With the widespread adoption of large vision-language models, the capacity for color vision in these models is crucial. However, the color vision abilities of large visual-language models have not yet been thoroughly explored. To address this gap, we define a color vision testing task for large vision-language models and construct a dataset that covers multiple categories of test questions and tasks of varying difficulty levels. Furthermore, we analyze the types of errors made by large vision-language models and propose a chain-of-thought prompting strategy to enhance their performance in color vision tests.

In the drug discovery process, the low success rate of drug candidate screening often leads to insufficient labeled data, causing the few-shot learning problem in molecular property prediction. Existing methods for few-shot molecular property prediction overlook the sample selection bias, which arises from non-random sample selection in chemical experiments. This bias in data representativeness leads to suboptimal performance. To overcome this challenge, we present a novel method named Contextual Representation Anchor Network (CRANet), where an anchor refers to a cluster center of the representations of molecules and serves as a bridge to transfer enriched contextual knowledge into molecular representations and enhance their expressiveness. CRANet introduces a dual-augmentation mechanism that includes context augmentation, which dynamically retrieves analogous unlabeled molecules and captures their task-specific contextual knowledge to enhance the anchors, and anchor augmentation, which leverages the anchors to augment the molecular representations. We evaluate our approach using the MoleculeNet and FS-Mol benchmarks, as well as through domain transfer experiments. The outcomes indicate that CRANet surpasses current state-of-the-art methods by 0.10% to 5.48% in AUC and 2.52% in ΔAUC-PR metrics, showcasing its exceptional generalization abilities.

Denoising Diffusion Probabilistic Models (DDPMs) have recently demonstrated exceptional performance in generating high-quality data. In this work, we propose CommunityDF, a novel framework that applies DDPMs to the community search problem, which involves identifying subgraphs containing nodes closely related to a given query node. However, three key challenges arise in this context: (I) learning effective node representations from limited examples, (II) discretizing continuous node representations into community members, and (III) reducing the number of diffusion steps without sacrificing performance. To tackle these, CommunityDF introduces several innovations. First, we focus on subgraphs around the query node to reduce interference from unrelated nodes, improve scalability. We then employ a contrastive learning approach, treating node states at different diffusion steps as positive examples and designing various negative sampling strategies to learn high-quality node representations from limited examples. Second, we propose a dynamic thresholding mechanism that effectively converts continuous representations into community members. Finally, we reduce the number of diffusion steps by leveraging the rough communities to initialize the process with rough community structures, which accelerates convergence while maintaining high accuracy. Extensive experiments on seven real-world datasets demonstrate that CommunityDF outperforms existing methods by 16%-47%, establishing it as a state-of-the-art solution for community search. The source code is available at https://github.com/JiazunChen/CommunityDF.

Time series anomaly detection aims to identify unusual patterns in data or deviations from systems' expected behavior. The reconstruction-based methods are the mainstream in this task, which learn point-wise representation via unsupervised learning. However, the unlabeled anomaly points in training data may cause these reconstruction-based methods to learn and reconstruct anomalous data, resulting in the challenge of capturing normal patterns. In this paper, we propose a time series anomaly detection method based on implicit neural representation (INR) reconstruction, named TSINR, to address this challenge. Due to the property of spectral bias, TSINR enables prioritizing low-frequency signals and exhibiting poorer performance on high-frequency abnormal data. Specifically, we adopt INR to parameterize time series data as a continuous function and employ a transformer-based architecture to predict the INR of given data. As a result, the proposed TSINR method achieves the advantage of capturing the temporal continuity and thus is more sensitive to discontinuous anomaly data. In addition, we further design a novel form of INR continuous function to learn inter- and intra-channel information, and leverage a pre-trained large language model to amplify the intense fluctuations in anomalies. Extensive experiments demonstrate that TSINR achieves superior overall performance on both univariate and multivariate time series anomaly detection benchmarks compared to other state-of-the-art reconstruction-based methods. Our codes are available here.

Effective molecular representation learning is crucial for advancing molecular property prediction and drug design. Mainstream molecular representation learning methods rely on Graph Neural Networks (GNNs) to model complex molecular structures. However, these GNN-based approaches struggle with three significant issues: insufficient annotations, molecular diversity, and architectural limitations such as over-squashing, which leads to the loss of critical structural details. To address these issues, we introduce a new class of GNNs that integrates the Kolmogorov-Arnold Networks (KANs), known for their robust data-fitting capabilities and high accuracy in small-scale AI + Science tasks. By incorporating KANs into GNNs, our model enhances the representation of molecular structures. We further advance this approach with a variant called SwallowKAN (SKAN), which employs adaptive Radial Basis Functions (RBFs) as the core of the non-linear neurons. This innovation improves both computational efficiency and adaptability to diverse molecular structures. Building on the strengths of SKAN, we propose a new class of GNNs, GNN-SKAN, and its augmented variant, GNN-SKAN+, which incorporates a SKAN-based classifier to further boost the performance. Experiments across 6 classification datasets, 6 regression datasets, and 4 few-shot learning datasets demonstrate that our approach achieves new state-of-the-art performance in terms of accuracy and computational cost.

In recent years, there has been a surge in research on dynamic graph representation learning, primarily focusing on modeling the evolution of temporal-spatial patterns in real-world applications. However, within the domain of discrete-time dynamic graphs, the exploration of temporal edges remains underexplored. Existing approaches often rely on additional sequential models to capture dynamics, leading to high computational and memory costs, particularly for large-scale graphs. To address this limitation, we propose the Input Snapshots Fusion based Dynamic Graph Neural Network (SFDyG), which combines Hawkes processes with graph neural networks to capture temporal and structural patterns in dynamic graphs effectively. By fusing multiple snapshots into a single temporal graph, SFDyG decouples computational complexity from the number of snapshots, enabling efficient full-batch and mini-batch training. Experimental evaluations on eight diverse dynamic graph datasets for future link prediction tasks demonstrate that SFDyG consistently outperforms existing methods.

Recently, graph neural networks (GNNs) have demonstrated outstanding performance in fundamental tasks such as node classification and link prediction, as well as in specialized domains like recommendation systems, fraud detection, and drug discovery. However, their vulnerability to adversarial attacks raises concerns about their reliability in security-critical areas. To address this issue, researchers are exploring various defense methods, including specific attack countermeasures and certifiable robustness approaches. Nevertheless, these strategies are often effective only against limited attack scenarios, and prevailing certification methods prove inadequate when confronted with injection attacks. In this paper, we propose a method named CERT_UIA to enhance the robustness of GNN models against worst-case attacks, specifically targeting the scenario of Universal node Injection Attacks (UIA), thereby filling a gap in the existing literature on certified robustness in this context. Our approach involves a two-stage attack process that replaces the transformations of the topology and feature spaces with equivalent unified feature transformations, unifying the optimization of worst-case perturbations into a single feature space. Furthermore, we empirically evaluate our method on several benchmark datasets and compare it with existing certified methods.

The recent prosperity of temporal graph research redefines many traditional concepts on static graphs, such as triangle, motif,$k$-core, etc. Inspired by that, we propose a novel$(k, \delta)$-truss on temporal graphs, which requires its triangles to exist in short enough time windows ever. The$(k,\delta)$-truss satisfies both static and temporal cohesion, while the original$k$-truss is its special case when$\delta=\infty$. In order to address the$(k, \delta)$-truss query, we propose both index-free and index-based approaches. By leveraging the dual containment relation on$(k, \delta)$-trusses, our indexes can compress all$(k, \delta)$-trusses losslessly into map or tree structures with dramatically less space, so that a specific$(k,\ \delta)$-truss can be retrieved from indexes in the optimal time. To enable our index to scale to large temporal graphs, we develop two index construction algorithms that can reduce redundant computation significantly, based on truss decomposition and truss maintenance respectively. The experimental results demonstrate that index-based approaches process queries in interactive time and outperform the index-free approach by 2~4 orders of magnitude, while indexes achieve compression ratios up to 10-4.

Self-supervised learning (SSL) has become one of the most popular learning paradigms and has achieved remarkable success in the graph field. Recently, a series of pre-training studies on heterogeneous graphs (HGs) using SSL have been proposed considering the heterogeneity of real-world graph data. However, verification of the robustness of heterogeneous graph pre-training is still a research gap. Most existing researches focus on supervised attacks on graphs, which are limited to a specific scenario and will not work when labels are not available. In this paper, we propose a novel unsupervised heterogeneous graph rewriting attack via node clustering (HGAC) that can effectively attack HG pre-training models without using labels. Specifically, a heterogeneous edge rewriting strategy is designed to ensure the rationality and concealment of the attacks. Then, a tailored heterogeneous graph contrastive learning (HGCL) is used as a surrogate model. Moreover, we leverage node clustering results of the clean HGs as the pseudo-labels to guide the optimization of structural attacks. Extensive experiments exhibit powerful attack performances of our HGAC on various downstream tasks (i.e., node classification, node clustering, metapath prediction, and visualization) under poisoning attack and evasion attack.

Spatiotemporal traffic forecasting plays a critical role in intelligent transportation systems, which empowers diverse urban services. Existing traffic forecasting frameworks usually devise various learning strategies to capture spatiotemporal correlations from the perspective of volume itself. However, we argue that previous traffic predictions are still unreliable due to two aspects. First, the influences of context factor-wise interactions on dynamic region-wise correlations are under exploitation. Second, the dynamics induce the credibility issue of forecasting that has not been well-explored. In this paper, we exploit the informative traffic-related context factors to jointly tackle the dynamic regional heterogeneity and explain the stochasticity, towards a credible uncertainty-aware traffic forecasting. Specifically, to internalize the dynamic contextual influences into learning process, we design a context-cross relational embedding to capture interactions between each context, and generate virtual graph topology to dynamically relate pairwise regions with context embedding. To quantify the prediction credibility, we attribute data-side aleatoric uncertainty to contexts and re-utilize them for aleatoric uncertainty quantification. Then we couple a dual-pipeline learning with the same objective to produce the discrepancy of model outputs and quantify model-side epistemic uncertainty. These two uncertainties are fed through a spatiotemporal network for extracting uncertainty evolution patterns. Finally, comprehensive experiments and model deployments have corroborated the credibility of our framework.

Unsupervised Graph Domain Adaptation (UGDA) has emerged as a practical solution to transfer knowledge from a label-rich source graph to a completely unlabelled target graph. However, most methods require a labelled source graph to provide supervision signals, which might not be accessible in the real-world settings due to regulations and privacy concerns. In this paper, we explore the scenario of source-free unsupervised graph domain adaptation, which tries to address the domain adaptation problem without accessing the labelled source graph. Specifically, we present a novel paradigm called GraphCTA, which performs model adaptation and graph adaptation collaboratively through a series of procedures: (1) conduct model adaptation based on node's neighborhood predictions in target graph considering both local and global information; (2) perform graph adaptation by updating graph structure and node attributes via neighborhood contrastive learning; and (3) the updated graph serves as an input to facilitate the subsequent iteration of model adaptation, thereby establishing a collaborative loop between model adaptation and graph adaptation. Comprehensive experiments are conducted on various public datasets. The experimental results demonstrate that our proposed model outperforms recent source-free baselines by large margins.

Effective resistance (ER) is a fundamental metric for measuring node similarities in a graph, and it finds applications in various domains including graph clustering, recommendation systems, link prediction, and graph neural networks. The state-of-the-art algorithm for computing effective resistance relies on a landmark technique, which involves selecting a node that is easy to reach by all the other nodes as a landmark. The performance of this technique heavily depends on the chosen landmark node. However, in many real-life graphs, it is not always possible to find an easily reachable landmark node, which can significantly hinder the algorithm's efficiency. To overcome this problem, we propose a novel multiple landmarks technique which involves selecting a set of landmark nodes V l such that the other nodes in the graph can easily reach any one of a landmark node in V l . Specifically, we first propose several new formulas to compute ER with multiple landmarks, utilizing the concept of Schur complement. These new formulas allow us to pre-compute and maintain several small-sized matrices related to V l as a compact index. With this powerful index technique, we demonstrate that both single-pair and single-source ER queries can be efficiently answered using a newly-developed V l -absorbed random walk sampling or V l -absorbed push technique. Comprehensive theoretical analysis shows that all proposed index-based algorithms achieve provable performance guarantees for both single-pair and single-source ER queries. Extensive experiments on 5 real-life datasets demonstrate the high efficiency of our multiple landmarks-based index techniques. For instance, our algorithms, with a 1.5 GB index size, can be up to 4 orders of magnitude faster than the state-of-the-art algorithms while achieving the same accuracy on a large road network.

Being the most cutting-edge generative methods, diffusion methods have shown great advances in wide generation tasks. Among them, graph generation attracts significant research attention for its broad application in real life. In our survey, we systematically and comprehensively review on diffusion-based graph generative methods. We first make a review on three mainstream paradigms of diffusion methods, which are denoising diffusion probabilistic models, score-based genrative models, and stochastic differential equations. Then we further categorize and introduce the latest applications of diffusion models on graphs. In the end, we point out some limitations of current studies and future directions of future explorations.

Graph pooling technique as the essential component of graph neural networks has gotten increasing attention recently and it aims to learn graph-level representations for the whole graph. Besides, graph pooling is important in graph classification and graph generation tasks. However, current graph pooling methods mainly coarsen a sequence of small-sized graphs to capture hierarchical structures, potentially resulting in the deterioration of the global structure of the original graph and influencing the quality of graph representations. Furthermore, these methods artificially select the number of graph pooling layers for different graph datasets rather than considering each graph individually. In reality, the structure and size differences among graphs necessitate a specific number of graph pooling layers for each graph. In this work, we propose reinforced pooling graph neural networks via adaptive hybrid graph coarsening networks. Specifically, we design a hybrid graph coarsening strategy to coarsen redundant structures of the original graph while retaining the global structure. In addition, we introduce multi-agent reinforcement learning to adaptively perform the graph coarsening process to extract the most representative coarsened graph for each graph, enhancing the quality of graph-level representations. Finally, we design graph-level contrast to improve the preservation of global information in graph-level representations. Extensive experiments with rich baselines on six benchmark datasets show the effectiveness of ReiPool1.

Recently, ChatGPT, a representative large language model (LLM), has gained considerable attention. Due to their powerful emergent abilities, recent LLMs are considered as a possible alternative to structured knowledge bases like knowledge graphs (KGs). However, while LLMs are proficient at learning probabilistic language patterns and engaging in conversations with humans, they, like previous smaller pre-trained language models (PLMs), still have difficulty in recalling facts while generating knowledge-grounded contents. To overcome these limitations, researchers have proposed enhancing data-driven PLMs with knowledge-based KGs to incorporate explicit factual knowledge into PLMs, thus improving their performance in generating texts requiring factual knowledge and providing more informed responses to user queries. This paper reviews the studies on enhancing PLMs with KGs, detailing existing knowledge graph enhanced pre-trained language models (KGPLMs) as well as their applications. Inspired by existing studies on KGPLM, this paper proposes enhancing LLMs with KGs by developing knowledge graph-enhanced large language models (KGLLMs). KGLLM provides a solution to enhance LLMs’ factual reasoning ability, opening up new avenues for LLM research.

Meta-learning methods have shown to be effective in dealing with cold-start recommendation. However, most previous methods rely on an ideal assumption that there exists a similar data distribution between source and target tasks, which are unsuitable for the scenario that only extremely limited number of new user or item interactions are available. In this paper, we propose to boost meta-learning cold-start recommendation with graph neural network (MeGNN). First, it utilizes the global neighborhood translation learning to obtain consistent potential interactions for all new user and item nodes, which can refine their representations. Second, it employs the local neighborhood translation learning to predict specific potential interactions for each node, thus guaranteeing the personalized requirement. In experiments, we combine MeGNN with two representative meta-learning models MeLU and TaNP. Extensive results on two widely-used datasets show the superiority of MeGNN in four different scenarios.

Both Transformer and Graph Neural Networks (GNNs) have been used in learning to rank (LTR), they however adhere to two distinct-yet-complementary problem formulations, i.e., ranking score regression based on query-webpage pairs and link prediction within query-webpage bipartite graphs, respectively. Though it is possible to pre-train GNNs or Transformers on source datasets and fine-tune them subject to sparsely annotated LTR datasets separately, the source-target distribution shifts across the pairs and bipartite graphs domains make it extremely difficult to integrate these diverse models into a single LTR framework at a web-scale. We introduce the novel MPGraf model, which utilizes a modular and capsule-based pre-training approach, aiming to incorporate regression capacities from Transformers and link prediction capabilities of GNNs cohesively. Specifically, rather than simply combining these two modules in stacking or parallelizing architectures, MPGraf proposes a three-step method to (1) construct query-webpage graphs from sparsely annotated query-webpage pairs, (2) pre-train the Transformer and GNN modules using source datasets from two domains, and (3) “surgically” fine-tune the integrated models with pretrained weights while handling the distribution shifts of two domains. Extensive experiments have been done to evaluate the performance of MPGraf using real-world datasets collected from large-scale search engines. The results show that MPGraf can outperform baseline algorithms on several major metrics. Further, we deploy and evaluate MPGraf atop a large-scale search engine with realistic web traffics via A/B tests, where we can still observe significant improvement. MPGraf performs consistently in both offline and online evaluations.

Root cause analysis for multi-dimensional time series from large scale micro-service scenarios aims at identifying the set of anomaly attributes by monitoring operational metrics. The online metrics provide a general indication to investigate these attributes' inter-dependencies and can guide the overall exploration process. However, the problem space for the root cause localization still remains largely challenging due to the combinatorial explosion of possible attribute combinations. This leads researchers and practitioners to (a) assume some prior distributions on the data set; (b) assume some data patterns on the attribute combinations; (c) perform pruning techniques to reduce the search space. Furthermore, state-of-the-art root cause analysis methods are often tied to one or more of these assumptions, which makes it difficult to be robust to general scenarios. In this paper, we conclude the heterogeneity in the data patterns by analyzing several open and industrial datasets. A uniform analytical framework, PatternRCA, is proposed such that it can be aware of the patterns in the metrics while avoiding explicit assumptions about them. We design an offline learning procedure that enables the framework to detect existing data patterns, which then can guide it to do fine-grain exploration in online metrics. Our extensive evaluation results show that PatternRCA outperforms state-of-the-art models with better benchmark results in public datasets. Meanwhile, it can scale to complex root cause analysis tasks on datasets with hybrid patterns in production environments.

Decision-focused learning (DFL) combines both machine learning and combinatorial optimization so as to enhance the quality of decision-making. In general, DFL adds an optimization layer after the neural network and solves a focused combinatorial optimization problem. The optimization layer is usually based on KKT conditions or surrogate functions. However, the optimizer associated with the DFL is inflexible and requires a large amount of expert knowledge. Furthermore, it has been shown that the optimizer exhibits a lack of robustness and differentiability when confronted with complex tasks, especially in the graph domain. To solve this problem, we study a more generic situation by taking the optimization layer as a black-box operator on graphs. Then, we design a mixed zeroth-order optimization to differentiate the layer. Specifically, we combine DFL with graph neural networks and present a decision-focused graph neural network named ZO4Graph based on a mixed zeroth-order optimizer. Empirically, we conduct extensive experiments compared with two-stage models on community detection. Numerical results demonstrate that our proposed framework outperforms its peers.

Anomaly detection in multi-type event sequences is a crucial and challenging problem with important applications in various domains, including cybersecurity, finance and healthcare. Temporal point process has emerged as a powerful technique for modeling event sequences and has gained considerable attention in the field of anomaly detection. However, existing temporal point process approaches are either inapplicable to multi-type event sequence data or incur the loss of valuable information in subsequences associated with specific event types. To this end, we propose a novel Multiple Hypothesis Testing based Anomaly Detection method (MultiAD) to detect anomalous multi-type event sequences. The basic idea of MultiAD is to capture the underlying distribution of normal sequences using a neural multivariate point process, based on which the original hypothesis testing problem can be converted into a multiple hypothesis testing using the multivariate time rescaling theorem. By conducting multiple hypothesis tests on the time-rescaled subsequences, MultiAD makes full use of the valuable information contained within individual subsequences. Moreover, we claim that the existing test statistic ignores the sequential information of inter-event time intervals and propose new statistics to address this shortcoming. Finally, we employ the kernel method to obtain a smooth estimator of the distribution of the proposed statistics under the null hypothesis. This ensures a more accurate and reliable computation of the p-value, providing robust statistical inference. Extensive experimental results demonstrate that MultiAD significantly outperforms the state-of-the-art methods on both synthetic and real-world data.

We study the task of spatio-temporal extrapolation that generates data at target locations from surrounding contexts in a graph. This task is crucial as sensors that collect data are sparsely deployed, resulting in a lack of fine-grained information due to high deployment and maintenance costs. Existing methods either use learning-based models like Neural Networks or statistical approaches like Gaussian Processes for this task. However, the former lacks uncertainty estimates and the latter fails to capture complex spatial and temporal correlations effectively. To address these issues, we propose Spatio-Temporal Graph Neural Processes (STGNP), a neural latent variable model which commands these capabilities simultaneously. Specifically, we first learn deterministic spatio-temporal representations by stacking layers of causal convolutions and cross-set graph neural networks. Then, we learn latent variables for target locations through vertical latent state transitions along layers and obtain extrapolations. Importantly during the transitions, we propose Graph Bayesian Aggregation (GBA), a Bayesian graph aggregator that aggregates contexts considering uncertainties in context data and graph structure. Extensive experiments show that STGNP has desirable properties such as uncertainty estimates and strong learning capabilities, and achieves state-of-the-art results by a clear margin.

Graph neural networks (GNNs) are powerful models to handle graph data and can achieve state-of-the-art in many critical tasks including node classification and link prediction. However, existing graph neural networks still face both challenges of over-smoothing and over-squashing based on previous literature. To this end, we propose a new Curvature-based topology-aware Dropout sampling technique named CurvDrop, in which we integrate the Discrete Ricci Curvature into graph neural networks to enable more expressive graph models. Also, this work can improve graph neural networks by quantifying connections in graphs and using structural information such as community structures in graphs. As a result, our method can tackle the both challenges of over-smoothing and over-squashing with theoretical justification. Also, numerous experiments on public datasets show the effectiveness and robustness of our proposed method. The code and data are released in https://github.com/liu-yang-maker/Curvature-based-Dropout.

Resistance distance is a fundamental metric to measure the similarity between two nodes in graphs which has been widely used in many real-world applications. In this paper, we study two problems on approximately computing resistance distance: (i) single-pair query which aims at calculating the resistance distance r(s, t) for a given pair of nodes (s, t); and (ii) single-source query which is to compute all the resistance distances r(s, u) for all nodes u in the graph with a given source node s. Existing algorithms for these two resistance distance query problems are often costly on large graphs. To efficiently solve these problems, we first establish several interesting connections among resistance distance, a new concept called v-absorbed random walk, random spanning forests, and a newly-developed v-absorbed push procedure. Based on such new connections, we propose three novel and efficient sampling-based algorithms as well as a deterministic algorithm for single-pair query; and we develop an online and two index-based approximation algorithms for single-source query. We show that the two index-based algorithms for single-source query take almost the same running time as the algorithms for single-pair query with the aid of a linear-size index. The striking feature of all our algorithms is that they are allowed to select an easy-to-hit node by random walks on the graph. Such an easy-to-hit landmark node v can make the v-absorbed random walk sampling, spanning tree sampling, as well as the v-absorbed push more efficient, thus significantly improving the performance of our algorithms. Extensive experiments on 5 real-life datasets show that our algorithms substantially outperform the state-of-the-art algorithms for two resistance distance query problems in terms of both running time and estimation errors.

Personalized PageRank (PPR) computation is a fundamental problem in graph analysis. The state-of-the-art algorithms for PPR computation are based on a bidirectional framework which include a deterministic forward push and a Monte Carlo sampling procedure. The Monte Carlo sampling procedure, however, often has a relatively-large variance, thus reducing the performance of the PPR computation algorithms. To overcome this issue, we develop two novel variance-reduced Monte Carlo techniques for PPR computation. Our first technique is to apply power iterations to reduce the variance of the Monte Carlo sampling procedure. We prove that conducting few power iterations can significantly reduce the variance of existing Monte Carlo estimators, only with few additional costs. Moreover, we show that such a simple and novel variance-reduced Monte Carlo technique can achieve comparable estimation accuracy and the same time complexity as the state-of-the-art bidirectional algorithms. Our second technique is a novel progressive sampling method which uses the historical information of former samples to reduce the variance of the Monte Carlo estimator. We develop several novel PPR computation algorithms by integrating both of these variance reduction techniques with two existing Monte Carlo sampling approaches, including random walk sampling and spanning forests sampling. Finally, we conduct extensive experiments on 5 real-life large graphs to evaluate our solutions. The results show that our algorithms can achieve much higher PPR estimation accuracy by using much less time, compared to the state-of-the-art bidirectional algorithms.

Spatio-temporal forecasting has a wide range of applications in smart city efforts, such as traffic forecasting and air quality prediction. Graph Convolutional Recurrent Neural Networks (GCRNN) are the state-of-the-art methods for this problem, which learn temporal dependencies by RNNs and exploit pairwise node proximity to model spatial dependencies. However, the spatial relations in real data are not simply pairwise but sometimes in a higher order among multiple nodes. Moreover, spatio-temporal sequences deriving from nature are often regulated by known or unknown physical laws. GCRNNs rarely take into account the underlying physics in real-world systems, which may result in degenerated performance. To address these issues, we devise a general model called Mixed-Order Relation-Aware RNN (MixRNN+) for spatio-temporal forecasting. Specifically, our MixRNN+ captures the complex mixed-order spatial relations of nodes through a newly proposed building block called Mixer, and simultaneously addressing the underlying physics by the integration of a new residual update strategy. Experimental results on three forecasting tasks in smart city applications (including traffic speed, taxi flow, and air quality prediction) demonstrate the superiority of our model against the state-of-the-art methods. We have also deployed a cloud-based system using our method as the bedrock model to show its practicality.

Modern sociology has profoundly uncovered many convincing social criteria for behavioral analysis. Unfortunately, many of them are too subjective to be measured and very challenging to be presented in online social networks (OSNs) for the large data volume and complicated environments to be explored. On the other hand, data mining techniques can better find data patterns but many of them leave behind unnatural understanding to humans. Although there are some works trying to integrate social observations for specific tasks, they are still hard to be applied to more general cases. In this paper, we propose a fundamental methodology to support the further fusion of data mining techniques and sociological behavioral criteria. Our highlights are three-fold: First, we propose an effective hypergraph awareness and a fast line graph construction framework. The hypergraph can more profoundly indicate the interactions between individuals and their environments because each edge in the hypergraph (a.k.a hyperedge) contains more than two nodes, which is perfect to describe social. A line graph treats each social environment as a super node with the underlying influence between different environments. In this way, we go beyond traditional pair-wise relations and explore richer patterns under various sociological criteria; Second, we propose a novel hypergraph-based neural network to learn social influence flowing from users to users, users to environments, environment to users, and environments to environments. The neural network can be learned via a task-free method, making our model very flexible to support various data mining tasks and sociological analysis; Third, we propose both qualitative and quantitive solutions to effectively evaluate the most common sociological criteria like social conformity, social equivalence, environmental evolving and social polarization. Our extensive experiments show that our framework can better support both data mining tasks for online user behaviors and sociological analysis.

Transformers have been an efficient alternative to recurrent neural networks in many sequential learning tasks. When adapting transformers to modeling trajectories, we encounter two major issues. First, being originally designed for language modeling, transformers assume regular intervals between input tokens, which contradicts the irregularity of trajectories. Second, transformers often suffer high computational costs, especially for long trajectories. In this paper, we address these challenges by presenting a novel transformer architecture entitled TrajFormer. Our model first generates continuous point embeddings by jointly considering the input features and the information of spatio-temporal intervals, and then adopts a squeeze function to speed up the representation learning. Moreover, we introduce an auxiliary loss to ease the training of transformers using the supervision signals provided by all output tokens. Extensive experiments verify that our TrajFormer achieves a preferable speed-accuracy balance compared to existing approaches.

Data visualization is a powerful tool for understating information through visual cues. However, allowing novices to create visualization artifacts for what they want to see is not easy, just as not everyone can write SQL queries. Arguably, the most natural way to specify what to visualize is through natural language or speech, similar to our daily search on Google or Apple Siri, leaving to the system the task of reasoning about what to visualize and how.