Multimodal generation and retrieval systems are increasingly central to modern information retrieval, powering retrieval-augmented generation (RAG), multimodal search, recommendation, and knowledge intensive applications. Despite rapid progress in multimodal large language models (MLLMs), robust and principled evaluation of multimodal generation and retrieval remains a major open challenge for the IR community. This workshop aims to foster discussions and research efforts by bringing together researchers and practitioners in information retrieval, natural language processing, computer vision, and multimodal AI. Our goal is to establish evaluation methods for multimodal research and advance research efforts in this direction.

Pseudo-Alignment is a pervasive challenge in many large language models for time series (LLM4TS) models, often causing them to underperform compared to linear models or randomly initialised backbones. However, there is limited discussion in the community for the reasons that pseudo-alignment occurs. In this work, we conduct a thorough investigation into the root causes of pseudo-alignment in LLM4TS and build a connection of pseudo-alignment to the cone effect in LLM. We demonstrate that pseudo-alignment arises from the interplay of cone effect within pretrained LLM components and the intrinsically low-dimensional manifold of time-series data. In addition, we also introduce TimeSUP, a novel technique designed to mitigate this issue and improve forecast performance in existing LLM4TS approaches. TimeSUP addresses this by increasing the time series manifold to more closely match the intrinsic dimension of language embeddings, allowing the model to distinguish temporal signals clearly while still capturing shared structures across modalities. As a result, representations for time and language tokens remain distinct yet exhibit high cosine similarity, signifying that the model preserves each modality's unique features while learning their commonalities in a unified embedding space. Empirically, TimeSUP consistently outperforms state-of-the-art LLM4TS methods and other lightweight baselines on long-term forecasting performance. Furthermore, it can be seamlessly integrated into four existing LLM4TS pipelines and delivers significant improvements in forecasting performance.

Large language models (LLMs) have shown outstanding performance across a variety of tasks, partly due to advanced prompting techniques. However, these techniques often require lengthy prompts, which increase computational costs and can hinder performance because of the limited context windows of LLMs. While prompt compression is a straightforward solution, existing methods confront the challenges of retaining essential information, adapting to context changes, and remaining effective across different tasks. To tackle these issues, we propose a task-agnostic method called Dynamic Prompt Compression (LLM-DPC). Our method reduces the number of prompt tokens while minimizing any degradation in LLM performance. We model prompt compression as a Markov Decision Process (MDP), enabling the DPC-Agent to sequentially remove redundant tokens by adapting to dynamic contexts and retaining crucial content. We develop a reward function for training the DPC-Agent that balances the compression ratio, the quality of the LLM output, and the retention of key information. This allows for prompt token reduction without needing an external black-box LLM. Inspired by the progressive difficulty adjustment in curriculum learning, we introduce a Hierarchical Prompt Compression (HPC) training strategy that gradually increases the compression difficulty, enabling the DPC-Agent to learn an effective compression method that maintains information integrity. Experiments demonstrate that our method outperforms state-of-the-art techniques, especially at higher compression ratio.

Kolmogorov-Arnold Networks (KANs) are neural architectures inspired by the Kolmogorov-Arnold representation theorem that leverage B-spline parameterizations for flexible, locally adaptive function approximation. Although KANs can capture complex nonlinearities beyond those modeled by standard Multi-Layer Perceptrons (MLPs), they frequently exhibit miscalibrated confidence estimates-manifesting as overconfidence in dense data regions and underconfidence in sparse areas. In this work, we systematically examine the impact of four critical hyperparameters -- Layer Width, Grid Order, Shortcut Function, and Grid Range -- on the calibration of KANs. Furthermore, we introduce a novel Temperature-Scaled Loss (TSL) that integrates a temperature parameter directly into the training objective, dynamically adjusting the predictive distribution during learning. Both theoretical analysis and extensive empirical evaluations on standard benchmarks demonstrate that TSL significantly reduces calibration errors, thereby improving the reliability of probabilistic predictions. Overall, our study provides actionable insights into the design of spline-based neural networks and establishes TSL as a robust, loss-agnostic solution for enhancing calibration.

Classical overlap metrics such as Dice or IoU quantify where a medical-image segmentation falls short but say nothing about the confidence of each prediction. Over-confident errors are particularly dangerous in clinical practice, where a single false-positive voxel may trigger an unnecessary biopsy. We introduce three contributions that jointly address spatial precision and reliability. (i) Signed-Distance Calibration (SDC) loss couples cross-entropy, local calibration and a differentiable signed-distance penalty, enforcing boundary accuracy while moderating confidence. (ii) A Spatially Adaptive Margin (SAM) module applies lightweight morphological transforms to ground-truth masks before computing the local target, sharpening ambiguous edges. (iii) Pixel-wise Expected Calibration Error (pECE) extends ECE to millions of voxels and penalises high-confidence false positives. Across four public datasets (ACDC, FLARE, BraTS, PROSTATE) and two back-bones (U-Net, nnU-Net), SDC improves Dice by up to 4 percentage points and halves ECE compared with the state of the art, without sacrificing runtime. Code is available on: https://github.com/EagleAdelaide/SDC-Loss.

In the era of big data, data mining has become indispensable for uncovering hidden patterns and insights from vast and complex datasets. The integration of multimodal data sources further enhances its potential. Multimodal Federated Learning (MFL) is a distributed approach that enhances the efficiency and quality of multimodal learning, ensuring collaborative work and privacy protection. However, missing modalities pose a significant challenge in MFL, often due to data quality issues or privacy policies across the clients. In this work, we present MMiC, a framework for Mitigating Modality incompleteness in MFL within the Clusters. MMiC replaces partial parameters within client models inside clusters to mitigate the impact of missing modalities. Furthermore, it leverages the Banzhaf Power Index to optimize client selection under these conditions. Finally, MMiC employs an innovative approach to dynamically control global aggregation by utilizing Markovitz Portfolio Optimization. Extensive experiments demonstrate that MMiC consistently outperforms existing federated learning architectures in both global and personalized performance on multimodal datasets with missing modalities, confirming the effectiveness of our proposed solution. Our code is available at https://github.com/gotobcn8/MMiC.

Kolmogorov-Arnold Neural Networks (KANs) have recently attracted significant attention in the machine learning community. However, their practical implementation often faces challenges such as poor training stability and a large number of trainable parameters. Moreover, the behavior of learnable activation functions based on B-splines remains insufficiently understood. In this work, we analyze KANs through the lens of spline knot behavior and derive lower and upper bounds on the number of knots in B-spline-based KANs. To address the existing limitations, we propose a novel KAN-based approach, which improves upon the original KAN by reducing the number of trainable parameters to match the scale of standard Multi-Layer Perceptrons (MLPs), while enhancing overall performance. Additionally, we introduce a new training strategy that enforces C2 continuity in the learnable splines, leading to smoother activation functions and improved training stability via range expansion. We evaluate our method across eight diverse datasets encompassing image, text, time series, multimodal, and function approximation tasks. The promising results demonstrate the feasibility of KAN-based architectures and the effectiveness of our proposed enhancements. The proposed method implementation is released in https://github.com/IcurasLW/FR-KAN.git

Large Language Models (LLMs) have demonstrated impressive performance in time series analysis and seems to understand the time temporal relationship well than traditional transformer-based approaches. However, since LLMs are not designed for time series tasks, simpler models-like linear regressions can often achieve comparable performance with far less complexity. In this study, we perform extensive experiments to assess the effectiveness of applying LLMs to key time series tasks, including forecasting, classification, imputation, and anomaly detection. We compare the performance of LLMs against simpler baseline models, such as single-layer linear models and randomly initialized LLMs. Our results reveal that LLMs offer minimal advantages for these core time series tasks and may even distort the temporal structure of the data. In contrast, simpler models consistently outperform LLMs while requiring far fewer parameters. Furthermore, we analyze existing reprogramming techniques and show, through data manifold analysis, that these methods fail to effectively align time series data with language and display ''pseudo-alignment'' behavior in embedding space. Our findings suggest that the performance of LLM-based methods in time series tasks arises from the intrinsic characteristics and structure of time series data, rather than any meaningful alignment with the language model architecture. We release the code for experiments here: https://github.com/IcurasLW/Official-Repository_Understanding_LLM_for_Time_Series_Analysis.git

Deep Neural Networks (DNNs) are widely used in Natural Language Processing (NLP). However, adversarial samples attack benign inputs to readily fool the DNN models. The detection of these samples is a significant challenge that has received little attention in textual domains. Existing defense strategies either assume prior knowledge of specific threats or do not perform well on complex models. In this article, we provide a new framework, namely TADD for detecting textual adversarial samples by leveraging the interpretability of DNNs. In particular, we distinguish between the adversarial distribution and the benign distribution for the decision boundary of the victim models. Our method applies to NLP tasks and does not require re-training victim models and prior knowledge of adversarial attack methods. We evaluate our detector against the state-of-the-art attack methods on various real-world datasets. As demonstrated in the extensive experiments, our approach effectively discriminates between adversarial and benign samples. Additionally, our method is competitive against unseen attacks, reflecting its ability to discover new adversarial samples generated by future attack methods.

Dynamic Learning-to-Rank (DLTR) is a method of updating a ranking policy in real time based on user feedback, which may not always be accurate. Although previous DLTR work has achieved fair and unbiased DLTR under inaccurate feedback, they face the tradeoff between fairness and user utility and also have limitations in the setting of feeding items. Existing DLTR works improve ranking utility by eliminating bias from inaccurate feedback on observed items, but the impact of another pervasive form of inaccurate feedback, overlooked or ignored interesting items, remains unclear. For example, users may browse the rankings too quickly to catch interesting items or miss interesting items because the snippets are not optimized enough. This phenomenon raises two questions: (i) Will overlooked interesting items affect the ranking results? and (ii) Is it possible to improve utility without sacrificing fairness if these effects are eliminated? These questions are particularly relevant for small and medium-sized retailers who are just starting out and may have limited data, leading to the use of inaccurate feedback to update their models. In this article, we find that inaccurate feedback in the form of overlooked interesting items has a negative impact on DLTR performance in terms of utility. To address this, we treat the overlooked interesting items as noise and propose a novel DLTR method, the Co-teaching Rank (CoTeR), that has good utility and fairness performance when inaccurate feedback is present in the form of overlooked interesting items. Our solution incorporates a co-teaching-based component with a customized loss function and data sampling strategy, as well as a mean pooling strategy to further accommodate newly added products without historical data. Through experiments, we demonstrate that CoTeR not only enhances utilities but also preserves ranking fairness and can smoothly handle newly introduced items.

Recommender systems have become increasingly important in navigating the vast amount of information and options available in various domains. By tailoring and personalizing recommendations to user preferences and interests, these systems improve the user experience, efficiency, and satisfaction. With a growing demand for transparency and understanding of recommendation outputs, explainable recommender systems have gained growing attention in recent years. Additionally, as user reviews could be considered the rationales behind why the user likes (or dislikes) the products, generating informative and reliable reviews alongside recommendations has thus emerged as a research focus in explainable recommendation. However, the model-generated reviews might contain factually inconsistent contents (i.e., the hallucination issue), which would thus compromise the recommendation rationales. To address this issue, we propose a contrastive learning framework to improve the faithfulness and factuality in explainable recommendation in this article. We further develop different strategies of generating positive and negative examples for contrastive learning, such as back-translation or synonym substitution for positive examples, and editing positive examples or utilizing model-generated texts for negative examples. Our proposed method optimizes the model to distinguish faithful explanations (i.e., positive examples) and unfaithful ones with factual errors (i.e., negative examples), which thus drives the model to generate faithful reviews as explanations while avoiding inconsistent contents. Extensive experiments and analysis on three benchmark datasets show that our proposed model outperforms other review generation baselines in faithfulness and factuality. In addition, the proposed contrastive learning component could be easily incorporated into other explainable recommender systems in a plug-and-play manner.

Cold-start recommendation is a well-known problem in practical application scenarios. Generating reliable recommendations can be challenging when interactions are typically sparse. To mitigate the cold-start problem, some methods incorporate auxiliary information about users and items, and others adopt meta-learning to improve recommendation accuracy. However, these approaches overlook the fact that items are interdependent and likely to be related or similar. Moreover, user preference distributions in the meta-training and meta-testing phases are different in the cold-start scenario. To address these problems, we present a novel strategy called Causal Meta-learning with Multi-view Graphs (CausalMMG). Specifically, we first construct multi-view item-item graphs to explore the correlations and similarities between items from multiple perspectives. A multi-view item representer is then used to learn item representations, exploiting graph convolution neural networks to capture the structure of these different item–item graphs. We then resort to the structural causal models of causal inference and further develop a causality-enhanced bi-level adaptive meta-learner to eliminate bias caused by the different distributions of user preferences. Moreover, the meta-learner learns the user preferences for items in different orders through hierarchical and task-level adaptations. Finally, we evaluate CausalMMG on several real-world datasets, demonstrating its effectiveness in various scenarios. The results show that the proposed CausalMMG is significantly superior to competitive baseline methods for cold-start recommendation on all datasets, highlighting the importance of incorporating the multiple relationships between items and modeling different user preference distributions in recommender systems.

Recently, the issue of adversarial robustness in the time series domain has garnered significant attention. However, the available defense mechanisms remain limited, with adversarial training being the predominant approach, though it does not provide theoretical guarantees. Randomized Smoothing has emerged as a standout method due to its ability to certify a provable lower bound on robustness radius under $\ell_p$-ball attacks. Recognizing its success, research in the time series domain has started focusing on these aspects. However, existing research predominantly focuses on time series forecasting, or under the non-$\ell_p$ robustness in statistic feature augmentation for time series classification~(TSC). Our review found that Randomized Smoothing performs modestly in TSC, struggling to provide effective assurances on datasets with poor robustness. Therefore, we propose a self-ensemble method to enhance the lower bound of the probability confidence of predicted labels by reducing the variance of classification margins, thereby certifying a larger radius. This approach also addresses the computational overhead issue of Deep Ensemble~(DE) while remaining competitive and, in some cases, outperforming it in terms of robustness. Both theoretical analysis and experimental results validate the effectiveness of our method, demonstrating superior performance in robustness testing compared to baseline approaches.

Drug-drug interaction (DDI) identification is a crucial aspect of pharmacology research. There are many DDI types (hundreds), and they are not evenly distributed with equal chance to occur. Some of the rarely occurred DDI types are often high risk and could be life-critical if overlooked, exemplifying the long-tailed distribution problem. Existing models falter against this distribution challenge and overlook the multi-faceted nature of drugs in DDI prediction. In this paper, a novel multi-modal deep learning-based framework, namely TFDM, is introduced to leverage multiple properties of a drug to achieve DDI classification. The proposed framework fuses multimodal features of drugs, including graph-based, molecular structure, Target and Enzyme, for DDI identification. To tackle the challenge posed by the distribution skewness across categories, a novel loss function called Tailed Focal Loss is introduced, aimed at further enhancing the model performance and address gradient vanishing problem of focal loss in extremely long-tailed dataset. Intensive experiments over 4 challenging long-tailed dataset demonstrate that the TFMD outperforms the most recent SOTA methods in long-tailed DDI classification tasks. The source code is released to reproduce our experiment results: https://github.com/IcurasLW/TFMD_Longtailed_DDI.git

Irregular Time Series Data (IRTS) has shown increasing prevalence in real-world applications. We observed that IRTS can be divided into two specialized types: Natural Irregular Time Series (NIRTS) and Accidental Irregular Time Series (AIRTS). Various existing methods either ignore the impacts of irregular patterns or statically learn the irregular dynamics of NIRTS and AIRTS data and suffer from limited data availability due to the sparsity of IRTS. We proposed a novel transformer-based framework for general irregular time series data that treats IRTS from four views: Locality, Time, Spatio and Irregularity to motivate the data usage to the highest potential. Moreover, we design a sophisticated irregularity-gate mechanism to adaptively select task-relevant information from irregularity, which improves the generalization ability to various IRTS data. We implement extensive experiments to demonstrate the resistance of our work to three highly missing ratio datasets (88.4%, 94.9%, 60% missing value) and investigate the significance of the irregularity information for both NIRTS and AIRTS by additional ablation study. We release our implementation in https://github.com/IcurasLW/MTSFormer-Irregular_Time_Series.git.

Contrastive learning has been extensively studied in sentence representation learning as it demonstrates effectiveness in various downstream applications, where the same sentence with different dropout masks (or other augmentation methods) is considered as positive pair while taking other sentences in the same mini-batch as negative pairs. However, these methods mostly treat all negative examples equally and overlook the different similarities between the negative examples and the anchors, which thus fail to capture the fine-grained semantic information of the sentences. To address this issue, we explicitly differentiate the negative examples by their similarities with the anchor, and thus propose a simple yet effective method SoftCSE that individualizes either the weight or temperature of each negative pair in the standard InfoNCE loss according to the similarities of the negative examples and the anchors. We further provide the theoretical analysis of our methods to show why and how SoftCSE works, including the optimal solution, gradient analysis and the connection with other loss. Empirically, we conduct extensive experiments on semantic textual similarity (STS) and transfer (TR) tasks, as well as text retrieval and reranking, where we observe significant performance improvements compared to strong baseline models.

User engagement has recently received significant attention in understanding the decay and expansion of communities in many online social networking platforms. Many user engagement studies have been conducted to find a set of critical (anchored) users in the static social network. However, social networks are highly dynamic and their structures are continuously evolving. In this paper, we target a new research problem called Anchored Vertex Tracking (AVT), aiming to track the anchored users at each timestamp of evolving networks. To address the AVT problem, we develop a greedy algorithm inspired by the previous anchored k-core study in the static networks. Furthermore, we design an incremental algorithm to efficiently solve the AVT problem by utilizing the smoothness of the network structure's evolution. The extensive experiments demonstrate the performance of our proposed algorithms.

Influence Maximization(IM), which aims to select a set of users from a social network to maximize the expected number of influenced users, has recently received significant attention for mass communication and commercial marketing. Existing research efforts dedicated to the IM problem depend on a strong assumption: the selected seed users are willing to spread the information after receiving benefits from a company or organization. In reality, however, some seed users may be reluctant to spread the information or need to be paid higher to be motivated. Furthermore, the existing IM works pay little attention to capture users’ influence propagation in the future period. In this paper, we target a new research problem named,ReconnectingTop-$l$lRelationships(RT$l$R) query, which aims to find$l$number of previous existing relationships but being estranged later such that reconnecting these relationships will maximize the expected number of influenced users by the given group in a future period. We prove that the RT$l$R problem is NP-hard. An efficient greedy algorithm is proposed to answer the RT$l$R queries with the influence estimation technique and the well-chosen link prediction method to predict the near future network structure. We also design a pruning method to reduce unnecessary probing from candidate edges. Further, a carefully designed order-based algorithm is proposed to accelerate the RT$l$R queries. Finally, we conduct extensive experiments on real-world datasets to demonstrate the effectiveness and efficiency of our proposed methods.

Summarising from the Web could be formed as a problem of multi-document Summarisaiton (MDS) from multiple sources. In contrast to the current MDS problem that involves working on benchmark datasets which provide well clustered set of documents, we envisage to build a pipeline for content Summarisaiton from the Web, but narrow down to the Social Internet of Things (SIoT) paradigm, starting at data collection from the IoT objects, then applying natural language processing techniques for grouping and summarising the data, to distributing summaries back to the IoT objects. In this paper, we present our simulation tool, SimSumIoT, that simulates the process of data sharing, receiving, clustering, and Summarisaiton. A Web-based interface is developed for this purpose allowing users to visualize the process through a set of interactions. The Web interface is accessible via http://simsumlot.tk.

User engagement has recently received significant attention in understanding the decay and expansion of communities in many online social networking platforms. When a user chooses to leave a social networking platform, it may cause a cascading dropping out among her friends. In many scenarios, it would be a good idea to persuade critical users to stay active in the network and prevent such a cascade because critical users can have significant influence on user engagement of the whole network. Many user engagement studies have been conducted to find a set of critical(anchored)users in the static social network. However, social networks are highly dynamic and their structures are continuously evolving. In order to fully utilize the power of anchored users in evolving networks, existing studies have to mine multiple sets of anchored users at different times, which incurs an expensive computational cost. To better understand user engagement in evolving network, we target a new research problem calledAnchored Vertex Tracking(AVT) in this paper, aiming to track the anchored users at each timestamp of evolving networks. Nonetheless, it is nontrivial to handle the AVT problem which we have proved to be NP-hard. To address the challenge, we develop a greedy algorithm inspired by the previous anchored$k$-core study in the static networks. Furthermore, we design an incremental algorithm to efficiently solve the AVT problem by utilizing the smoothness of the network structure's evolution. The extensive experiments conducted on real and synthetic datasets demonstrate the performance of our proposed algorithms and the effectiveness in solving the AVT problem.

Abstract Question answering (QA) systems provide a way of querying the information available in various formats including, but not limited to, unstructured and structured data in natural languages. It constitutes a considerable part of conversational artificial intelligence (AI) which has led to the introduction of a special research topic on conversational question answering (CQA), wherein a system is required to understand the given context and then engages in multi-turn QA to satisfy a user’s information needs. While the focus of most of the existing research work is subjected to single-turn QA, the field of multi-turn QA has recently grasped attention and prominence owing to the availability of large-scale, multi-turn QA datasets and the development of pre-trained language models. With a good amount of models and research papers adding to the literature every year recently, there is a dire need of arranging and presenting the related work in a unified manner to streamline future research. This survey is an effort to present a comprehensive review of the state-of-the-art research trends of CQA primarily based on reviewed papers over the recent years. Our findings show that there has been a trend shift from single-turn to multi-turn QA which empowers the field of Conversational AI from different perspectives. This survey is intended to provide an epitome for the research community with the hope of laying a strong foundation for the field of CQA.

Medical decision-making is guided by the results of rich medical research and clinical trials. Doctors, practitioners and researchers urgently need to get updated by the most recent research and clinical outputs to make correct decisions, especially when a new virus such as Covid-19 is causing a global epidemic. However, medical literature for a certain topic could be from different aspects thus archived in different literature databases, resulting in the searching for all related articles become a laborious and time-consuming task. It becomes worse when there is a rapid growth of the number of published literature for the given topic. In this work, we build an online knowledge hub (http://covid19knowledgehub.herokuapp.com/) particularly for Covid-19 related research articles per the requirement from researchers in a hospital. The system is built on top of nine medical research article databases, which covers a wide range of medical aspects. It allows users to easily retrieve and explore the articles from multiple literature databases at one-stop. The system also provides the statistics of article distributions to offer an overview of the status of research under this topic. This real-demand driven system is deployed in a research team of Renmin Hospital, Wuhan University, and largely reduces their time for searching the latest articles. Although this project focuses on Covid-19 related research articles, the approach at the back could be applied to any topic in any domain.

Adversarial attacks pose significant challenges for detecting adversarial attacks at an early stage. We propose attack-agnostic detection on reinforcement learning-based interactive recommendation systems. We first craft adversarial examples to show their diverse distributions and then augment recommendation systems by detecting potential attacks with a deep learning-based classifier based on the crafted data. Finally, we study the attack strength and frequency of adversarial examples and evaluate our model on standard datasets with multiple crafting methods. Our extensive experiments show that most adversarial attacks are effective, and both attack strength and attack frequency impact the attack performance. The strategically-timed attack achieves comparative attack performance with only 1/3 to 1/2 attack frequency. Besides, our black-box detector trained with one crafting method has the generalization ability over several crafting methods.

Truth discovery has been widely studied in recent years as a fundamental means for resolving the conflicts in multi-source data. Although many truth discovery methods have been proposed based on different considerations and intuitions, investigations show that no single method consistently outperforms the others. To select the right truth discovery method for a specific application scenario, it becomes essential to evaluate and compare the performance of different methods. A drawback of current research efforts is that they commonly assume the availability of certain ground truth for the evaluation of methods. However, the ground truth may be very limited or even impossible to obtain, rendering the evaluation biased. In this article, we present CompTruthHyp , a generic approach for comparing the performance of truth discovery methods without using ground truth. In particular, our approach calculates the probability of observations in a dataset based on the output of different methods. The probability is then ranked to reflect the performance of these methods. We review and compare 12 representative truth discovery methods and consider both single-valued and multi-valued objects. The empirical studies on both real-world and synthetic datasets demonstrate the effectiveness of our approach for comparing truth discovery methods.

With the development of high computational devices, deep neural networks (DNNs), in recent years, have gained significant popularity in many Artificial Intelligence (AI) applications. However, previous efforts have shown that DNNs are vulnerable to strategically modified samples, named adversarial examples . These samples are generated with some imperceptible perturbations, but can fool the DNNs to give false predictions. Inspired by the popularity of generating adversarial examples against DNNs in Computer Vision (CV), research efforts on attacking DNNs for Natural Language Processing (NLP) applications have emerged in recent years. However, the intrinsic difference between image (CV) and text (NLP) renders challenges to directly apply attacking methods in CV to NLP. Various methods are proposed addressing this difference and attack a wide range of NLP applications. In this article, we present a systematic survey on these works. We collect all related academic works since the first appearance in 2017. We then select, summarize, discuss, and analyze 40 representative works in a comprehensive way. To make the article self-contained, we cover preliminary knowledge of NLP and discuss related seminal works in computer vision. We conclude our survey with a discussion on open issues to bridge the gap between the existing progress and more robust adversarial attacks on NLP DNNs.

Plenty of research attempts target the automatic duplicate detection in Community Question Answering (CQA) systems and frame the task as a supervised learning problem on the question pairs. However, these methods rely on handcrafted features, leading to the difficulty of distinguishing related and duplicate questions as they are often textually similar. To tackle this issue, we propose to leverage neural network architecture to extract "deep" features to identify whether a question pair is duplicate or related. In particular, we construct question correlation matrices, which capture the word-wise similarities between questions. The constructed matrices are input to our proposed convolutional neural network (CNN), in which the convolutional operation moves through the two dimensions of the matrices. Empirical studies on a range of real-world CQA datasets confirm the effectiveness of our proposed correlation matrices and the CNN. Our method outperforms the state-of-the-art methods and achieves better classification performance.

Programming community-based question-answering (PCQA) websites such as Stack Overflow enable programmers to find working solutions to their questions. Despite detailed posting guidelines, duplicate questions that have been answered are frequently created. To tackle this problem, Stack Overflow provides a mechanism for reputable users to manually mark duplicate questions. This is a laborious effort, and leads to many duplicate questions remain undetected. Existing duplicate detection methodologies from traditional community based question-answering (CQA) websites are difficult to be adopted directly to PCQA, as PCQA posts often contain source code which is linguistically very different from natural languages. In this paper, we propose a methodology designed for the PCQA domain to detect duplicate questions. We model the detection as a classification problem over question pairs. To extract features for question pairs, our methodology leverages continuous word vectors from the deep learning literature, topic model features and phrases pairs that co-occur frequently in duplicate questions mined using machine translation systems. These features capture semantic similarities between questions and produce a strong performance for duplicate detection. Experiments on a range of real-world datasets demonstrate that our method works very well; in some cases over 30% improvement compared to state-of-the-art benchmarks. As a product of one of the proposed features, the association score feature, we have mined a set of associated phrases from duplicate questions on Stack Overflow and open the dataset to the public.

How to accurately forecast seasonal time series is very important for many business area such as marketing decision, planning production and profit estimation. In this paper, we propose a weighted gradient Radial Basis Function Network based AutoRegressive (WGRBF-AR) model for modeling and predicting the nonlinear and non-stationary seasonal time series. This WGRBF-AR model is a synthesis of the weighted gradient RBF network and the functional-coefficient autoregressive (FAR) model through using the WGRBF networks to approximate varying coefficients of FAR model. It not only takes the advantages of the FAR model in nonlinear dynamics description but also inherits the capability of the WGRBF network to deal with non-stationarity. We test our model using ten-years retail sales data on five different commodity in US. The results demonstrate that the proposed WGRBF-AR model can achieve competitive prediction accuracy compared with the state-of-the-art.

In the era of the Internet of Things, enormous number of sensors have been deployed in different locations, generating massive time-series sensory data with geo-tags. However, such sensory readings are easily missing due to various reasons such as the hardware malfunction, connection errors, and data corruption. This paper focuses on this challenge--how to accurately yet efficiently recover the missing values for corrupted time-series sensor data with geo-stamps. In this paper, we formulate the time-series sensor data as a 3-order tensor that naturally preserves sensors' temporal and spatial dependencies. Then we exploit its low-rank and sparse-noise structures by drawing upon recent advances in Robust Principal Component Analysis (RPCA) and tensor completion theory. The main novelty of this paper lies in that, we design a highly efficient optimization method that combines the alternating direction method of multipliers and accelerated proximal gradient to recover the data tensor. Besides testing our method using the synthetic data, we also design a real-world testbed by passive RFID (RadioFrequency IDentification) sensors. The results demonstrate the effectiveness and accuracy of our approach.

Orthogonal Non-negative Matrix Factorization (ONMF) approximates a data matrix X by the product of two lower dimensional factor matrices: X -- UVT, with one of them orthogonal. ONMF has been widely applied for clustering, but it often suffers from high computational cost due to the orthogonality constraint. In this paper, we propose a method, called Nonlinear Riemannian Conjugate Gradient ONMF (NRCG-ONMF), which updates U and V alternatively and preserves the orthogonality of U while achieving fast convergence speed. Specifically, in order to update U, we develop a Nonlinear Riemannian Conjugate Gradient (NRCG) method on the Stiefel manifold using Barzilai-Borwein (BB) step size. For updating V, we use a closed-form solution under non-negativity constraint. Extensive experiments on both synthetic and real-world data sets show consistent superiority of our method over other approaches in terms of orthogonality preservation, convergence speed and clustering performance.

Shortest path computation is one of the most fundamental operations for managing and analyzing graphs. A number of methods have been proposed to answer shortest path distance queries on static graphs. Unfortunately, there is little work on answering distance queries on dynamic graphs, particularly graphs with edge failures. Today’s real-world graphs, such as the social network graphs and web graphs, are evolving all the time and link failures occur due to various factors, such as people stopping following others on Twitter or web links becoming invalid. Therefore, it is of great importance to handle distance queries on these failureprone graphs. This is not only a problem far more difficult than that of static graphs but also important for processing distance queries on evolving or unstable networks. In this paper, we focus on the problem of computing the shortest path distance on graphs subject to edge failures. We propose SIEF, a Supplemental Index for Edge Failures on a graph, which is based on distance labeling. Together with the original index created for the original graph, SIEF can support distance queries with edge failures efficiently. By exploiting properties of distance labeling on static graphs, we are able to compute very compact distance labeling for all singe-edge failure cases on dynamic graphs. We extensively evaluate our algorithms using six real-world graphs and confirm the effectiveness and efficiency of our approach.

Semantic technologies aim to facilitate machine-to-machine communication and are attracting more and more interest from both academia and industry, especially in the emerging Internet of Things (IoT). In this paper, we consider large-scale information sharing scenarios among mobile objects in IoT by leveraging semantic techniques. We propose to broadcast Linked Data on-air using RDF format to allow simultaneous access to the information and to achieve better scalability. We introduce a novel air indexing method to reduce the information access latency and energy consumption. To build air indexes, we firstly map RDF triples in the Linked Data into points in a 3D space and build B+-trees based on 3D Hilbert curve mappings for all of the 3D points. We then convert these trees into linear sequences so that they can be broadcast over a wireless channel. A novel search algorithm is also designed to efficiently evaluate queries against the air indexes. Experiments show that our indexing method outperforms the air indexing method based on traditional 3D R-trees.

We propose a two-stage lossless compression approach on large scale RDF data. Our approach exploits both Representation Compression and Component Compression techniques to support query and dynamic operations directly on the compressed data.