Time series data is essential in various applications, including climate modeling, healthcare monitoring, and financial analytics. Understanding the contextual information associated with real-world time series data is often essential for accurate and reliable event predictions. In this paper, we introduce TimeCAP, a time-series processing framework that creatively employs Large Language Models (LLMs) as contextualizers of time series data, extending their typical usage as predictors. TimeCAP incorporates two independent LLM agents: one generates a textual summary capturing the context of the time series, while the other uses this enriched summary to make more informed predictions. In addition, TimeCAP employs a multi-modal encoder that synergizes with the LLM agents, enhancing predictive performance through mutual augmentation of inputs with in-context examples. Experimental results on real-world datasets demonstrate that TimeCAP outperforms state-of-the-art methods for time series event prediction, including those utilizing LLMs as predictors, achieving an average improvement of 28.75% in F1 score.

Real-world time series data often require analysis or interpretation from domain experts. Some tasks, like time series question answering, involve both time series and natural language questions, posing challenges for single-modality language models to understand their interaction. To this end, we present TSLA (Time Series Language Model), a framework designed to enhance the language model with the understanding of time series data for multi-modality tasks. TSLA comprises three key components. (1) Time Series Tokenizer learns how to represent time series data into discrete tokens, making it more manageable for language models. (2) Joint (Pre-)Training on task-agnostic time series and text data integrates time series tokens and text tokens to model the interplay between time series and language concepts. (3) Multi-task Instruction Tuning fine-tunes the pretrained TSLA for various downstream tasks relevant to user interests. For evaluation, we applied TSLA to time series data from human motions on four tasks: time series captioning, time series question answering, text-based time series synthesis, and text-based time series continuation. The results demonstrate TSLA’s effectiveness in handling multiple time series analysis tasks, pointing the way for future research endeavors.

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%.

We frame code generation as a black-box optimization problem within the code space and demonstrate how optimization-inspired techniques can enhance inference scaling over text. Based on this perspective, we propose **SCATTERED FOREST SEARCH (SFS)**, a novel approach that improves solution diversity during evolutionary search, thereby avoiding local optima. Our theoretical analysis illustrates how these methods improve exploration and enhance efficiency. Extensive experiments on *HumanEval, MBPP, APPS, CodeContests,* and *Leetcode* reveal significant performance gains. For instance, our method achieves a **pass@1 rate of 67.1% on HumanEval+** and **87.2% on HumanEval with GPT-3.5**, marking improvements of **8.6%** and **4.3%** over the state-of-the-art, while also halving the iterations needed to find the correct solution. Furthermore, our approach scales more efficiently than existing search techniques, including **tree search, line search,** and **repeated sampling (Best of N)**.

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.

Xinyuan Wang, Yanchi Liu, Wei Cheng, Xujiang Zhao, Zhengzhang Chen, Wenchao Yu, Yanjie Fu, Haifeng Chen. Proceedings of the 2025 Conference of the Nations of the Americas Chapter of the Association for Computational Linguistics: Human Language Technologies (Volume 1: Long Papers). 2025.

Time series analysis provides essential insights for real-world system dynamics and informs downstream decision-making, yet most existing methods often overlook the rich contextual signals present in auxiliary modalities. To bridge this gap, we introduce TimeXL, a multi-modal prediction framework that integrates a prototype-based time series encoder with three collaborating Large Language Models (LLMs) to deliver more accurate predictions and interpretable explanations. First, a multi-modal prototype-based encoder processes both time series and textual inputs to generate preliminary forecasts alongside case-based rationales. These outputs then feed into a prediction LLM, which refines the forecasts by reasoning over the encoder's predictions and explanations. Next, a reflection LLM compares the predicted values against the ground truth, identifying textual inconsistencies or noise. Guided by this feedback, a refinement LLM iteratively enhances text quality and triggers encoder retraining. This closed-loop workflow---prediction, critique (reflect), and refinement---continuously boosts the framework's performance and interpretability. Empirical evaluations on four real-world datasets demonstrate that TimeXL achieves up to 8.9\% improvement in AUC and produces human-centric, multi-modal explanations, highlighting the power of LLM-driven reasoning for time series prediction.

Time series, typically represented as numerical sequences, can also be transformed into images and texts, offering multi-modal views (MMVs) of the same underlying signal. These MMVs can reveal complementary patterns and enable the use of powerful pre-trained large models, such as large vision models (LVMs), for long-term time series forecasting (LTSF). However, as we identified in this work, the state-of-the-art (SOTA) LVM-based forecaster poses an inductive bias towards "forecasting periods". To harness this bias, we propose DMMV, a novel decomposition-based multi-modal view framework that leverages trend-seasonal decomposition and a novel backcast-residual based adaptive decomposition to integrate MMVs for LTSF. Comparative evaluations against 14 SOTA models across diverse datasets show that DMMV outperforms single-view and existing multi-modal baselines, achieving the best mean squared error (MSE) on 6 out of 8 benchmark datasets. The code for this paper is available at: https://github.com/D2I-Group/dmmv.

The rapid advancement of large language models (LLMs) such as ChatGPT, DeepSeek, and Claude has significantly increased the presence of AI-generated text in digital communication. This trend has heightened the need for reliable detection methods to distinguish between human-authored and machine-generated content. Existing approaches both zero-shot methods and supervised classifiers largely conceptualize this task as a binary classification problem, often leading to poor generalization across domains and models. In this paper, we argue that such a binary formulation fundamentally mischaracterizes the detection task by assuming a coherent representation of human-written texts. In reality, human texts do not constitute a unified distribution, and their diversity cannot be effectively captured through limited sampling. This causes previous classifiers to memorize observed OOD characteristics rather than learn the essence of `non-ID' behavior, limiting generalization to unseen human-authored inputs. Based on this observation, we propose reframing the detection task as an out-of-distribution (OOD) detection problem, treating human-written texts as distributional outliers while machine-generated texts are in-distribution (ID) samples. To this end, we develop a detection framework using one-class learning method including DeepSVDD and HRN, and score-based learning techniques such as energy-based method, enabling robust and generalizable performance. Extensive experiments across multiple datasets validate the effectiveness of our OOD-based approach. Specifically, the OOD-based method achieves 98.3\% AUROC and AUPR with only 8.9\% FPR95 on DeepFake dataset. Moreover, we test our detection framework on multilingual, attacked, and unseen-model and -domain text settings, demonstrating the robustness and generalizability of our framework. Code will be released openly and also available in the supplementary materials.

Yijia Xiao, Yiqiao Jin, Yushi Bai, Yue Wu, Xianjun Yang, Xiao Luo, Wenchao Yu, Xujiang Zhao, Yanchi Liu, Quanquan Gu, Haifeng Chen, Wei Wang, Wei Cheng. Proceedings of the 2024 Conference on Empirical Methods in Natural Language Processing. 2024.

Synthetic aperture radar (SAR) is vulnerable to interference, including intentional and unintentional-ones. Noise frequency modulated (FM) interference is a kind of intentional interference, which has the characteristics of broadband and randomness, which makes the noise FM signal become a kind of most commonly used interference signal. Noise FM interference will have a serious impact on the SAR image, but the current algorithms for interference suppression are not sufficiently studied. This paper extends a time-domain cancellation algorithm for suppressing the noise FM interference of SAR. This algorithm can reconstruct the noise FM interference signal from the contaminated SAR echo, and then suppress the interference component in the echo by time-domain cancellation. Finally, this paper validates the superior performance of the algorithm by point target simulation and Radarsat-1 data. The proposed method is valid even when the signal-to-interference ratio is lower than -40dB.

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.

Molecular property prediction faces the challenge of limited labeled data as it necessitates a series of specialized experiments to annotate target molecules. Data augmentation techniques can effectively address the issue of data scarcity. In recent years, Mixup has achieved significant success in traditional domains such as image processing. However, its application in molecular property prediction is relatively limited due to the irregular, non-Euclidean nature of graphs and the fact that minor variations in molecular structures can lead to alterations in their properties. To address these challenges, we propose a novel data augmentation method called Mix-Key tailored for molecular property prediction. Mix-Key aims to capture crucial features of molecular graphs, focusing separately on the molecular scaffolds and functional groups. By generating isomers that are relatively invariant to the scaffolds or functional groups, we effectively preserve the core information of molecules. Additionally, to capture interactive information between the scaffolds and functional groups while ensuring correlation between the original and augmented graphs, we introduce molecular fingerprint similarity and node similarity. Through these steps, Mix-Key determines the mixup ratio between the original graph and two isomers, thus generating more informative augmented molecular graphs. We extensively validate our approach on molecular datasets of different scales with several Graph Neural Network architectures. The results demonstrate that Mix-Key consistently outperforms other data augmentation methods in enhancing molecular property prediction on several datasets.

Despite recent progress in Graph Neural Networks (GNNs), explaining predictions made by GNNs remains a challenging and nascent problem. The leading method mainly considers the local explanations, i.e., important subgraph structure and node features, to interpret why a GNN model makes the prediction for a single instance, e.g. a node or a graph. As a result, the explanation generated is painstakingly customized at the instance level. The unique explanation interpreting each instance independently is not sufficient to provide a global understanding of the learned GNN model, leading to the lack of generalizability and hindering it from being used in the inductive setting. Besides, training the explanation model explaining for each instance is time-consuming for large-scale real-life datasets. In this study, we address these key challenges and propose PGExplainer, a parameterized explainer for GNNs. PGExplainer adopts a deep neural network to parameterize the generation process of explanations, which renders PGExplainer a natural approach to multi-instance explanations. Compared to the existing work, PGExplainer has better generalization ability and can be utilized in an inductive setting without training the model for new instances. Thus, PGExplainer is much more efficient than the leading method with significant speed-up. In addition, the explanation networks can also be utilized as a regularizer to improve the generalization power of existing GNNs when jointly trained with downstream tasks. Experiments on both synthetic and real-life datasets show highly competitive performance with up to 24.7% relative improvement in AUC on explaining graph classification over the leading baseline.

Various contrastive learning approaches have been proposed in recent years and achieve significant empirical success. While effective and prevalent, contrastive learning has been less explored for time series data. A key component of contrastive learning is to select appropriate augmentations imposing some priors to construct feasible positive samples, such that an encoder can be trained to learn robust and discriminative representations. Unlike image and language domains where "desired'' augmented samples can be generated with the rule of thumb guided by prefabricated human priors, the ad-hoc manual selection of time series augmentations is hindered by their diverse and human-unrecognizable temporal structures. How to find the desired augmentations of time series data that are meaningful for given contrastive learning tasks and datasets remains an open question. In this work, we address the problem by encouraging both high fidelity and variety based on information theory. A theoretical analysis leads to the criteria for selecting feasible data augmentations. On top of that, we propose a new contrastive learning approach with information-aware augmentations, InfoTS, that adaptively selects optimal augmentations for time series representation learning. Experiments on various datasets show highly competitive performance with up to a 12.0% reduction in MSE on forecasting tasks and up to 3.7% relative improvement in accuracy on classification tasks over the leading baselines.

The recent trend towards Personalized Federated Learning (PFL) has garnered significant attention as it allows for the training of models that are tailored to each client while maintaining data privacy. However, current PFL techniques primarily focus on modeling the conditional distribution heterogeneity (i.e. concept shift), which can result in suboptimal performance when the distribution of input data across clients diverges (i.e. covariate shift). Additionally, these techniques often lack the ability to adapt to unseen data, further limiting their effectiveness in real-world scenarios. To address these limitations, we propose a novel approach, FedGMM, which utilizes Gaussian mixture models (GMM) to effectively fit the input data distributions across diverse clients. The model parameters are estimated by maximum likelihood estimation utilizing a federated Expectation-Maximization algorithm, which is solved in closed form and does not assume gradient similarity. Furthermore, FedGMM possesses an additional advantage of adapting to new clients with minimal overhead, and it also enables uncertainty quantification. Empirical evaluations on synthetic and benchmark datasets demonstrate the superior performance of our method in both PFL classification and novel sample detection.

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.

Sound Event Early Detection (SEED) is an essential task in recognizing the acoustic environments and soundscapes. However, most of the existing methods focus on the offline sound event detection, which suffers from the over-confidence issue of early-stage event detection and usually yield unreliable results. To solve the problem, we propose a novel Polyphonic Evidential Neural Network (PENet) to model the evidential uncertainty of the class probability with Beta distribution. Specifically, we use a Beta distribution to model the distribution of class probabilities, and the evidential uncertainty enriches uncertainty representation with evidence information, which plays a central role in reliable prediction. To further improve the event detection performance, we design the backtrack inference method that utilizes both the forward and backward audio features of an ongoing event. Experiments on the DESED database show that the proposed method can simultaneously improve 13.0% and 3.8% in time delay and detection F1 score compared to the state-of-the-art methods.

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.

Radio frequency interference (RFI) suppression is a hot topic in synthetic aperture radar (SAR) imaging. Mathematically, the RFI suppression problem can be considered as an underdetermined signal separation problem to extract the signal of interest (SOI) from the RFI contaminated raw data. The regularization-based method can exploit both the prior knowledge of RFI and SOI and, therefore, has the advantage of solving the underdetermined problem and preserving the information of SOI. Current regularization methods make use of the RFI prior well by exploiting low-rank representation (LRR) or sparse representation (SR), but the prior knowledge of SOI has not been sufficiently studied and used. In some literature, the sparsity of the raw data or range profile was exploited to formulate the regularization term, which we found to be inadequate in describing the SOI property. In this article, we explore the features of SAR images and propose an RFI suppression model with a combination of multiple image domain regularizations to preserve different types of targets. An efficient solution to the optimization problem is proposed based on the alternating direction multiplier method (ADMM). The proposed method can accurately recover both the sparse strong targets, and the nonsparse regions in the illuminated area and its performance is validated by measured data.

We consider the models of deep multi-task learning with recurrent architectures that exploit regularities across tasks to improve the performance of multiple sequence processing tasks jointly. Most existing architectures are painstakingly customized to learn task relationships for different problems, which is not flexible enough to model the dynamic task relationships and lacks generalization abilities to novel test-time scenarios. We propose multi-task recurrent modular networks (MT-RMN) that can be incorporated in any multi-task recurrent models to address the above drawbacks. MT-RMN consists of a shared encoder and multiple task-specific decoders, and recurrently operates over time. For better flexibility, it modularizes the encoder into multiple layers of sub-networks and dynamically controls the connection between these sub-networks and the decoders at different time steps, which provides the recurrent networks with varying degrees of parameter sharing for tasks with dynamic relatedness. For the generalization ability, MT-RMN aims to discover a set of generalizable sub-networks in the encoder that are assembled in different ways for different tasks. The policy networks augmented with the differentiable routers are utilized to make the binary connection decisions between the sub-networks. The experimental results on three multi-task sequence processing datasets consistently demonstrate the effectiveness of MT-RMN.

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.

Recent studies have demonstrated the vulnerability of deep neural networks against adversarial examples. In-spired by the observation that adversarial examples often lie outside the natural image data manifold and the intrinsic dimension of image data is much smaller than its pixel space dimension, we propose to embed high-dimensional input images into a low-dimensional space and apply regularization on the embedding space to push the adversarial examples back to the manifold. The proposed framework is called Embedding Regularized Classifier (ER-Classifier), which improves the adversarial robustness of the classifier through embedding regularization. Besides improving classification accuracy against adversarial examples, the framework can be combined with detection methods to detect adversarial examples. Experimental results on several benchmark datasets show that, our proposed framework achieves good performance against strong adversarial at-tack methods.

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.

Autofocus is one of the key problems in inverse synthetic aperture radar (ISAR) since the noncooperation of the target motion. For sparse aperture ISAR, classical autofocus algorithms are not suitable due to the discontinuity of the azimuth sampling. In this paper, a novel framework is proposed for ISAR autofocus with sparse aperture. The autofocus problem is transformed into an optimization problem with l0norm and nonlocal total variation (NLTV) regularization constraints. Therefore, both spatial sparsity and structural information of the target can be considered in the process. Dual iterative computation which combines regularization method and conjugate gradient (CG) algorithm is applied to reconstruct the image and correct the phase error. Results of real data experiments show the effectiveness of the proposed method.

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.

The performance of synthetic aperture radar is vulnerable to radio frequency interference (RFI). In many situations, the RFI has a low-rank property, since the frequency bands occupied by RFI usually remain stable during a short slow time period. Therefore, low-rank representation (LRR)-based methods can be applied to separate RFI and signal of interest (SOI), by minimizing the rank of RFI components with a regularization constraint to protect SOI. However, traditional methods use the sparsity of the raw data or range profile to formulate the regularization term, which fails to describe the properties of SOI accurately. In addition to the sparse property of range profiles, this article explores the common patterns hidden in the range profiles and proposes two new LRR-based RFI suppression optimization models with a well-designed regularization term to describe such common sparsity to protect the SOI. Four methods are proposed to solve the optimization problems based on the alternating direction multiplier (ADM) method, which provides tradeoff between efficiency and accuracy. Compared with traditional LRR-based RFI suppression methods, the proposed methods make a more precise description of the features of SOI, therefore can better protect the information of SOI during the RFI suppression process and improves the imaging quality. The superior performance of the proposed method is validated by measured data in both sparse and nonsparse scenes.

The problem of learning and forecasting underlying trends in time series data arises in a variety of applications, such as traffic management, energy optimization, etc. In literature, a trend in time series is characterized by the slope and duration, and its prediction is then to forecast the two values of the subsequent trend given historical data of the time series. For this problem, existing approaches mainly deal with the case in univariate time series. However, in many real-world applications, there are multiple variables at play, and handling all of them at the same time is crucial for an accurate prediction. A natural way is to employ multi-task learning (MTL) techniques in which the trend learning of each time series is treated as a task. The key point of MTL is to learn task relatedness to achieve better parameter sharing, which however is challenging in trend prediction task. First, effectively modeling the complex temporal patterns in different tasks is hard as the temporal and spatial dimensions are entangled. Second, the relatedness among tasks may change over time. In this paper, we propose a neural network, DeepTrends, for multivariate time series trend prediction. The core module of DeepTrends is a tensorized LSTM with adaptive shared memory (TLASM). TLASM employs the tensorized LSTM to model the temporal patterns of long-term trend sequences in an MTL setting. With an adaptive shared memory, TLASM is able to learn the relatedness among tasks adaptively, based upon which it can dynamically vary degrees of parameter sharing among tasks. To further consider short-term patterns, DeepTrends utilizes a multi-task 1dCNN to learn the local time series features, and employs a task-specific sub-network to learn a mixture of long-term and short-term patterns for trend prediction. Extensive experiments on real datasets demonstrate the effectiveness of the proposed model.

Graph representation learning serves as the core of important prediction tasks, ranging from product recommendation to fraud detection. Real-life graphs usually have complex information in the local neighborhood, where each node is described by a rich set of features and connects to dozens or even hundreds of neighbors. Despite the success of neighborhood aggregation in graph neural networks, task-irrelevant information is mixed into nodes’ neighborhood, making learned models suffer from sub-optimal generalization performance. In this paper, we present NeuralSparse, a supervised graph sparsification technique that improves generalization power by learning to remove potentially task-irrelevant edges from input graphs. Our method takes both structural and non-structural information as input, utilizes deep neural networks to parameterize sparsification processes, and optimizes the parameters by feedback signals from downstream tasks. Under the NeuralSparse framework, supervised graph sparsification could seamlessly connect with existing graph neural networks for more robust performance. Experimental results on both benchmark and private datasets show that NeuralSparse can yield up to 7.2% improvement in testing accuracy when working with existing graph neural networks on node classification tasks.

Despite recent progress in Graph Neural Networks (GNNs), explaining predictions made by GNNs remains a challenging open problem. The leading method mainly addresses the local explanations (i.e., important subgraph structure and node features) to interpret why a GNN model makes the prediction for a single instance, e.g. a node or a graph. As a result, the explanation generated is painstakingly customized for each instance. The unique explanation interpreting each instance independently is not sufficient to provide a global understanding of the learned GNN model, leading to the lack of generalizability and hindering it from being used in the inductive setting. Besides, as it is designed for explaining a single instance, it is challenging to explain a set of instances naturally (e.g., graphs of a given class). In this study, we address these key challenges and propose PGExplainer, a parameterized explainer for GNNs. PGExplainer adopts a deep neural network to parameterize the generation process of explanations, which enables PGExplainer a natural approach to multi-instance explanations. Compared to the existing work, PGExplainer has a better generalization power and can be utilized in an inductive setting easily. Experiments on both synthetic and real-life datasets show highly competitive performance with up to 24.7\% relative improvement in AUC on explaining graph classification over the leading baseline.

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.

Dynamic networks are ubiquitous. Link prediction in dynamic networks has attracted tremendous research interests. Many models have been developed to predict links that may emerge in the immediate future from the past evolution of the networks. There are two key factors: 1) a node is more likely to form a link in the near future with another node within its close proximity, rather than with a random node; 2) a dynamic network usually evolves smoothly. Existing approaches seldom unify these two factors to strive for the spatial and temporal consistency in a dynamic network. To address this limitation, in this paper, we propose a link prediction model with spatial and temporal consistency (LIST), to predict links in a sequence of networks over time. LIST characterizes the network dynamics as a function of time, which integrates the spatial topology of network at each timestamp and the temporal network evolution. Comparing to existing approaches, LIST has two advantages: 1) LIST uses a generic model to express the network structure as a function of time, which makes it also suitable for a wide variety of temporal network analysis problems beyond the focus of this paper; 2) by retaining the spatial and temporal consistency, LIST yields better prediction performance. Extensive experiments on four real datasets demonstrate the effectiveness of the LIST model.

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.

This paper proposes a route planning algorithm for the automatic garment cutter, a machine extensively used in the clothing industry, aiming at reducing the length and improving the smoothness of quick moving route for the cutter. With proper constraints for the cloth segments and knife-down points, the route planning problem is resolved into a generalized travelling salesman problem (GTSP) of the first category, for which an enhanced genetic algorithm is proposed. In this paper, we firstly outline the procedure of the algorithm and discuss some important details, including individual fitness calculation based on the multistage graph problem, a local search algorithm with 2-opt method, etc. Then a positionreservation crossover operator based on dual-relevancy, and an adaptive mutation operator based on population dispersion are proposed, which can accelerate convergence of the algorithm as well as prevent locking into local minima as much as possible. Finally, experimental tests are performed on the GTSP Instances Library and the data of garment CAD files, which demonstrates the effectiveness of our route planning strategy in terms of both solution quality and running time.