Extreme events frequently occur in real-world time series and often carry significant practical implications. In domains such as climate and healthcare, these events, such as floods, heatwaves, or acute medical episodes, can lead to serious consequences. Accurate forecasting of such events is therefore of substantial importance. Most existing time series forecasting models are optimized for overall performance within the prediction window, but often struggle to accurately predict extreme events, such as high temperatures or heart rate spikes. The main challenges are data imbalance and the neglect of valuable information contained in intermediate events that precede extreme events. In this paper, we propose xTime, a novel framework for extreme event forecasting in time series. xTime leverages knowledge distillation to transfer information from models trained on lower-rarity events, thereby improving prediction performance on rarer ones. In addition, we introduce a MoE mechanism that dynamically selects and fuses outputs from expert models across different rarity levels, which further improves the forecasting performance for extreme events. Experiments on multiple datasets show that xTime achieves consistent improvements, with forecasting accuracy on extreme events improving from 3% to 78%.

Multi-modal time series analysis has recently emerged as a prominent research area, driven by the increasing availability of diverse data modalities, such as text, images, and structured tabular data from real-world sources. However, effective analysis of multi-modal time series is hindered by data heterogeneity, modality gap, misalignment, and inherent noise. Recent advancements in multi-modal time series methods have exploited the multi-modal context via cross-modal interactions based on deep learning methods, significantly enhancing various downstream tasks. In this tutorial and survey, we present a systematic and up-to-date overview of multi-modal time series datasets and methods. We first state the existing challenges of multi-modal time series analysis and our motivations, with a brief introduction of preliminaries. Then, we summarize the general pipeline and categorize existing methods through a unified cross-modal interaction framework encompassing fusion, alignment, and transference at different levels (i.e., input, intermediate, output), where key concepts and ideas are highlighted. We also discuss the real-world applications of multi-modal analysis for both standard and spatial time series, tailored to general and specific domains. Finally, we discuss future research directions to help practitioners explore and exploit multi-modal time series. The up-to-date resources are provided in the GitHub repository. https://github.com/UConn-DSIS/Multi-modal-Time-Series-Analysis.

Achieving carbon neutrality within industrial operations has become increasingly imperative for sustainable development. It is both a significant challenge and a key opportunity for operational optimization in industry 4.0. In recent years, Deep Reinforcement Learning (DRL) based methods offer promising enhancements for sequential optimization processes and can be used for reducing carbon emissions. However, existing DRL methods need a pre-defined reward function to assess the impact of each action on the final sustainable development goals (SDG). In many real applications, such a reward function cannot be given in advance. To address the problem, this study proposes a Performance based Adversarial Imitation Learning (PAIL) engine. It is a novel method to acquire optimal operational policies for carbon neutrality without any pre-defined action rewards. Specifically, PAIL employs a Transformer-based policy generator to encode historical information and predict following actions within a multi-dimensional space. The entire action sequence will be iteratively updated by an environmental simulator. Then PAIL uses a discriminator to minimize the discrepancy between generated sequences and real-world samples of high SDG. In parallel, a Q-learning framework based performance estimator is designed to estimate the impact of each action on SDG. Based on these estimations, PAIL refines generated policies with the rewards from both discriminator and performance estimator. PAIL is evaluated on multiple real-world application cases and datasets. The experiment results demonstrate the effectiveness of PAIL comparing to other state-of-the-art baselines. In addition, PAIL offers meaningful interpretability for the optimization in carbon neutrality.

Imitation learning, which learns agent policy by mimicking expert demonstration, has shown promising results in many applications such as medical treatment regimes and self-driving vehicles. However, it remains a difficult task to interpret control policies learned by the agent. Difficulties mainly come from two aspects: 1) agents in imitation learning are usually implemented as deep neural networks, which are black-box models and lack interpretability; 2) the latent causal mechanism behind agents' decisions may vary along the trajectory, rather than staying static throughout time steps. To increase transparency and offer better interpretability of the neural agent, we propose to expose its captured knowledge in the form of a directed acyclic causal graph, with nodes being action and state variables and edges denoting the causal relations behind predictions. Furthermore, we design this causal discovery process to be state-dependent, enabling it to model the dynamics in latent causal graphs. Concretely, we conduct causal discovery from the perspective of Granger causality and propose a self-explainable imitation learning framework, CAIL. The proposed framework is composed of three parts: a dynamic causal discovery module, a causality encoding module, and a prediction module, and is trained in an end-to-end manner. After the model is learned, we can obtain causal relations among states and action variables behind its decisions, exposing policies learned by it. Experimental results on both synthetic and real-world datasets demonstrate the effectiveness of the proposed CAIL in learning the dynamic causal graphs for understanding the decision-making of imitation learning meanwhile maintaining high prediction accuracy.

Imitation learning that replicates experts' skills via their demonstrations has shown significant success in various decision-making tasks. However, two critical challenges still hinder the deployment of imitation learning techniques in real-world application scenarios. First, existing methods lack the intrinsic interpretability to explicitly explain the underlying rationale of the learned skill and thus making learned policy untrustworthy. Second, due to the scarcity of expert demonstrations from each end user (client), learning a policy based on different data silos is necessary but challenging in privacy-sensitive applications such as finance and healthcare. To this end, we present a privacy-preserved interpretable skill learning framework (FedSkill) that enables global policy learning to incorporate data from different sources and provides explainable interpretations to each local user without violating privacy and data sovereignty. Specifically, our proposed interpretable skill learning model can capture the varying patterns in the trajectories of expert demonstrations, and extract prototypical information as skills that provide implicit guidance for policy learning and explicit explanations in the reasoning process. Moreover, we design a novel aggregation mechanism coupled with the based skill learning model to preserve global information utilization and maintain local interpretability under the federated framework. Thoroughly experiments on three datasets and empirical studies demonstrate that our proposed FedSkill framework not only outperforms state-of-the-art imitation learning methods but also exhibits good interpretability under a federated setting. Our proposed FedSkill framework is the first attempt to bridge the gaps among federated learning, interpretable machine learning, and imitation learning.

Imitation learning has achieved great success in many sequential decision-making tasks, in which a neural agent is learned by imitating collected human demonstrations. However, existing algorithms typically require a large number of high-quality demonstrations that are difficult and expensive to collect. Usually, a trade-off needs to be made between demonstration quality and quantity in practice. Targeting this problem, in this work we consider the imitation of sub-optimal demonstrations, with both a small clean demonstration set and a large noisy set. Some pioneering works have been proposed, but they suffer from many limitations, e.g., assuming a demonstration to be of the same optimality throughout time steps and failing to provide any interpretation w.r.t knowledge learned from the noisy set. Addressing these problems, we propose \method by evaluating and imitating at the sub-demonstration level, encoding action primitives of varying quality into different skills. Concretely, SDIL consists of a high-level controller to discover skills and a skill-conditioned module to capture action-taking policies, and is trained following a two-phase pipeline by first discovering skills with all demonstrations and then adapting the controller to only the clean set. A mutual-information-based regularization and a dynamic sub-demonstration optimality estimator are designed to promote disentanglement in the skill space. Extensive experiments are conducted over two gym environments and a real-world healthcare dataset to demonstrate the superiority of SDIL in learning from sub-optimal demonstrations and its improved interpretability by examining learned skills.

Personalized Federated Learning (PFL) which collaboratively trains a federated model while considering local clients under privacy constraints has attracted much attention. Despite its popularity, it has been observed that existing PFL approaches result in sub-optimal solutions when the joint distribution among local clients diverges. To address this issue, we present Federated Modular Network (FedMN), a novel PFL approach that adaptively selects sub-modules from a module pool to assemble heterogeneous neural architectures for different clients. FedMN adopts a light-weighted routing hypernetwork to model the joint distribution on each client and produce the personalized selection of the module blocks for each client. To reduce the communication burden in existing FL, we develop an efficient way to interact between the clients and the server. We conduct extensive experiments on the real-world test beds and the results show both effectiveness and efficiency of the proposed FedMN over the baselines.

Point-of-interest (POI) recommendation is an emerging area of research on location-based social networks to analyze user behaviors and contextual check-in information. For this problem, existing approaches, with shallow or deep architectures, have two major drawbacks. First, for these approaches, the attributes of individuals have been largely ignored. Therefore, it would be hard, if not impossible, to gather sufficient user attribute features to have complete coverage of possible motivation factors. Second, most existing models preserve the information of users or POIs by latent representations without explicitly highlighting salient factors or signals. Consequently, the trained models with unjustifiable parameters provide few persuasive rationales to explain why users favor or dislike certain POIs and what really causes a visit. To overcome these drawbacks, we propose GEAPR, a POI recommender that is able to interpret the POI prediction in an end-to-end fashion. Specifically, GEAPR learns user representations by aggregating different factors, such as structural context, neighbor impact, user attributes, and geolocation influence. GEAPR takes advantage of a triple attention mechanism to quantify the influences of different factors for each resulting recommendation and performs a thorough analysis of the model interpretability. Extensive experiments on real-world datasets demonstrate the effectiveness of the proposed model. GEAPR is deployed and under test on an internal web server. An example interface is presented to showcase its application on explainable POI recommendation.

Aspect-based sentiment classification aims to predict sentimental polarities of one or multiple aspects in texts. As texts always contain a large proportion of task-irrelevant words, accurate alignment between aspects and their sentimental descriptions is the most crucial and challenging step. State-of-the-art approaches are mainly based on word-level attention learned from recurrent neural network variants (e.g., LSTM) or graph neural networks. From another view, these methods essentially weight and aggregate all possible alignments. However, this mechanism heavily relies on large-scale supervision training: without enough labels, it could easily overfit with difficulty in generalization. To address this challenge, we propose SentRL, a reinforcement learning-based framework for aspect-based sentiment classification. In this framework, input texts are transformed into their dependency graphs. Then, an agent is deployed to walk on the graphs, explores paths from target aspect nodes to their potential sentimental regions, and differentiates the effectiveness of different paths. By limiting the agent’s exploration budget, our method encourages the agent to skip task-irrelevant information and focus on the most effective paths for alignment purpose. Our method considerably reduces the impact of task-irrelevant words and improves generalization performance. Compared with competitive baseline methods, our approach achieves the highest performance on public benchmark datasets with up to 3.7% improvement.

Graph Neural Networks (GNNs) have shown to be powerful tools for graph analytics. The key idea is to recursively propagate and aggregate information along the edges of the given graph. Despite their success, however, the existing GNNs are usually sensitive to the quality of the input graph. Real-world graphs are often noisy and contain task-irrelevant edges, which may lead to suboptimal generalization performance in the learned GNN models. In this paper, we propose PTDNet, a parameterized topological denoising network, to improve the robustness and generalization performance of GNNs by learning to drop task-irrelevant edges. PTDNet prunes task-irrelevant edges by penalizing the number of edges in the sparsified graph with parameterized networks. To take into consideration the topology of the entire graph, the nuclear norm regularization is applied to impose the low-rank constraint on the resulting sparsified graph for better generalization. PTDNet can be used as a key component in GNN models to improve their performances on various tasks, such as node classification and link prediction. Experimental studies on both synthetic and benchmark datasets show that PTDNet can improve the performance of GNNs significantly and the performance gain becomes larger for more noisy datasets.

Recent developments in discovering dynamic treatment regimes (DTRs) have heightened the importance of deep reinforcement learning (DRL) which are used to recover the doctor’s treatment policies. However, existing DRL-based methods expose the following limitations: 1) supervised methods based on behavior cloning suffer from compounding errors; 2) the self-defined reward signals in reinforcement learning models are either too sparse or need clinical guidance; 3) only positive trajectories (e.g. survived patients) are considered in current imitation learning models, with negative trajectories (e.g. deceased patients) been largely ignored, which are examples of what not to do and could help the learned policy avoid repeating mistakes. To address these limitations, in this paper, we propose the adversarial cooperative imitation learning model, ACIL, to deduce the optimal dynamic treatment regimes that mimics the positive trajectories while differs from the negative trajectories. Specifically, two discriminators are used to help achieve this goal: an adversarial discriminator is designed to minimize the discrepancies between the trajectories generated from the policy and the positive trajectories, and a cooperative discriminator is used to distinguish the negative trajectories from the positive and generated trajectories. The reward signals from the discriminators are utilized to refine the policy for dynamic treatment regimes. Experiments on the publicly real-world medical data demonstrate that ACIL improves the likelihood of patient survival and provides better dynamic treatment regimes with the exploitation of information from both positive and negative trajectories.

Existing representation learning methods based on graph neural networks and their variants rely on the aggregation of neighborhood information, which makes it sensitive to noises in the graph, e.g. erroneous links between nodes, incorrect/missing node features. In this paper, we propose Graph Denoising Policy Network (short for GDPNet) to learn robust representations from noisy graph data through reinforcement learning. GDPNet first selects signal neighborhoods for each node, and then aggregates the information from the selected neighborhoods to learn node representations for the down-stream tasks. Specifically, in the signal neighborhood selection phase, GDPNet optimizes the neighborhood for each target node by formulating the process of removing noisy neighborhoods as a Markov decision process and learning a policy with task-specific rewards received from the representation learning phase. In the representation learning phase, GDPNet aggregates features from signal neighbors to generate node representations for down-stream tasks, and provides task-specific rewards to the signal neighbor selection phase. These two phases are jointly trained to select optimal sets of neighbors for target nodes with maximum cumulative task-specific rewards, and to learn robust representations for nodes. Experimental results on node classification task demonstrate the effectiveness of GDNet, outperforming the state-of-the-art graph representation learning methods on several well-studied datasets.

Network embedding aims to learn the low-dimensional representations/embeddings of vertices which preserve the structure and inherent properties of the networks. The resultant embeddings are beneficial to downstream tasks such as vertex classification and link prediction. A vast majority of real-world networks are coupled with a rich set of vertex attributes, which could be potentially complementary in learning better embeddings. Existing attributed network embedding models, with shallow or deep architectures, typically seek to match the representations in topology space and attribute space for each individual vertex by assuming that the samples from the two spaces are drawn uniformly. The assumption, however, can hardly be guaranteed in practice. Due to the intrinsic sparsity of sampled vertex sequences and incompleteness in vertex attributes, the discrepancy between the attribute space and the network topology space inevitably exists. Furthermore, the interactions among vertex attributes, a.k.a cross features, have been largely ignored by existing approaches. To address the above issues, in this paper, we propose Nettention, a self-attentive network embedding approach that can efficiently learn vertex embeddings on attributed network. Instead of sample-wise optimization, Nettention aggregates the two types of information through minimizing the difference between the representation distributions in the low-dimensional topology and attribute spaces. The joint inference is encapsulated in a generative adversarial training process, yielding better generalization performance and robustness. The learned distributions consider both locality-preserving and global reconstruction constraints which can be inferred from the learning of the adversarially regularized autoencoders. Additionally, a multi-head self-attention module is developed to explicitly model the attribute interactions. Extensive experiments on benchmark datasets have verified the effectiveness of the proposed Nettention model on a variety of tasks, including vertex classification and link prediction.

Many large-scale knowledge bases simultaneously represent two views of knowledge graphs (KGs): an ontology view for abstract and commonsense concepts, and an instance view for specific entities that are instantiated from ontological concepts. Existing KG embedding models, however, merely focus on representing one of the two views alone. In this paper, we propose a novel two-view KG embedding model, JOIE, with the goal to produce better knowledge embedding and enable new applications that rely on multi-view knowledge. JOIE employs both cross-view and intra-view modeling that learn on multiple facets of the knowledge base. The cross-view association model is learned to bridge the embeddings of ontological concepts and their corresponding instance-view entities. The intra-view models are trained to capture the structured knowledge of instance and ontology views in separate embedding spaces, with a hierarchy-aware encoding technique enabled for ontologies with hierarchies. We explore multiple representation techniques for the two model components and investigate with nine variants of JOIE. Our model is trained on large-scale knowledge bases that consist of massive instances and their corresponding ontological concepts connected via a (small) set of cross-view links. Experimental results on public datasets show that the best variant of JOIE significantly outperforms previous models on instance-view triple prediction task as well as ontology population on ontology-view KG. In addition, our model successfully extends the use of KG embeddings to entity typing with promising performance.

Co-clustering partitions instances and features simultaneously by leveraging the duality between them and it often yields impressive performance improvement over traditional clustering algorithms. The recent development in learning deep representations has demonstrated the advantage in extracting effective features. However, the research on leveraging deep learning frameworks for co-clustering is limited for two reasons: 1) current deep clustering approaches usually decouple feature learning and cluster assignment as two separate steps, which cannot yield the task-specific feature representation; 2) existing deep clustering approaches cannot learn representations for instances and features simultaneously. In this paper, we propose a deep learning model for co-clustering called DeepCC. DeepCC utilizes the deep autoencoder for dimension reduction, and employs a variant of Gaussian Mixture Model (GMM) to infer the cluster assignments. A mutual information loss is proposed to bridge the training of instances and features. DeepCC jointly optimizes the parameters of the deep autoencoder and the mixture model in an end-to-end fashion on both the instance and the feature spaces, which can help the deep autoencoder escape from local optima and the mixture model circumvent the Expectation-Maximization (EM) algorithm. To the best of our knowledge, DeepCC is the first deep learning model for co-clustering. Experimental results on various dataseis demonstrate the effectiveness of DeepCC.

Massive and dynamic networks arise in many practical applications such as social media, security and public health. Given an evolutionary network, it is crucial to detect structural anomalies, such as vertices and edges whose "behaviors'' deviate from underlying majority of the network, in a real-time fashion. Recently, network embedding has proven a powerful tool in learning the low-dimensional representations of vertices in networks that can capture and preserve the network structure. However, most existing network embedding approaches are designed for static networks, and thus may not be perfectly suited for a dynamic environment in which the network representation has to be constantly updated. In this paper, we propose a novel approach, NetWalk, for anomaly detection in dynamic networks by learning network representations which can be updated dynamically as the network evolves. We first encode the vertices of the dynamic network to vector representations by clique embedding, which jointly minimizes the pairwise distance of vertex representations of each walk derived from the dynamic networks, and the deep autoencoder reconstruction error serving as a global regularization. The vector representations can be computed with constant space requirements using reservoir sampling. On the basis of the learned low-dimensional vertex representations, a clustering-based technique is employed to incrementally and dynamically detect network anomalies. Compared with existing approaches, NetWalk has several advantages: 1) the network embedding can be updated dynamically, 2) streaming network nodes and edges can be encoded efficiently with constant memory space usage, 3). flexible to be applied on different types of networks, and 4) network anomalies can be detected in real-time. Extensive experiments on four real datasets demonstrate the effectiveness of NetWalk.

The problem of network representation learning, also known as network embedding, arises in many machine learning tasks assuming that there exist a small number of variabilities in the vertex representations which can capture the "semantics" of the original network structure. Most existing network embedding models, with shallow or deep architectures, learn vertex representations from the sampled vertex sequences such that the low-dimensional embeddings preserve the locality property and/or global reconstruction capability. The resultant representations, however, are difficult for model generalization due to the intrinsic sparsity of sampled sequences from the input network. As such, an ideal approach to address the problem is to generate vertex representations by learning a probability density function over the sampled sequences. However, in many cases, such a distribution in a low-dimensional manifold may not always have an analytic form. In this study, we propose to learn the network representations with adversarially regularized autoencoders (NetRA). NetRA learns smoothly regularized vertex representations that well capture the network structure through jointly considering both locality-preserving and global reconstruction constraints. The joint inference is encapsulated in a generative adversarial training process to circumvent the requirement of an explicit prior distribution, and thus obtains better generalization performance. We demonstrate empirically how well key properties of the network structure are captured and the effectiveness of NetRA on a variety of tasks, including network reconstruction, link prediction, and multi-label classification.

Multiple and co-evolving networks are common in many real settings such as social networks, communication networks and other information networks. Most of the work in the field of network evolution has focused on a single evolving network or specific network pairs, lacking generality in the analysis of multiple networks and ignoring the co-evolutionary dynamics between networks. In practice, a significant amount of information is encoded in the evolution of multiple networks with respect to one another. In this paper, we show how to use a shared temporal matrix factorization framework to model co-evolution across multiple networks, and we refer to this framework as CoEvol. Specifically, the proposed framework decomposes the adjacency matrix of each co-evolving network into a product of network-independent shared factor and a set of network-specific temporal factors, and impose a non-negativity constraint on the factors for greater interpretability. Our approach has the potential to predict multiple changes in co-evolving networks over time, because of its ability to explicitly represent co-evolving networks as a function of time. The CoEvol framework also has the advantage of generality in addressing various temporal tasks across multiple networks. We show the benefits of this approach in predicting co-evolution across multiple networks on the tasks including cross-network link prediction, lag correlation detection and community detection. Compared to baseline methods, CoEvol obtains lower root mean-squared error in cross-network link prediction and higher cluster purity in community detection, which demonstrates that the CoEvol framework can capture the dynamics across multiple networks.

The problem of evolutionary network analysis has gained increasing attention in recent years, because of an increasing number of networks, which are encountered in temporal settings. For example, social networks, communication networks, and information networks continuously evolve over time, and it is desirable to learn interesting trends about how the network structure evolves over time, and in terms of other interesting trends. One challenging aspect of networks is that they are inherently resistant to parametric modeling, which allows us to truly express the edges in the network as functions of time. This is because, unlike multidimensional data, the edges in the network reflect interactions among nodes, and it is difficult to independently model the edge as a function of time, without taking into account its correlations and interactions with neighboring edges. Fortunately, we show that it is indeed possible to achieve this goal with the use of a matrix factorization, in which the entries are parameterized by time. This approach allows us to represent the edge structure of the network purely as a function of time, and predict the evolution of the network over time. This opens the possibility of using the approach for a wide variety of temporal network analysis problems, such as predicting future trends in structures, predicting links, and node-centric anomaly/event detection. This flexibility is because of the general way in which the approach allows us to express the structure of the network as a function of time. We present a number of experimental results on a number of temporal data sets showing the effectiveness of the approach.

In a sponsored search market, the problem of measuring the intensity of competition among advertisers is increasingly gaining prominence today. Usually, search providers want to monitor the advertiser communities that share common bidding keywords, so that they can intervene when competition slackens. However, to the best of our knowledge, not much research has been conducted in identifying advertiser communities and understanding competition within these communities. In this paper we introduce a novel approach to detect competitive communities in a weighted bi-partite network formed by advertisers and their bidding keywords. The proposed approach is based on an advertiser vertex metric called intensity score, which takes the following two factors into consideration: the competitors that bid on the same keywords, and the advertisers' consumption proportion within the community. Evidence shows that when market competition rises, the revenue for a search provider also increases. Our community detection algorithm Max-Intensity is designed to detect communities which have the maximum intensity score. In this paper, we conduct experiments and validate the performance of Max-Intensity on sponsored search advertising data. Compared to baseline methods, the communities detected by our algorithm have low Herfindahl-Hirschman index (HHI) and comprehensive concentration index (CCI), which demonstrates that the communities given by Max-Intensity can capture the structure of the competitive communities.