As Large Language Models (LLMs) grow increasingly powerful, ensuring their safety and alignment with human values remains a critical challenge.Ideally, LLMs should provide informative responses while avoiding harmful or sensitive disclosures.However, current alignment strategies, reliant on binary refusal (e.g., rejecting prompts or coarse filtering), lack nuance.This leads to overcensorship, failure to detect subtle harm (like withholding public medication information due to misuse concerns), and difficulty with mixed or context-dependent sensitivities, often overcensoring benign content.To overcome these challenges, we introduce HIDDENGUARD, a novel framework for fine-grained, safe generation in LLMs.HIDDENGUARD incorporates PRISM (Representation Router for In-Stream Moderation), which operates alongside the LLM to enable real-time, token-level detection and redaction of harmful content by leveraging intermediate hidden states.This fine-grained approach allows for more nuanced, contextaware moderation, enabling the model to generate informative responses while selectively redacting or replacing sensitive information, rather than outright refusal.We also contribute a comprehensive dataset with token-level finegrained annotations of potentially harmful information across diverse contexts.Our experiments demonstrate that HIDDENGUARD achieves over 90% in F 1 score for detecting and redacting harmful content while preserving the overall utility and informativeness of the model's responses.

Lingrui Mei, Shenghua Liu, Yiwei Wang, Yuyao Ge, Baolong Bi, Jiayu Yao, Jun Wan, Ziling Yin, Jiafeng Guo, Xueqi Cheng. Proceedings of the 64th Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers). 2026.

Baolong Bi, Shenghua Liu, Lingrui Mei, Yiwei Wang, Junfeng Fang, Pengliang Ji, Xueqi Cheng. Proceedings of the 63rd Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers). 2025.

Yuyao Ge, Shenghua Liu, Baolong Bi, Yiwei Wang, Lingrui Mei, Wenjie Feng, Lizhe Chen, Xueqi Cheng. Proceedings of the 63rd Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers). 2025.

“Jailbreak” is a major safety concern of Large Language Models (LLMs), which occurs when malicious prompts lead LLMs to produce harmful outputs, raising issues about the reliability and safety of LLMs. Therefore, an effective evaluation of jailbreaks is very crucial to develop its mitigation strategies. However, our research reveals that many jailbreaks identified by current evaluations may actually be hallucinations—erroneous outputs that are mistaken for genuine safety breaches. This finding suggests that some perceived vulnerabilities might not represent actual threats, indicating a need for more precise red teaming benchmarks. To address this problem, we propose the Benchmark for reliABilitY and jailBreak haLlUcination Evaluation (BabyBLUE). BabyBLUE introduces a specialized validation framework including various evaluators to enhance existing jailbreak benchmarks, ensuring outputs are useful malicious instructions. Additionally, BabyBLUE presents a new dataset as an augmentation to the existing red teaming benchmarks, specifically addressing hallucinations in jailbreaks, aiming to evaluate the true potential of jailbroken LLM outputs to cause harm to human society.

Multimodal Retrieval-Augmented Generation (RAG) systems have become essential in knowledge-intensive and open-domain tasks.As retrieval complexity increases, ensuring the robustness of these systems is critical.However, current RAG models are highly sensitive to the order in which evidence is presented, often resulting in unstable performance and biased reasoning, particularly as the number of retrieved items or modality diversity grows.This raises a central question: How does the position of retrieved evidence affect multimodal RAG performance?To answer this, we present the first comprehensive study of position bias in multimodal RAG systems.Through controlled experiments across text-only, imageonly, and mixed-modality tasks, we observe a consistent U-shaped accuracy curve with respect to evidence position.To quantify this bias, we introduce the Position Sensitivity Index (P SI p ) and develop a visualization framework to trace attention allocation patterns across decoder layers.Our results reveal that multimodal interactions intensify position bias compared to unimodal settings, and that this bias increases logarithmically with retrieval range.These findings offer both theoretical and empirical foundations for position-aware analysis in RAG, highlighting the need for evidence reordering or debiasing strategies to build more reliable and equitable generation systems.Our code and experimental resources are available at https://github.com/Theodyy/ Multimodal-Rag-Position-Bias.

As the modern tools of choice for text understanding and generation, large language models (LLMs) are expected to accurately output answers by leveraging the input context. This requires LLMs to possess both context-faithfulness and factual accuracy. While extensive efforts aim to reduce hallucinations through factuality enhancement methods, they also pose risks of hindering context-faithfulness, as factuality enhancement can lead LLMs to become overly confident in their parametric knowledge, causing them to overlook the relevant input context. In this work, we argue that current factuality enhancement methods can significantly undermine the context-faithfulness of LLMs. We first revisit the current factuality enhancement methods and evaluate their effectiveness in enhancing factual accuracy. Next, we evaluate their performance on knowledge editing tasks to assess the potential impact on context-faithfulness. The experimental results reveal that while these methods may yield inconsistent improvements in factual accuracy, they also cause a more severe decline in context-faithfulness, with the largest decrease reaching a striking 69.7\%. To explain these declines, we analyze the hidden states and logit distributions for the tokens representing new knowledge and parametric knowledge respectively, highlighting the limitations of current approaches. Our finding highlights the complex trade-offs inherent in enhancing LLMs. Therefore, we recommend that more research on LLMs' factuality enhancement make efforts to reduce the sacrifice of context-faithfulness.

The dynamic nature of language, particularly evident in the realm of slang and memes on the Internet, poses serious challenges to the adaptability of Large Language Models (LLMs).Traditionally anchored to static datasets, these models often struggle to keep up with the rapid linguistic evolution characteristic of online communities.This research aims to bridge this gap by enhancing LLMs' comprehension of the evolving new concepts on the Internet, without the high cost of continual retraining.In pursuit of this goal, we introduce SLANG, a benchmark designed to autonomously integrate novel data and assess LLMs' ability to comprehend emerging concepts, alongside FOCUS, an approach uses causal inference to enhance LLMs to understand new phrases and their colloquial context.Our benchmark and approach involves understanding real-world instances of linguistic shifts, serving as contextual beacons, to form more precise and contextually relevant connections between newly emerging expressions and their meanings.The empirical analysis shows that our causal inference-based approach outperforms the baseline methods in terms of precision and relevance in the comprehension of Internet slang and memes. 1

How does the graph change if we summarize it by merging nodes? How can we summarize the graph while preserving its spectral characteristics? Graph summarization aims to present a graph in a compact summary graph form while keeping its important structural information. Existing methods primarily focus on preserving the adjacency matrix. In contrast, spectral graph theory provides a powerful tool to describe the characteristics of a graph. In this paper, we propose a novel graph summarization method that preserves the spectral characteristics, including spectral moments and heat traces. We analyze the change of the spectral characteristics after summarization and design a simple yet effective summarization method based on agglomerative clustering. Our approach is extensively evaluated on real-world datasets. The experimental results show that our method excels in preserving the spectral characteristics and obtains better performance on the subsequent graph classification task.

Graph summarization is a useful tool for analyzing large-scale graphs. Some works tried to preserve original node embeddings encoding rich structural information of nodes on the summary graph. However, their algorithms are designed heuristically and not theoretically guaranteed. In this article, we theoretically study the problem of preserving node embeddings on summary graph. We prove that three matrix-factorization-based node embedding methods of the original graph can be approximated by that of the summary graph, and we propose a novel graph summarization method, named HCSumm , based on this analysis. Extensive experiments are performed on real-world datasets to evaluate the effectiveness of our proposed method. The experimental results show that our method outperforms the state-of-the-art methods in preserving node embeddings.

How can we effectively detect fake reviews or fraudulent links on a website? How can we spot communities that suddenly appear based on users’ interactions? And how can we efficiently find the minimum cut in a large graph? All of these are related to the finding of dense subgraphs, a significant primitive problem in graph analysis with extensive applications across various domains. In this paper, we focus on formulating the problem of the densest subgraph detection and theoretically compare and contrast several correlated problems. Moreover, we propose a unified framework,GenDS, for the densest subgraph detection, provide some theoretical analysis based on the network flow and spectral graph theory, and devise simple and computationally efficient algorithms,SpecGDSandGepGDS, to solve it by leveraging the spectral properties and greedy search. We conduct thorough experiments on 40 real-world networks with up to 1.47 billion edges from various domains. We demonstrate that ourSpecGDSyields up to$58.6 \ \times$speedup and achieves better or approximately equal-quality solutions for the densest subgraph detection compared to the baselines.GepGDSalso reveals some properties of generalized eigenvalue problems for theGenDS. Also, our methods scale linearly with the graph size and are proven effective in applications such as finding collaborations that appear suddenly in an extensive, time-evolving co-authorship network.

Given a heterogeneous multilayer network with various connections in pharmacology, how can we detect components with intensive interactions and strong dependencies? Can we accurately capture suspicious groups in a multi-lot transaction network under camouflage? These challenges related to dense subgraph detection have been extensively studied in simple graphs (such as bipartite graph, multi-view network) but remain under-explored on complex networks. Existing methods struggle to effectively handle theintricate dependencies, let alone accurately identify theinterrelated dense connected patternswithin a series of complex heterogeneous networks. In this paper, we proposeInDuen, a novel algorithm designed to detect interrelated densest subgraphs in multilayer networks through joint optimization of coupled factorization and local search for an elaborate-designed joint density measure. It is(a)effective for both large synthetic and real networks,(b)resistant to camouflage for anomaly detection, and(c)linearly scalable. Experimental results demonstrate thatInDuenoutperforms the state-of-the-art baselines in accurately detecting interrelated densest subgraphs under various settings. Furthermore,InDuenuncovers some intriguing patterns in real-world data, i.e., closely cooperated academic groups and interrelated dependent functional components in biology-net.InDuenachieves more than$35 \times$speedup compared to the SOTA methodDestine.

Given a large graph, can we learn its node embeddings from a smaller summary graph? What is the relationship between embeddings learned from original graphs and their summary graphs? Graph representation learning plays an important role in many graph mining applications, but learning em-beddings of large-scale graphs remains a challenge. Recent works try to alleviate it via graph summarization, which typ-ically includes the three steps: reducing the graph size by combining nodes and edges into supernodes and superedges,learning the supernode embedding on the summary graph and then restoring the embeddings of the original nodes. How-ever, the justification behind those steps is still unknown. In this work, we propose GELSUMM, a well-formulated graph embedding learning framework based on graph sum-marization, in which we show the theoretical ground of learn-ing from summary graphs and the restoration with the three well-known graph embedding approaches in a closed form.Through extensive experiments on real-world datasets, we demonstrate that our methods can learn graph embeddings with matching or better performance on downstream tasks.This work provides theoretical analysis for learning node em-beddings via summarization and helps explain and under-stand the mechanism of the existing works.

With the rapid development of electronic payment, risks in large-scale financial transaction networks are persistently arising. One important problem is how to use the transaction data to detect sellers who do fraudulent trades on the online platform. This paper analyzes three attributes of the transaction flow: money (what), time (when), region (where), and summarizes corresponding characteristics among fraudulent sellers. Based on this, we propose an unsupervised anomaly detection algorithm: W3Detector. It processes the raw data with a new sequence discretization method and uses statistical tools to convert data indicators into information value. With the minimum description length principle, we finally filter out the suspicious sellers. The algorithm is not affected by factors such as unit or range of the attributes, and is highly flexible and scalable. After running on three real-world transaction datasets collected from WeChat Pay, W3Detector has show significantly better performance than the baseline methods of anomaly detection, with weighted accuraccy (WACC) increased by 1.13X and F-score increased by 0.105 on average, and the recall value over 60%.

This study proposes a minimum cost consensus-based failure mode and effect analysis (MCC-FMEA) framework considering experts' limited compromise and tolerance behaviors, where the first behavior indicates that a failure mode and effect analysis (FMEA) expert might not tolerate modifying his/her risk assessment without limitations, and the second behavior indicates that an FMEA expert will accept risk assessment suggestions without being paid for any cost if the suggested risk assessments fall within his/her tolerance threshold. First, an MCC-FMEA with limited compromise behaviors is presented. Second, experts' tolerance behaviors are added to the MCC-FMEA with limited compromise behaviors. Theoretical results indicate that in some cases, this MCC-FMEA with limited compromise and tolerance behaviors has no solution. Thus, a minimum compromise adjustment consensus model and a maximum consensus model with limited compromise behaviors are developed and analyzed, and an interactive MCC-FMEA framework, resulting in an FMEA problem consensual collective solution, is designed. A case study, regarding the assessment of COVID-19-related risk in radiation oncology, and a detailed sensitivity and comparative analysis with the existing FMEA approaches are provided to verify the effectiveness of the proposed approach to FMEA consensus-reaching.

Dense subtensor detection gains remarkable success in spotting anomalies and fraudulent behaviors for multi-aspect data (i.e., tensors), like in social media and event streams. Existing methods detect the densest subtensors flatly and separately, with the underlying assumption that those subtensors are exclusive. However, many real-world tensors usually present hierarchical properties, e.g., the core-periphery structure and dynamic communities in networks. It is also unexplored how to fuse the prior knowledge into dense pattern detection to capture the local behavior. In this article, we propose CatchCore , a novel framework to efficiently find the hierarchical dense subtensors. We first design a unified metric for dense subtensor detection, which can be optimized with gradient-based methods. With the proposed metric, CatchCore detects hierarchical dense subtensors through the hierarchy-wise alternative optimization and finds local dense patterns concerning some items in a query manner. Finally, we utilize the minimum description length principle to measure the quality of detection results and select the optimal hierarchical dense subtensors. Extensive experiments on synthetic and real-world datasets demonstrate that CatchCore outperforms the top competitors in accuracy for detecting dense subtensors and anomaly patterns, like network attacks. Additionally, CatchCore successfully identifies a hierarchical researcher co-authorship group with intense interactions in the DBLP dataset; it can also capture core collaboration and multi-hop relations around some query objects. Meanwhile, CatchCore also scales linearly with all aspects of tensors.

Time series data naturally exist in many domains including medical data analysis, infrastructure sensor monitoring, and motion tracking. However, a very small portion of anomalous time series can be observed, comparing to the whole data. Most existing approaches are based on the supervised classification model requiring representative labels for anomaly class(es), which is challenging in real-world problems. So can we learn how to detect anomalous time ticks in an effective yet efficient way, given mostly normal time series data? Therefore, we propose an unsupervised reconstruction model named BeatGAN which learns to detect anomalies based on normal data, or data which majority of samples are normal. BeatGAN provides a framework to adversarially learn to reconstruct, which can cooperate with both 1-d CNN and RNN. Rarely observed anomalies can result in larger reconstruction errors, which are then detected based on extreme value theory. Moreover, data augmentation with dynamic time warping regularizes reconstruction and provides robustness. In the experiments, effectiveness and sensitivity are studied in both synthetic data and various real-world time series. BeatGAN achieves better accuracy and fast inference.

Given a stream of money transactions between accounts in a bank, how can we accurately detect money laundering agent accounts and suspected behaviors in real-time? Money laundering agents try to hide the origin of illegally obtained money by dispersive multiple small transactions and evade detection by smart strategies. Therefore, it is challenging to accurately catch such fraudsters in an unsupervised manner. Existing approaches do not consider the characteristics of those agent accounts and are not suitable to the streaming settings. Therefore, we propose MonLAD and MonLAD-W to detect money laundering agent accounts in a transaction stream by keeping track of their residuals and other features; we devise AnoScore algorithm to find anomalies based on the robust measure of statistical deviation. Experimental results show that MonLAD outperforms the state-of-the-art baselines on real-world data and finds various suspicious behavior patterns of money laundering. Additionally, several detected suspected accounts have been manually-verified as agents in real money laundering scenario.

How can we track synchronized behavior in a stream of time-stamped tuples, such as mobile devices installing and uninstalling applications in the lockstep, to boost their ranks in the app store? We model such tuples as entries in a streaming tensor, which augments attribute sizes in its modes over time. Synchronized behavior tends to form dense blocks (i.e.~subtensors) in such a tensor, signaling anomalous behavior, or interesting communities. However, existing dense block detection methods are either based on a static tensor, or lack an efficient algorithm in a streaming setting. Therefore, we propose a fast streaming algorithm, AUGSPLICING, which can detect the top dense blocks by incrementally splicing the previous detection with the incoming ones in new tuples, avoiding re-runs over all the history data at every tracking time step. AUGSPLICING is based on a splicing condition that guides the algorithm (Section 4). Compared to the state-of-the-art methods, our method is (1) effective to detect fraudulent behavior in installing data of real-world apps and find a synchronized group of students with interesting features in campus Wi-Fi data; (2) robust with splicing theory for dense block detection; (3) streaming and faster than the existing streaming algorithm, with closely comparable accuracy.

Given a large graph, how can we summarize it with fewer nodes and edges while maintaining its key properties, e.g.node degrees and graph spectrum?As a solution, graph summarization, which aims to find the compact representation for optimally describing and reconstructing a given graph, has received much attention, and numerous methods have been developed for it.However, many existing methods adopt the uniform reconstruction scheme, which is an unrealistic assumption as most real-world graphs have highly skewed node degrees, even within communities.Therefore we propose a degree-preserving graph summarization model, DPGS, with a novel reconstruction scheme based on the configuration model.To optimize the Minimum Description Length of our model, we deisgn a linearly scalable algorithm using hashing techniques.We theoretically show that the minimized reconstruction error bounds the perturbation of graph spectral information.Extensive experiments on realworld datasets show that DPGS yields more accurate summary graphs than several well-known baselines.Moreover, our reduced summary graphs can effectively train graph neural networks (GNNs) while saving computational cost.

Given a graph of the money transfers between accounts of a bank, how can we detect money laundering? Money laundering refers to criminals using the bank's services to move massive amounts of illegal money to untraceable destination accounts, in order to inject their illegal money into the legitimate financial system. Existing graph fraud detection approaches focus on dense subgraph detection, without considering the fact that money laundering involves high-volume flows of funds through chains of bank accounts, thereby decreasing their detection accuracy. Instead, we propose to model the transactions using a multipartite graph, and detect the complete flow of money from source to destination using a scalable algorithm, FlowScope. Theoretical analysis shows that FlowScope provides guarantees in terms of the amount of money that fraudsters can transfer without being detected. FlowScope outperforms state-of-the-art baselines in accurately detecting the accounts involved in money laundering, in both injected and real-world data settings.

Graph Convolutional Networks (GCNs) have achieved state-of-the-art performance on node classification. However, recent works have shown that GCNs are vulnerable to adversarial attacks, such as additions or deletions of adversarially-chosen edges in the graph, in order to mislead the node classification algorithms. How can we design robust GCNs that are resistant to such adversarial attacks? More challengingly, how can we do this in a way that is provably robust? We propose a robust node classification approach based on a low-pass `message passing' mechanism, that (a) reduces the effectiveness of adversarial attacks in experiments, and (b) provides theoretical guarantees against adversarial attacks. Our approach can be embedded into the existing GCN architectures to enhance their robustness. Empirical results show that our loss-pass method effectively improves the performance of multiple GCNs under miscellaneous perturbations and helps them to achieve superior performance on various graphs.

A model-based collaborative filtering (CF) approach utilizing fast adaptive randomized singular value decomposition (SVD) is proposed for the matrix completion problem in recommender system. Firstly, a fast adaptive PCA framework is presented which combines the fixed-precision randomized matrix factorization algorithm [1] and accelerating skills for handling large sparse data. Then, a novel termination mechanism for the adaptive PCA is proposed to automatically determine a number of latent factors for achieving the near optimal prediction accuracy during the subsequent model-based CF. The resulted CF approach has good accuracy while inheriting high runtime efficiency. Experiments on real data show that, the proposed adaptive PCA is up to 2.7X and 6.7X faster than the original fixed-precision SVD approach [1] and svds in Matlab repsectively, while preserving accuracy. The proposed model-based CF approach is able to efficiently process the MovieLens data with 20M ratings and exhibits more than 10X speedup over the regularized matrix factorization based approach [2] and the fast singular value thresholding approach [3] with comparable or better accuracy. Compared with the deep-learning-based CF approach, the proposed approach is much more computationally efficient, with just marginal performance loss.

How can one quickly answer the most and top popular objects at any time, given a large log stream in a system of billions of users? It is equivalent to find the mode and top-frequent elements in a dynamic array corresponding to the log stream. However, most existing work either restrain the dynamic array within a sliding window, or do not take advantages of only one element can be added or removed in a log stream. Therefore, we propose a profiling algorithm, named S-Profile, which is of $O(1)$ time complexity for every updating of the dynamic array, and optimal in terms of computational complexity. With the profiling results, answering the queries on the statistics of dynamic array becomes trivial and fast. With the experiments of various settings of dynamic arrays, our accurate S-Profile algorithm outperforms the well-known methods, showing at least 2X speedup to the heap based approach and 13X or larger speedup to the balanced tree based approach.

Given a large-scale rhythmic time series containing mostly normal data segments (or `beats'), can we learn how to detect anomalous beats in an effective yet efficient way? For example, how can we detect anomalous beats from electrocardiogram (ECG) readings? Existing approaches either require excessively high amounts of labeled and balanced data for classification, or rely on less regularized reconstructions, resulting in lower accuracy in anomaly detection. Therefore, we propose BeatGAN, an unsupervised anomaly detection algorithm for time series data. BeatGAN outputs explainable results to pinpoint the anomalous time ticks of an input beat, by comparing them to adversarially generated beats. Its robustness is guaranteed by its regularization of reconstruction error using an adversarial generation approach, as well as data augmentation using time series warping. Experiments show that BeatGAN accurately and efficiently detects anomalous beats in ECG time series, and routes doctors' attention to anomalous time ticks, achieving accuracy of nearly 0.95 AUC, and very fast inference (2.6 ms per beat). In addition, we show that BeatGAN accurately detects unusual motions from multivariate motion-capture time series data, illustrating its generality.

Consider a stream of time-stamped events, such as taxi rides, where we record the start and end locations of each ride. How do we learn a matrix factorization model which takes into account seasonal patterns (such as: rides toward office areas occur more frequently in the morning), and use it to forecast taxi rides tomorrow? Also, how can we model drift (such as population growth), and detect sudden changes (or anomalies)? Existing matrix factorization algorithms do not take seasonal patterns into account. We propose SMF (Seasonal Matrix Factorization), a matrix factorization model for seasonal data, and a streaming algorithm for fitting it. SMF is (a) accurate in forecasting: outperforming baselines by 13% to 60% in RMSE; (b) online: requiring fixed memory even as more data is received over time, and scaling linearly; (c) effective: providing interpretable results. In addition, we propose SMF-A, an algorithm which detects anomalies in a computationally feasible way, without forecasting every observation in the matrix.

How to quantify influences between users, seeing that social network users influence each other in their temporal behaviors? Previous work has directly defined an independent model parameter to capture the interpersonal influence between each pair of users. To do so, these models need a parameter for each pair of users, which results in high-dimensional models becoming easily trapped into the overfitting problem. However, such models do not consider how influences depend on each other if influences are sent from the same user or if influences are received by the same user. Therefore, we propose a model that defines parameters for every user with a latent influence vector and a susceptibility vector, opposite to define influences on user pairs. Such low-dimensional representations naturally cause the interpersonal influences involving the same user to be coupled with each other, thus reducing the model’s complexity. Additionally, the model can easily consider the temporal information and sentimental polarities of users’ messages. Finally, we conduct extensive experiments on two real-world Microblog datasets, showing that our model with such representations achieves best performance on three prediction tasks, compared to the state-of-the-art and pair-wise baselines.

How can we detect fraud in a big graph with rich properties, as online fraudsters invest more resources, including purchasing large pools of fake user accounts and dedicated IPs, to hide their fraudulent attacks? To achieve robustness, existing approaches detected dense sub-graphs as suspicious patterns in an unsupervised way, such as average degree maximization. However, such approaches suffer from the bias of including more nodes than necessary, resulting in lower accuracy and increased need for manual verification. Therefore, we propose HoloScope, which introduces a novel metric “contrast suspiciousness” integrating information from graph topology and spikes to more accurately detect fraudulent users and objects. Contrast suspiciousness dynamically emphasizes the contrasting patterns between fraudsters and normal users, making HoloScope capable of distinguishing the synchronized and strange behaviors of fraudsters by means of topology, bursts and drops, and rating scores. In addition, we provide theoretical bounds for how much this method increases the time cost needed for fraudsters to conduct adversarial attacks. Moreover, HoloScope has a concise framework and sub-quadratic time complexity, making the algorithm reproducible and scalable. In extensive experiments, HoloScope achieved significant accuracy improvements on real data with injected labels and true labels, when compared with state-of-the-art fraud detection methods.

In the smart power grid, short-term load forecasting (STLF) is a crucial step in scheduling and planning for future load, so as to improve the reliability, cost, and emissions of the power grid. Different from traditional time series forecast, STLF is a more challenging task, because of the complex demand of active and reactive power from numerous categories of electrical loads and the effects of environment. Therefore, we propose NeuCast, a seasonal neural forecasting method, which dynamically models various loads as co-evolving time series in a hidden space, as well as extra weather conditions, in a neural network structure. NeuCast captures seasonality and patterns of the time series by integrating factor modeling and hidden state recognition. NeuCast can also detect anomalies and forecast under different temperature assumptions. Extensive experiments on 134 real-word datasets show the improvements of NeuCast over the stateof-the-art methods.

As online fraudsters invest more resources, including purchasing large pools of fake user accounts and dedicated IPs, fraudulent attacks become less obvious and their detection becomes increasingly challenging. Existing approaches such as average degree maximization suffer from the bias of including more nodes than necessary, resulting in lower accuracy and increased need for manual verification. Hence, we propose HoloScope, which introduces a novel metric "contrast suspiciousness" integrating information from graph topology and spikes to more accurately detect fraudulent users and objects. Contrast suspiciousness dynamically emphasizes the contrast patterns between fraudsters and normal users, making HoloScope capable of distinguishing the synchronized and anomalous behaviors of fraudsters on topology, bursts and drops, and rating scores. In addition, we provide theoretical bounds for how much this increases the time cost needed for fraudsters to conduct adversarial attacks. Moreover, HoloScope has a concise framework and sub-quadratic time complexity, making the algorithm reproducible and scalable. Extensive experiments showed that HoloScope achieved significant accuracy improvements on synthetic and real data, compared with state-of-the-art fraud detection methods.

Given a retinal image, can we automatically determine whether it is of high quality (suitable for medical diagnosis)? Can we also explain our decision, pinpointing the region or regions that led to our decision? Images from human retinas are vital for the diagnosis of multiple health issues, like hypertension, diabetes, and Alzheimer's; low quality images may force the patient to come back again for a second scanning, wasting time and possibly delaying treatment. However, existing retinal image quality assessment methods are either black boxes without explanations of the results or depend heavily on feature engineering or on complex and error-prone anatomical structures' segmentation. Therefore, we propose EyeQual, that solves exactly this problem. EyeQual is novel, fast for inference, accurate and explainable, pinpointing low-quality regions on the image. We evaluated EyeQual on two real datasets where it achieved 100% accuracy taking just 36 milliseconds for each image.

Whereas it is well known that social network users influence each other, a fundamental problem in influence maximization, opinion formation and viral marketing is that users' influences are difficult to quantify. Previous work has directly defined an independent model parameter to capture the interpersonal influence between each pair of users. However, such models do not consider how influences depend on each other if they originate from the same user or if they act on the same user. To do so, these models need a parameter for each pair of users, which results in high-dimensional models becoming easily trapped into the overfitting problem. Given these problems, another way of defining the parameters is needed to consider the dependencies. Thus we propose a model that defines parameters for every user with a latent influence vector and a susceptibility vector. Such low-dimensional and distributed representations naturally cause the interpersonal influences involving the same user to be coupled with each other, thus reducing the model's complexity. Additionally, the model can easily consider the sentimental polarities of users' messages and how sentiment affects users' influences. In this study, we conduct extensive experiments on real Microblog data, showing that our model with distributed representations achieves better accuracy than the state-of-the-art and pair-wise models, and that learning influences on sentiments benefit performance.

An ability of modeling and predicting the cascades of resharing is crucial to understanding information propagation and to launching campaign of viral marketing. Conventional methods for cascade prediction heavily depend on the hypothesis of diffusion models, e.g., independent cascade model and linear threshold model. Recently, researchers attempt to circumvent the problem of cascade prediction using sequential models (e.g., recurrent neural network, namely RNN) that do not require knowing the underlying diffusion model. Existing sequential models employ a chain structure to capture the memory effect. However, for cascade prediction, each cascade generally corresponds to a diffusion tree, causing cross-dependence in cascade---one sharing behavior could be triggered by its non-immediate predecessor in the memory chain. In this paper, we propose to an attention-based RNN to capture the cross-dependence in cascade. Furthermore, we introduce a \emph{coverage} strategy to combat the misallocation of attention caused by the memoryless of traditional attention mechanism. Extensive experiments on both synthetic and real world datasets demonstrate the proposed models outperform state-of-the-art models at both cascade prediction and inferring diffusion tree.

Principal component analysis (PCA) is a fundamental dimension reduction tool in statistics and machine learning. For large and high-dimensional data, computing the PCA (i.e., the top singular vectors of the data matrix) becomes a challenging task. In this work, a single-pass randomized algorithm is proposed to compute PCA with only one pass over the data. It is suitable for processing extremely large and high-dimensional data stored in slow memory (hard disk) or the data generated in a streaming fashion. Experiments with synthetic and real data validate the algorithm's accuracy, which has orders of magnitude smaller error than an existing single-pass algorithm. For a set of high-dimensional data stored as a 150 GB file, the algorithm is able to compute the first 50 principal components in just 24 minutes on a typical 24-core computer, with less than 1 GB memory cost.

Predicting cascade dynamics has important implications for understanding information propagation and launching viral marketing. Previous works mainly adopt a pair-wise manner, modeling the propagation probability between pairs of users using n2 independent parameters for n users. Consequently, these models suffer from severe overfitting problem, especially for pairs of users without direct interactions, limiting their prediction accuracy. Here we propose to model the cascade dynamics by learning two low-dimensional user-specific vectors from observed cascades, capturing their influence and susceptibility respectively. This model requires much less parameters and thus could combat overfitting problem. Moreover, this model could naturally model context-dependent factors like cumulative effect in information propagation. Extensive experiments on synthetic dataset and a large-scale microblogging dataset demonstrate that this model outperforms the existing pair-wise models at predicting cascade dynamics, cascade size, and "who will be retweeted."

Sentiment classification is a topic-sensitive task, i.e., a classifier trained from one topic will perform worse on another. This is especially a problem for the tweets sentiment analysis. Since the topics in Twitter are very diverse, it is impossible to train a universal classifier for all topics. Moreover, compared to product review, Twitter lacks data labeling and a rating mechanism to acquire sentiment labels. The extremely sparse text of tweets also brings down the performance of a sentiment classifier. In this paper, we propose a semi-supervised topic-adaptive sentiment classification (TASC) model, which starts with a classifier built on common features and mixed labeled data from various topics. It minimizes the hinge loss to adapt to unlabeled data and features including topic-related sentiment words, authors' sentiments and sentiment connections derived from“@” mentions of tweets, named as topic-adaptive features. Text and non-text features are extracted and naturally split into two views for co-training. The TASC learning algorithm updates topic-adaptive features based on the collaborative selection of unlabeled data, which in turn helps to select more reliable tweets to boost the performance. We also design the adapting model along a timeline (TASC-t) for dynamic tweets. An experiment on 6 topics from published tweet corpuses demonstrates that TASC outperforms other well-known supervised and ensemble classifiers. It also beats those semi-supervised learning methods without feature adaption. Meanwhile, TASC-t can also achieve impressive accuracy and F-score. Finally, with timeline visualization of “river” graph, people can intuitively grasp the ups and downs of sentiments' evolvement, and the intensity by color gradation.

Probabilistic topic models have been widely used for sentiment analysis. However, most of existing topic methods only model the sentiment text, but do not consider the user, who expresses the sentiment, and the item, which the sentiment is expressed on. Since different users may use different sentiment expressions for different items, we argue that it is better to incorporate the user and item information into the topic model for sentiment analysis. In this paper, we propose a new Supervised User-Item based Topic model, called SUIT model, for sentiment analysis. It can simultaneously utilize the textual topic and latent user-item factors. Our proposed method uses the tensor outer product of text topic proportion vector, user latent factor and item latent factor to model the sentiment label generalization. Extensive experiments are conducted on two datasets: review dataset and microblog dataset. The results demonstrate the advantages of our model. It shows significant improvement compared with supervised topic models and collaborative filtering methods.

Tweets ranking is important for information acquisition in Microblog. Due to the content sparsity and lackof labeled data, it is better to employ semi-supervisedlearning methods to utilize the unlabeled data. However,most of previous semi-supervised learning methods donot consider the pair conflict problem, which means thatthe new selected unlabeled data may conflict with the labeled and previously selected data. It will hurt the learning performance a lot, if the training data contains manyconflict pairs. In this paper, we propose a new collaborative semi-supervised SVM ranking model (CSR-TC)with consideration of the order conflict. The unlabeleddata is selected based on a dynamically maintained transitive closure graph to avoid pair conflict. We also investigate the two views of features, intrinsic and contentrelevant features, for the proposed model. Extensive experiments are conducted on TREC Microblogging corpus. The results demonstrate that our proposed methodachieves significant improvement, compared to severalstate-of-the-art models.

Sentiment classification is an important problem in tweets mining. There lack labeled data and rating mechanism for generating them in Twitter service. And topics in Twitter are more diverse while sentiment classifiers always dedicate themselves to a specific domain or topic. Thus it is a challenge to make sentiment classification adaptive to diverse topics without sufficient labeled data. Therefore we formally propose an adaptive multiclass SVM model which transfers an initial common sentiment classifier to a topic-adaptive one. To tackle the tweet sparsity, non-text features are explored besides the conventional text features, which are intuitively split into two views. An iterative algorithm is proposed for solving this model by alternating among three steps: optimization, unlabeled data selection and adaptive feature expansion steps. The algorithm alternatively minimizes the margins of two independent objectives on different views to learn coefficient matrices, which are collaboratively used for unlabeled tweets selection from the topic that the algorithm is adapting to. And then topic-adaptive sentiment words are expended based on the above selection, in turn to help the first two steps find more confident and unlabeled tweets and boost the final performance. Comparing with the well-known supervised sentiment classifiers and semi-supervised approaches, our algorithm achieves promising increases in accuracy averagely on the 6 topics from public tweet corpus.

Nowadays, short texts are very prevalent in various web applications, such as microblogs, instant messages. The severe sparsity of short texts hinders existing topic models to learn reliable topics. In this paper, we propose a novel way to tackle this problem. The key idea is to learn topics by exploring term correlation data, rather than the high-dimensional and sparse term occurrence information in documents. Such term correlation data is less sparse and more stable with the increase of the collection size, and can well capture the necessary information for topic learning. To obtain reliable topics from term correlation data, we first introduce a novel way to compute term correlation in short texts by representing each term with its co-occurred terms. Then we formulated the topic learning problem as symmetric non-negative matrix factorization on the term correlation matrix. After learning the topics, we can easily infer the topics of documents. Experimental results on three data sets show that our method provides substantially better performance than the baseline methods.

Social tagging has grown in popularity on the web due to its effectiveness in organizing and accessing web pages. This short paper addresses the problem of automated social tagging, which aims to predict tags for web pages automatically and help with future navigation, filtering or search. We explore and find three foundations of the collaborative tags in social tagging services, that are consistency, sharability and stability. The complementary advantages are studied among three well-known methods, i.e. TF-weighted keyword extraction, collaborative filtering approach, and Corr-LDA (correspondence latent Dirichlet allocation) topic model. We then propose a blending model for automated social tagging to emphasize all the foundations, which linearly combines those tags generated by the three methods, and a permutation probability model is built to learn the linear blending. With the experiments on 50,000 training and 10,000 testing web pages from Delicious database, the results show that our blending method outperforms the four baselines. Furthermore, compared with both topic models, Corr-LDA and mixed membership LDA, our approach results in 14.2% and 25.6% of NDCG10improvement separately.

Non-negative matrix factorization (NMF) has been successfully applied in document clustering. However, experiments on short texts, such as microblogs, Q&A documents and news titles, suggest unsatisfactory performance of NMF. An major reason is that the traditional term weighting schemes, like binary weight and tfidf, cannot well capture the terms' discriminative power and importance in short texts, due to the sparsity of data. To tackle this problem, we proposed a novel term weighting scheme for NMF, derived from the Normalized Cut (Ncut) problem on the term affinity graph. Different from idf, which emphasizes discriminability on document level, the Ncut weighting measures terms' discriminability on term level. Experiments on two data sets show our weighting scheme significantly boosts NMF's performance on short text clustering.

With the challenges of growing functionality and scaling chip size, the possible performance improvements should be considered in the earlier IC design stages, which gives more freedom to the later optimization. Potential slack as an effective metric of possible performance improvements is considered in this work which, as far as we known, is the first work that maximizes the potential slack by retiming for synchronous sequential circuit. A simultaneous slack budgeting and incremental retiming algorithm is proposed for maximizing potential slack. The overall slack budget is optimized by relocating the FFs iteratively with the MIS-based slack estimation. Compared with the potential slack of a well-known min-period retiming, our algorithm improves potential slack averagely 19.6% without degrading the circuit performance in reasonable runtime. Furthermore, at the expense of a small amount of timing performance, 0.52% and 2.08%, the potential slack is increased averagely by 19.89% and 28.16% separately, which give a hint of the tradeoff between the timing performance and the slack budget.

Off-chip substrate routing for high-density packages is challenging due to requirements such as high density, lack of vertical detour, non-Manhattan routing, and primarily planar routing. The existing substrate routing algorithms often result in a large number of unrouted nets that have to be routed manually. This article develops an effective yet efficient diffusion-driven method D-Router to reduce congestion. Starting with an initial routing, we develop an effective diffusion-based congestion reduction. We iteratively find a congested window and spread out connections to reduce congestion inside the window by a simulated diffusion process based on the duality between congestion and concentration. The window is released after the congestion is eliminated. Compared with the state-of-the-art substrate routing method that leads to 480 nets unrouted for ten industrial designs with a total of 6415 nets, the D-Router reduces the amount of unrouted nets to 104, a reduction to the 4.6 multiple. In addition, the D-Router obtains a similar reduction on unrouted nets but runs up to 94 times faster when compared with a negotiation-based substrate routing.

O-chip substrate routing for high density packages is chal-lenging, and the existing substrate routing algorithms often result in a large number of unrouted nets that have to be routed manually. This paper develops an eective yet e-cient diusion-driven method D-Router to improve routabil-ity by a simulated diusion process based on the duality between congestion and concentration. Compared with a recently published A*-based algorithm used in a state of the art commercial tool and with similar routability and run-time as the negotiation based routing, D-Router reduces the number of unrouted nets by 4.6x with up to 94x runtime reduction.

Off-chip substrate routing for high-density packages is on the critical path for time to market. Compared with on-chip routers, existing commercial tools for off-chip routing have lower routability and often result in a large number of unrouted nets for manual routing. In this paper, we explain why planar routing is still required with multiple routing layers for substrate routing and then propose a flexible via-staggering technique to improve routability. In addition, we develop an efficient yet effective substrate routing algorithm, applying dynamic pushing to tackle the net ordering problem and reordering and rerouting to further reduce wire length and congestion. Compared with an industrial design tool that leaves 936 nets unrouted for nine industrial designs with a total of 6100 nets, our algorithm reduces the unrouted nets to 212, a 4.5-times net number reduction, which translates to design time reduction.

Compared with on-chip routers, the existing commercial tools for off-chip routing have a much lower routability and often result in a large number of unrouted nets for manual routing. In this paper, we develop an effective, yet efficient, substrate routing algorithm, applying dynamic pushing to alleviate the net ordering problem and reordering and rerouting for further wire length and congestion reduction. Compared with an industrial design tool that leaves 936 nets unrouted for nine industrial designs with a total of 6100 nets, our algorithm reduces the unrouted nets to 212, a 4.5-times net number reduction and practically more design time reduction.