods suffer from two major defects: (i) they only require that the target result contains the query vertexq, leading to the temporal proximity betweenqand other vertices being ignored. Thus, they may find many temporal irrelevant vertices (these vertices are called query-drifted vertices) concerningqfor satisfying their objective functions; (ii) their methods are NP-hard, incurring high costs for exact solutions or compromised qualities for approximate/heuristic algorithms. In this paper, we propose a new problem named query-centered temporal community search to overcome these limitations. Specifically, we first present a novel concept of Time-Constrained Personalized PageRank to characterize the temporal proximity betweenqand other vertices. Then, we introduce a model calledβ-temporal proximity core, which can seamlessly combine temporal proximity and structural cohesiveness. Subsequently, our problem is formulated as an optimization task that finds aβ-temporal proximity core with the largestβ.We theoretically prove that our problem can circumvent these query-drifted vertices. To solve our problem, we first devise an exact and near-linear time greedy removing algorithm that iteratively removes unpromising vertices. To improve efficiency, we then design an approximate two-stage local search algorithm with bound-based pruning techniques. Finally, extensive experiments on eight real-life datasets and nine competitors show the superiority of the proposed solutions.

Conductance-based graph clustering has been recognized as a fundamental operator in numerous graph analysis applications. Despite the significant success of conductance-based graph clustering, existing algorithms are either hard to obtain satisfactory clustering qualities, or have high time and space complexity to achieve provable clustering qualities. To overcome these limitations, we devise a powerful peeling-based graph clustering framework PCon. We show that many existing solutions can be reduced to our framework. Namely, they first define a score function for each vertex, then iteratively remove the vertex with the smallest score. Finally, they output the result with the smallest conductance during the peeling process. Based on our framework, we propose two novel algorithms PCon_core and PCon_de with linear time and space complexity, which can efficiently and effectively identify clusters from massive graphs with more than a few billion edges. Surprisingly, we prove that PCon_de can identify clusters with near-constant approximation ratio, resulting in an important theoretical improvement over the well-known quadratic Cheeger bound. Empirical results on real-life and synthetic datasets show that our algorithms can achieve 5~42 times speedup with a high clustering accuracy, while using 1.4~7.8 times less memory than the baseline algorithms.

While collaborative systems provide convenience to our lives, they also face many security threats. One of them is the Low-rate Distributed Denial-of-Service (LDDoS) attack, which is a worthy concern. Unlike volumetric DDoS attacks that continuously send large volumes of traffic, LDDoS attacks are more stealthy and difficult to be detected owing to their low-volume feature. Due to its stealthiness and harmfulness, LDDoS has become one of the most destructive attacks in cloud computing. Although a few LDDoS attack detection and defense methods have been proposed, we observe that sophisticated LDDoS attacks (being more stealthy) can bypass some of the existing LDDoS defense methods. To verify our security observation, we proposed a new Feint-based LDDoS (F-LDDoS) attack strategy. In this strategy, we divide a Pulse Interval into a Feinting Interval and an Attack Interval. Unlike the previous LDDoS attacks, the bots also send traffic randomly in the Feinting Interval, thus disguise themselves as benign users during the F-LDDoS attack. In this way, although the victim detects that it is under an LDDoS attack, it is difficult to locate the attack sources and apply mitigation solutions. Experimental results show that F-LDDoS attack can degrade TCP bandwidth 6.7%-14% more than the baseline LDDoS attack. Besides, F-LDDoS also reduces the similarities between bot traffic and aggregated attack traffic, and increases the uncertainty of packet arrival. These results mean that the proposed F-LDDoS is more effective and more stealthy than normal LDDoS attacks. Finally, we discuss the countermeasures of F-LDDoS to draw the attention of defenders and improve the defense methods.

The links in many real networks are evolving with time. The task of dynamic link prediction is to use past connection histories to infer links of the network at a future time. How to effectively learn the temporal and structural pattern of the network dynamics is the key. In this paper, we propose a graph representation learning model based on enhanced structure and temporal information (GRL_EnSAT). For structural information, we exploit a combination of a graph attention network (GAT) and a self-attention network to capture structural neighborhood. For temporal dynamics, we use a masked self-attention network to capture the dynamics in the link evolution. In this way, GRL_EnSAT not only learns low-dimensional embedding vectors but also preserves the nonlinear dynamic feature of the evolving network. GRL_EnSAT is evaluated on four real datasets, in which GRL_EnSAT outperforms most advanced baselines. Benefiting from the dynamic self-attention mechanism, GRL_EnSAT yields better performance than approaches based on recursive graph evolution modeling.

With the widespread innovation of the Internet of Things, software-defined networking (SDN), and cloud computing, cyber-physical systems (CPSs) have been developed and widely adopted to facilitate our daily life and economy. In particular, modern society heavily relies on all kinds of CPSs, such as smart grids, and transportation systems. So the shutdown of critical services can lead to serious consequences. Meanwhile, distributed denial-of-service (DDoS) attacks are becoming a major threat to the CPSs due to their ease of execution and the devastation they cause. In addition, owing to the constant updating of attack methods, there is an urgent need for a method to defend against both the known and unknown DDoS attacks. In this article, we present an adaptive DDoS attack mitigation (ADAM) scheme to detect and mitigate DDoS attacks in software-defined CPSs. By combining information entropy and unsupervised anomaly detection methods, ADAM can not only automatically determine the current state, but also adaptively identify suspicious features and thereafter precisely mitigate DDoS attacks. We also propose a pipeline filtering mechanism to accurately drop attack traffic, and this method can be implemented in the existing SDN networks without additional devices required. Unlike most of the classification-based DDoS mitigation scenarios, we aim to mitigate a wide spectrum of DDoS attacks without defining attack characteristics in advance. Real data-driven experimental results show that ADAM has an average mitigation accuracy of 99.13% under high-intensity DDoS attacks. Compared to similar work, our method reduces the false-positive rate by 35%-59%.

The development of information gathering and extraction technology has led to the popularity of multi-view data, which enables samples to be seen from numerous perspectives. Multi-view clustering (MVC), which groups data samples by leveraging complementary and consensual information from several views, is gaining popularity. Despite the rapid evolution of MVC approaches, there has yet to be a study that provides a full MVC roadmap for both stimulating technical improvements and orienting research newbies to MVC. In this article, we review recent MVC techniques with the purpose of exhibiting the concepts of popular methodologies and their advancements. This survey not only serves as a unique MVC comprehensive knowledge for researchers but also has the potential to spark new ideas in MVC research. We summarise a large variety of current MVC approaches based on two technical mechanisms: heuristic-based multi-view clustering (HMVC) and neural network-based multi-view clustering (NNMVC). We end with four technological approaches within the category of HMVC: nonnegative matrix factorisation, graph learning, latent representation learning, and tensor learning. Deep representation learning and deep graph learning are two technical methods that we demonstrate in NNMVC. We also show 15 publicly available multi-view datasets and examine how representative MVC approaches perform on them. In addition, this study identifies the potential research directions that may require further investigation in order to enhance the further development of MVC.

Cascade prediction aims at modeling information diffusion in the network. Most previous methods concentrate on mining either structural or sequential features from the network and the propagation path. Recent efforts devoted to combining network structure and sequence features by graph neural networks and recurrent neural networks. Nevertheless, the limitation of spectral or spatial methods restricts the improvement of prediction performance. Moreover, recurrent neural networks are time-consuming and computation-expensive, which causes the inefficiency of prediction. Here, we propose a novel method CCasGNN considering the individual profile, structural features, and sequence information. The method benefits from using a collaborative framework of GAT and GCN and stacking positional encoding into the layers of graph neural networks, which is different from all existing ones and demonstrates good performance. The experiments conducted on two real-world datasets confirm that our method significantly improves the prediction accuracy compared to state-of-the-art approaches. Whats more, the ablation study investigates the contribution of each component in our method.

The prediction for information diffusion on social networks has great practical significance in marketing and public opinion control. It aims to predict the individuals who will potentially repost the message on the social network. One type of method is based on demographics, complex networks, and other prior knowledge to establish an interpretable model to simulate and predict the propagation process, while the other type of method is completely data-driven and maps the nodes to a latent space for propagation prediction. Existing latent space design and embedding methods lack consideration for the intervention among users. In this paper, we propose an independent asymmetric embedding method to embed each individual into one latent influence space and multiple latent susceptibility spaces. Based on the similarity between information diffusion and heat diffusion phenomenon, the heat diffusion kernel is exploited in our model and establishes the embedding rules. Furthermore, our method captures the co-occurrence regulation of user combinations in cascades to improve the calculating effectiveness. The results of extensive experiments conducted on real-world datasets verify both the predictive accuracy and cost-effectiveness of our approach.

Name ambiguity is common in academic digital libraries, such as multiple authors having the same name. This creates challenges for academic data management and analysis, thus name disambiguation becomes necessary. The procedure of name disambiguation is to divide publications with the same name into different groups, each group belonging to a unique author. A large amount of attribute information in publications makes traditional methods fall into the quagmire of feature selection. These methods always select attributes artificially and equally, which usually causes a negative impact on accuracy. The proposed method is mainly based on representation learning for heterogeneous networks and clustering and exploits the self-attention technology to solve the problem. The presentation of publications is a synthesis of structural and semantic representations. The structural representation is obtained by meta-path-based sampling and a skip-gram-based embedding method, and meta-path level attention is introduced to automatically learn the weight of each feature. The semantic representation is generated using NLP tools. Our proposal performs better in terms of name disambiguation accuracy compared with baselines and the ablation experiments demonstrate the improvement by feature selection and the meta-path level attention in our method. The experimental results show the superiority of our new method for capturing the most attributes from publications and reducing the impact of redundant information.

One important task in the study of information cascade is to predict the future recipients of a message given its past spreading trajectory. While the network structure serves as the backbone of the spreading, an accurate prediction can hardly be made without the knowledge of the dynamics on the network. The temporal information in the spreading sequence captures many hidden features, but predictions based on sequence alone have their limitations. Recent efforts start to explore the possibility of combining both the network structure and the temporal feature. Here, we propose a new end-to-end prediction method CasSeqGCN in which the structure and temporal feature are simultaneously taken into account. A cascade is divided into multiple snapshots which record the network topology and the state of nodes. The graph convolutional network (GCN) is used to learn the representation of a snapshot. A novel aggregation method based on dynamic routing is proposed to aggregate node representation and the long short-term memory (LSTM) model is used to extract temporal information. CasSeqGCN predicts the future cascade size more accurately compared with other state-of-art baseline methods. The ablation study demonstrates that the improvement mainly comes from the design of the input and the GCN layer. We explicitly design an experiment to show the quality of the cascade representation learned by our approach is better than other methods. Our work proposes a new approach to combine the structural and temporal features, which not only gives a useful baseline model for future studies of cascade prediction, but also brings new insights on a wide collection of problems related with dynamics on and of the network.