Chen Wang

Shaojun Zhang, Chen Wang, Albert Zomaya

Dependency-aware job scheduling in the cluster is NP-hard. Recent work shows that Deep Reinforcement Learning (DRL) is capable of solving it. It is difficult for the administrator to understand the DRL-based policy even though it achieves remarkable performance gain. Therefore the complex model-based scheduler is not easy to gain trust in the system where simplicity is favored. In this paper, we give the multi-level explanation framework to interpret the policy of DRL-based scheduling. We dissect its decision-making process to job level and task level and approximate each level with interpretable models and rules, which align with operational practices. We show that the framework gives the system administrator insights into the state-of-the-art scheduler and reveals the robustness issue in regards to its behavior pattern.

Yuan-Chen Guo, Yan-Pei Cao, Chen Wang et al.

With the emergence of neural radiance fields (NeRFs), view synthesis quality has reached an unprecedented level. Compared to traditional mesh-based assets, this volumetric representation is more powerful in expressing scene geometry but inevitably suffers from high rendering costs and can hardly be involved in further processes like editing, posing significant difficulties in combination with the existing graphics pipeline. In this paper, we present a hybrid volume-mesh representation, VMesh, which depicts an object with a textured mesh along with an auxiliary sparse volume. VMesh retains the advantages of mesh-based assets, such as efficient rendering, compact storage, and easy editing, while also incorporating the ability to represent subtle geometric structures provided by the volumetric counterpart. VMesh can be obtained from multi-view images of an object and renders at 2K 60FPS on common consumer devices with high fidelity, unleashing new opportunities for real-time immersive applications.

Sepehr Assadi, Chen Wang

We give a near-optimal sample-pass trade-off for pure exploration in multi-armed bandits (MABs) via multi-pass streaming algorithms: any streaming algorithm with sublinear memory that uses the optimal sample complexity of $O(\frac{n}{Δ^2})$ requires $Ω(\frac{\log{(1/Δ)}}{\log\log{(1/Δ)}})$ passes. Here, $n$ is the number of arms and $Δ$ is the reward gap between the best and the second-best arms. Our result matches the $O(\log(\frac{1}Δ))$-pass algorithm of Jin et al. [ICML'21] (up to lower order terms) that only uses $O(1)$ memory and answers an open question posed by Assadi and Wang [STOC'20].

Chen Wang, Xunzhuo Liu, Yue Zhu et al.

LLM serving systems process heterogeneous query workloads where different categories exhibit different characteristics. Code queries cluster densely in embedding space while conversational queries distribute sparsely. Content staleness varies from minutes (stock data) to months (code patterns). Query repetition patterns range from power-law (code) to uniform (conversation), producing long tail cache hit rate distributions: high-repetition categories achieve 40-60% hit rates while low-repetition or volatile categories achieve 5-15% hit rates. Vector databases must exclude the long tail because remote search costs (30ms) require 15--20% hit rates to break even, leaving 20-30% of production traffic uncached. Uniform cache policies compound this problem: fixed thresholds cause false positives in dense spaces and miss valid paraphrases in sparse spaces; fixed TTLs waste memory or serve stale data. This paper presents category-aware semantic caching where similarity thresholds, TTLs, and quotas vary by query category. We present a hybrid architecture separating in-memory HNSW search from external document storage, reducing miss cost from 30ms to 2ms. This reduction makes low-hit-rate categories economically viable (break-even at 3-5% versus 15-20%), enabling cache coverage across the entire workload distribution. Adaptive load-based policies extend this framework to respond to downstream model load, dynamically adjusting thresholds and TTLs to reduce traffic to overloaded models by 9-17% in theoretical projections.

Jiwei Guan, Tianyu Ding, Longbing Cao et al.

Vision-language pretraining (VLP) with transformers has demonstrated exceptional performance across numerous multimodal tasks. However, the adversarial robustness of these models has not been thoroughly investigated. Existing multimodal attack methods have largely overlooked cross-modal interactions between visual and textual modalities, particularly in the context of cross-attention mechanisms. In this paper, we study the adversarial vulnerability of recent VLP transformers and design a novel Joint Multimodal Transformer Feature Attack (JMTFA) that concurrently introduces adversarial perturbations in both visual and textual modalities under white-box settings. JMTFA strategically targets attention relevance scores to disrupt important features within each modality, generating adversarial samples by fusing perturbations and leading to erroneous model predictions. Experimental results indicate that the proposed approach achieves high attack success rates on vision-language understanding and reasoning downstream tasks compared to existing baselines. Notably, our findings reveal that the textual modality significantly influences the complex fusion processes within VLP transformers. Moreover, we observe no apparent relationship between model size and adversarial robustness under our proposed attacks. These insights emphasize a new dimension of adversarial robustness and underscore potential risks in the reliable deployment of multimodal AI systems.

Tiezheng Guo, Chen Wang, Yanyi Liu et al.

Retrieving external knowledge and prompting large language models with relevant information is an effective paradigm to enhance the performance of question-answering tasks. Previous research typically handles paragraphs from external documents in isolation, resulting in a lack of context and ambiguous references, particularly in multi-document and complex tasks. To overcome these challenges, we propose a new retrieval framework IIER, that leverages Inter-chunk Interactions to Enhance Retrieval. This framework captures the internal connections between document chunks by considering three types of interactions: structural, keyword, and semantic. We then construct a unified Chunk-Interaction Graph to represent all external documents comprehensively. Additionally, we design a graph-based evidence chain retriever that utilizes previous paths and chunk interactions to guide the retrieval process. It identifies multiple seed nodes based on the target question and iteratively searches for relevant chunks to gather supporting evidence. This retrieval process refines the context and reasoning chain, aiding the large language model in reasoning and answer generation. Extensive experiments demonstrate that IIER outperforms strong baselines across four datasets, highlighting its effectiveness in improving retrieval and reasoning capabilities.

Jiwei Guan, Xi Zheng, Chen Wang et al.

With recent advances in autonomous driving, Voice Control Systems have become increasingly adopted as human-vehicle interaction methods. This technology enables drivers to use voice commands to control the vehicle and will be soon available in Advanced Driver Assistance Systems (ADAS). Prior work has shown that Siri, Alexa and Cortana, are highly vulnerable to inaudible command attacks. This could be extended to ADAS in real-world applications and such inaudible command threat is difficult to detect due to microphone nonlinearities. In this paper, we aim to develop a more practical solution by using camera views to defend against inaudible command attacks where ADAS are capable of detecting their environment via multi-sensors. To this end, we propose a novel multimodal deep learning classification system to defend against inaudible command attacks. Our experimental results confirm the feasibility of the proposed defense methods and the best classification accuracy reaches 89.2%. Code is available at https://github.com/ITSEG-MQ/Sensor-Fusion-Against-VoiceCommand-Attacks.

Yuzhe Zhang, Yipeng Zhang, Yidong Gan et al.

Causal graph recovery is traditionally done using statistical estimation-based methods or based on individual's knowledge about variables of interests. They often suffer from data collection biases and limitations of individuals' knowledge. The advance of large language models (LLMs) provides opportunities to address these problems. We propose a novel method that leverages LLMs to deduce causal relationships in general causal graph recovery tasks. This method leverages knowledge compressed in LLMs and knowledge LLMs extracted from scientific publication database as well as experiment data about factors of interest to achieve this goal. Our method gives a prompting strategy to extract associational relationships among those factors and a mechanism to perform causality verification for these associations. Comparing to other LLM-based methods that directly instruct LLMs to do the highly complex causal reasoning, our method shows clear advantage on causal graph quality on benchmark datasets. More importantly, as causality among some factors may change as new research results emerge, our method show sensitivity to new evidence in the literature and can provide useful information for updating causal graphs accordingly.

Pu Jian, Junhong Wu, Wei Sun et al.

Recent advances in text-only "slow-thinking" reasoning have prompted efforts to transfer this capability to vision-language models (VLMs), for training visual reasoning models (\textbf{VRMs}). owever, such transfer faces critical challenges: Effective "slow thinking" in VRMs requires \textbf{visual reflection}, the ability to check the reasoning process based on visual information. Through quantitative analysis, we observe that current VRMs exhibit limited visual reflection, as their attention to visual information diminishes rapidly with longer generated responses. To address this challenge, we propose a new VRM \textbf{Reflection-V}, which enhances visual reflection based on reasoning data construction for cold-start and reward design for reinforcement learning (RL). Firstly, we construct vision-centered reasoning data by leveraging an agent that interacts between VLMs and reasoning LLMs, enabling cold-start learning of visual reflection patterns. Secondly, a visual attention based reward model is employed during RL to encourage reasoning based on visual information. Therefore, \textbf{Reflection-V} demonstrates significant improvements across multiple visual reasoning benchmarks. Furthermore, \textbf{Reflection-V} maintains a stronger and more consistent reliance on visual information during visual reasoning, indicating effective enhancement in visual reflection capabilities.

Shiyi Yang, Lina Yao, Chen Wang et al.

Recent studies have shown that recommender systems (RSs) are highly vulnerable to data poisoning attacks. Understanding attack tactics helps improve the robustness of RSs. We intend to develop efficient attack methods that use limited resources to generate high-quality fake user profiles to achieve 1) transferability among black-box RSs 2) and imperceptibility among detectors. In order to achieve these goals, we introduce textual reviews of products to enhance the generation quality of the profiles. Specifically, we propose a novel attack framework named R-Trojan, which formulates the attack objectives as an optimization problem and adopts a tailored transformer-based generative adversarial network (GAN) to solve it so that high-quality attack profiles can be produced. Comprehensive experiments on real-world datasets demonstrate that R-Trojan greatly outperforms state-of-the-art attack methods on various victim RSs under black-box settings and show its good imperceptibility.

Shiyi Yang, Xinshu Li, Guanglin Zhou et al.

Recent studies have shown that recommender systems (RSs) are highly vulnerable to data poisoning attacks, where malicious actors inject fake user profiles, including a group of well-designed fake ratings, to manipulate recommendations. Due to security and privacy constraints in practice, attackers typically possess limited knowledge of the victim system and thus need to craft profiles that have transferability across black-box RSs. To maximize the attack impact, the profiles often remains imperceptible. However, generating such high-quality profiles with the restricted resources is challenging. Some works suggest incorporating fake textual reviews to strengthen the profiles; yet, the poor quality of the reviews largely undermines the attack effectiveness and imperceptibility under the practical setting. To tackle the above challenges, in this paper, we propose to enhance the quality of the review text by harnessing in-context learning (ICL) capabilities of multimodal foundation models. To this end, we introduce a demonstration retrieval algorithm and a text style transfer strategy to augment the navie ICL. Specifically, we propose a novel practical attack framework named RAGAN to generate high-quality fake user profiles, which can gain insights into the robustness of RSs. The profiles are generated by a jailbreaker and collaboratively optimized on an instructional agent and a guardian to improve the attack transferability and imperceptibility. Comprehensive experiments on various real-world datasets demonstrate that RAGAN achieves the state-of-the-art poisoning attack performance.

Chengkun He, Xiangmin Zhou, Chen Wang et al.

Group recommendation over social media streams has attracted significant attention due to its wide applications in domains such as e-commerce, entertainment, and online news broadcasting. By leveraging social connections and group behaviours, group recommendation (GR) aims to provide more accurate and engaging content to a set of users rather than individuals. Recently, influence-aware GR has emerged as a promising direction, as it considers the impact of social influence on group decision-making. In earlier work, we proposed Influence-aware Group Recommendation (IGR) to solve this task. However, this task remains challenging due to three key factors: the large and ever-growing scale of social graphs, the inherently dynamic nature of influence propagation within user groups, and the high computational overhead of real-time group-item matching. To tackle these issues, we propose an Enhanced Influence-aware Group Recommendation (EIGR) framework. First, we introduce a Graph Extraction-based Sampling (GES) strategy to minimise redundancy across multiple temporal social graphs and effectively capture the evolving dynamics of both groups and items. Second, we design a novel DYnamic Independent Cascade (DYIC) model to predict how influence propagates over time across social items and user groups. Finally, we develop a two-level hash-based User Group Index (UG-Index) to efficiently organise user groups and enable real-time recommendation generation. Extensive experiments on real-world datasets demonstrate that our proposed framework, EIGR, consistently outperforms state-of-the-art baselines in both effectiveness and efficiency.

Jiwei Guan, Lei Pan, Chen Wang et al.

There are increasing concerns about malicious attacks on autonomous vehicles. In particular, inaudible voice command attacks pose a significant threat as voice commands become available in autonomous driving systems. How to empirically defend against these inaudible attacks remains an open question. Previous research investigates utilizing deep learning-based multimodal fusion for defense, without considering the model uncertainty in trustworthiness. As deep learning has been applied to increasingly sensitive tasks, uncertainty measurement is crucial in helping improve model robustness, especially in mission-critical scenarios. In this paper, we propose the Multimodal Fusion Framework (MFF) as an intelligent security system to defend against inaudible voice command attacks. MFF fuses heterogeneous audio-vision modalities using VGG family neural networks and achieves the detection accuracy of 92.25% in the comparative fusion method empirical study. Additionally, extensive experiments on audio-vision tasks reveal the model's uncertainty. Using Expected Calibration Errors, we measure calibration errors and Monte-Carlo Dropout to estimate the predictive distribution for the proposed models. Our findings show empirically to train robust multimodal models, improve standard accuracy and provide a further step toward interpretability. Finally, we discuss the pros and cons of our approach and its applicability for Advanced Driver Assistance Systems.

Linfeng Liang, Yao Deng, Yang Zhang et al.

Discrepancies in decision-making between Autonomous Driving Systems (ADS) and human drivers underscore the need for intuitive human gaze predictors to bridge this gap, thereby improving user trust and experience. Existing gaze datasets, despite their value, suffer from noise that hampers effective training. Furthermore, current gaze prediction models exhibit inconsistency across diverse scenarios and demand substantial computational resources, restricting their on-board deployment in autonomous vehicles. We propose a novel adaptive cleansing technique for purging noise from existing gaze datasets, coupled with a robust, lightweight convolutional self-attention gaze prediction model. Our approach not only significantly enhances model generalizability and performance by up to 12.13% but also ensures a remarkable reduction in model complexity by up to 98.2% compared to the state-of-the art, making in-vehicle deployment feasible to augment ADS decision visualization and performance.

Ruxin Wang, Long Huang, Chen Wang

Handheld phone distraction is the leading cause of traffic accidents. However, few efforts have been devoted to detecting when the phone distraction happens, which is a critical input for taking immediate safety measures. This work proposes a phone-use monitoring system, which detects the start of the driver's handheld phone use and eliminates the distraction at once. Specifically, the proposed system emits periodic ultrasonic pulses to sense if the phone is being held in hand or placed on support surfaces (e.g., seat and cup holder) by capturing the unique signal interference resulted from the contact object's damping, reflection and refraction. We derive the short-time Fourier transform from the microphone data to describe such impacts and develop a CNN-based binary classifier to discriminate the phone use between the handheld and the handsfree status. Additionally, we design an adaptive window-based filter to correct the classification errors and identify each handheld phone distraction instance, including its start, end, and duration. Extensive experiments with fourteen people, three phones and two car models show that our system achieves 99% accuracy of recognizing handheld phone-use instances and 0.76-second median error to estimate the distraction's start time.

Guanglin Zhou, Lina Yao, Xiwei Xu et al.

With the widespread accumulation of observational data, researchers obtain a new direction to learn counterfactual effects in many domains (e.g., health care and computational advertising) without Randomized Controlled Trials(RCTs). However, observational data suffer from inherent missing counterfactual outcomes, and distribution discrepancy between treatment and control groups due to behaviour preference. Motivated by recent advances of representation learning in the field of domain adaptation, we propose a novel framework based on Cycle-Balanced REpresentation learning for counterfactual inference (CBRE), to solve above problems. Specifically, we realize a robust balanced representation for different groups using adversarial training, and meanwhile construct an information loop, such that preserve original data properties cyclically, which reduces information loss when transforming data into latent representation space.Experimental results on three real-world datasets demonstrate that CBRE matches/outperforms the state-of-the-art methods, and it has a great potential to be applied to counterfactual inference.

Chen Wang, Claudia Pérez-D'Arpino, Danfei Xu et al.

We present a method for learning a human-robot collaboration policy from human-human collaboration demonstrations. An effective robot assistant must learn to handle diverse human behaviors shown in the demonstrations and be robust when the humans adjust their strategies during online task execution. Our method co-optimizes a human policy and a robot policy in an interactive learning process: the human policy learns to generate diverse and plausible collaborative behaviors from demonstrations while the robot policy learns to assist by estimating the unobserved latent strategy of its human collaborator. Across a 2D strategy game, a human-robot handover task, and a multi-step collaborative manipulation task, our method outperforms the alternatives in both simulated evaluations and when executing the tasks with a real human operator in-the-loop. Supplementary materials and videos at https://sites.google.com/view/co-gail-web/home

Xiaowei Zhou, Jie Yin, Ivor Tsang et al.

The widespread use of deep neural networks has achieved substantial success in many tasks. However, there still exists a huge gap between the operating mechanism of deep learning models and human-understandable decision making, so that humans cannot fully trust the predictions made by these models. To date, little work has been done on how to align the behaviors of deep learning models with human perception in order to train a human-understandable model. To fill this gap, we propose a new framework to train a deep neural network by incorporating the prior of human perception into the model learning process. Our proposed model mimics the process of perceiving conceptual parts from images and assessing their relative contributions towards the final recognition. The effectiveness of our proposed model is evaluated on two classical visual recognition tasks. The experimental results and analysis confirm our model is able to provide interpretable explanations for its predictions, but also maintain competitive recognition accuracy.

Panpan Li, Yikun Gong, Chen Wang

With the continuous development of NoSQL databases, more and more developers choose to use semi-structured data for development and data management, which puts forward requirements for schema management of semi-structured data stored in NoSQL databases. Schema extraction plays an important role in understanding schemas, optimizing queries, and validating data consistency. Therefore, in this survey we investigate structural methods based on tree and graph and statistical methods based on distributed architecture and machine learning to extract schemas. The schemas obtained by the structural methods are more interpretable, and the statistical methods have better applicability and generalization ability. Moreover, we also investigate tools and systems for schemas extraction. Schema extraction tools are mainly used for spark or NoSQL databases, and are suitable for small datasets or simple application environments. The system mainly focuses on the extraction and management of schemas in large data sets and complex application scenarios. Furthermore, we also compare these techniques to facilitate data managers' choice.

Sunny Verma, Chen Wang, Liming Zhu et al.

The principal component analysis network (PCANet) is an unsupervised parsimonious deep network, utilizing principal components as filters in its convolution layers. Albeit powerful, the PCANet consists of basic operations such as principal components and spatial pooling, which suffers from two fundamental problems. First, the principal components obtain information by transforming it to column vectors (which we call the amalgamated view), which incurs the loss of the spatial information in the data. Second, the generalized spatial pooling utilized in the PCANet induces feature redundancy and also fails to accommodate spatial statistics of natural images. In this research, we first propose a tensor-factorization based deep network called the Tensor Factorization Network (TFNet). The TFNet extracts features from the spatial structure of the data (which we call the minutiae view). We then show that the information obtained by the PCANet and the TFNet are distinctive and non-trivial but individually insufficient. This phenomenon necessitates the development of proposed HybridNet, which integrates the information discovery with the two views of the data. To enhance the discriminability of hybrid features, we propose Attn-HybridNet, which alleviates the feature redundancy by performing attention-based feature fusion. The significance of our proposed Attn-HybridNet is demonstrated on multiple real-world datasets where the features obtained with Attn-HybridNet achieves better classification performance over other popular baseline methods, demonstrating the effectiveness of the proposed technique.

Sin Kit Lo, Qinghua Lu, Chen Wang et al.

Federated learning is an emerging machine learning paradigm where clients train models locally and formulate a global model based on the local model updates. To identify the state-of-the-art in federated learning and explore how to develop federated learning systems, we perform a systematic literature review from a software engineering perspective, based on 231 primary studies. Our data synthesis covers the lifecycle of federated learning system development that includes background understanding, requirement analysis, architecture design, implementation, and evaluation. We highlight and summarise the findings from the results, and identify future trends to encourage researchers to advance their current work.

Sepehr Assadi, Chen Wang

Consider the following abstract coin tossing problem: Given a set of $n$ coins with unknown biases, find the most biased coin using a minimal number of coin tosses. This is a common abstraction of various exploration problems in theoretical computer science and machine learning and has been studied extensively over the years. In particular, algorithms with optimal sample complexity (number of coin tosses) have been known for this problem for quite some time. Motivated by applications to processing massive datasets, we study the space complexity of solving this problem with optimal number of coin tosses in the streaming model. In this model, the coins are arriving one by one and the algorithm is only allowed to store a limited number of coins at any point -- any coin not present in the memory is lost and can no longer be tossed or compared to arriving coins. Prior algorithms for the coin tossing problem with optimal sample complexity are based on iterative elimination of coins which inherently require storing all the coins, leading to memory-inefficient streaming algorithms. We remedy this state-of-affairs by presenting a series of improved streaming algorithms for this problem: we start with a simple algorithm which require storing only $O(\log{n})$ coins and then iteratively refine it further and further, leading to algorithms with $O(\log\log{(n)})$ memory, $O(\log^*{(n)})$ memory, and finally a one that only stores a single extra coin in memory -- the same exact space needed to just store the best coin throughout the stream. Furthermore, we extend our algorithms to the problem of finding the $k$ most biased coins as well as other exploration problems such as finding top-$k$ elements using noisy comparisons or finding an $ε$-best arm in stochastic multi-armed bandits, and obtain efficient streaming algorithms for these problems.

Miao Du, Qin Yu, Shaomin Fei et al.

Nowadays, we mainly use various convolution neural network (CNN) structures to extract features from radio data or spectrogram in AMR. Based on expert experience and spectrograms, they not only increase the difficulty of preprocessing, but also consume a lot of memory. In order to directly use in-phase and quadrature (IQ) data obtained by the receiver and enhance the efficiency of network extraction features to improve the recognition rate of modulation mode, this paper proposes a new network structure called Fully Dense Neural Network (FDNN). This network uses residual blocks to extract features, dense connect to reduce model size, and adds attentions mechanism to recalibrate. Experiments on RML2016.10a show that this network has a higher recognition rate and lower model complexity. And it shows that the FDNN model with dense connections can not only extract features effectively but also greatly reduce model parameters, which also provides a significant contribution for the application of deep learning to the intelligent radio system.

Ruisen Luo, Tao Hu, Zuodong Tang et al.

To solve the problem of inaccurate recognition of types of communication signal modulation, a RNN neural network recognition algorithm combining residual block network with attention mechanism is proposed. In this method, 10 kinds of communication signals with Gaussian white noise are generated from standard data sets, such as MASK, MPSK, MFSK, OFDM, 16QAM, AM and FM. Based on the original RNN neural network, residual block network is added to solve the problem of gradient disappearance caused by deep network layers. Attention mechanism is added to the network to accelerate the gradient descent. In the experiment, 16QAM, 2FSK and 4FSK are used as actual samples, IQ data frames of signals are used as input, and the RNN neural network combined with residual block network and attention mechanism is trained. The final recognition results show that the average recognition rate of real-time signals is over 93%. The network has high robustness and good use value.

Ruisen Luo, Tianran Sun, Chen Wang et al.

As an important part of speech recognition technology, automatic speech keyword recognition has been intensively studied in recent years. Such technology becomes especially pivotal under situations with limited infrastructures and computational resources, such as voice command recognition in vehicles and robot interaction. At present, the mainstream methods in automatic speech keyword recognition are based on long short-term memory (LSTM) networks with attention mechanism. However, due to inevitable information losses for the LSTM layer caused during feature extraction, the calculated attention weights are biased. In this paper, a novel approach, namely Multi-layer Attention Mechanism, is proposed to handle the inaccurate attention weights problem. The key idea is that, in addition to the conventional attention mechanism, information of layers prior to feature extraction and LSTM are introduced into attention weights calculations. Therefore, the attention weights are more accurate because the overall model can have more precise and focused areas. We conduct a comprehensive comparison and analysis on the keyword spotting performances on convolution neural network, bi-directional LSTM cyclic neural network, and cyclic neural network with the proposed attention mechanism on Google Speech Command datasets V2 datasets. Experimental results indicate favorable results for the proposed method and demonstrate the validity of the proposed method. The proposed multi-layer attention methods can be useful for other researches related to object spotting.

Huijun Wu, Chen Wang, Yuriy Tyshetskiy et al.

Graph deep learning models, such as graph convolutional networks (GCN) achieve remarkable performance for tasks on graph data. Similar to other types of deep models, graph deep learning models often suffer from adversarial attacks. However, compared with non-graph data, the discrete features, graph connections and different definitions of imperceptible perturbations bring unique challenges and opportunities for the adversarial attacks and defenses for graph data. In this paper, we propose both attack and defense techniques. For attack, we show that the discreteness problem could easily be resolved by introducing integrated gradients which could accurately reflect the effect of perturbing certain features or edges while still benefiting from the parallel computations. For defense, we observe that the adversarially manipulated graph for the targeted attack differs from normal graphs statistically. Based on this observation, we propose a defense approach which inspects the graph and recovers the potential adversarial perturbations. Our experiments on a number of datasets show the effectiveness of the proposed methods.

Huijun Wu, Chen Wang, Jie Yin et al.

Despite outperforming the human in many tasks, deep neural network models are also criticized for the lack of transparency and interpretability in decision making. The opaqueness results in uncertainty and low confidence when deploying such a model in model sharing scenarios, when the model is developed by a third party. For a supervised machine learning model, sharing training process including training data provides an effective way to gain trust and to better understand model predictions. However, it is not always possible to share all training data due to privacy and policy constraints. In this paper, we propose a method to disclose a small set of training data that is just sufficient for users to get the insight of a complicated model. The method constructs a boundary tree using selected training data and the tree is able to approximate the complicated model with high fidelity. We show that traversing data points in the tree gives users significantly better understanding of the model and paves the way for trustworthy model sharing.

Binqi Zhang, Chen Wang, Bing Bing Zhou et al.

To improve the temporal and spatial storage efficiency, researchers have intensively studied various techniques, including compression and deduplication. Through our evaluation, we find that methods such as photo tags or local features help to identify the content-based similar- ity between raw images. The images can then be com- pressed more efficiently to get better storage space sav- ings. Furthermore, storing similar raw images together enables rapid data sorting, searching and retrieval if the images are stored in a distributed and large-scale envi- ronment by reducing fragmentation. In this paper, we evaluated the compressibility by designing experiments and observing the results. We found that on a statistical basis the higher similarity photos have, the better com- pression results are. This research helps provide a clue for future large-scale storage system design.