User behavior data, such as ratings and clicks, has been widely used to build personalizing models for recommender systems. However, many unflattering factors (e.g., popularity, ranking position, users’ selection) significantly affect the performance of the learned recommendation model. Most existing work on unbiased recommendation addressed these biases from sample granularity (e.g., sample reweighting, data augmentation) or from the perspective of representation learning (e.g., bias-modeling). However, these methods are usually designed for a specific bias, lacking the universal capability to handle complex situations where multiple biases co-exist. Besides, rare work frees itself from laborious and sophisticated debiasing configurations (e.g., propensity scores, imputed values, or user behavior-generating process). Towards this research gap, in this article, we propose a universal G enerative framework for B ias D isentanglement termed as GBD , constantly generating calibration perturbations for the intermediate representations during training to keep them from being affected by the bias. Specifically, a bias-identifier that tries to retrieve the bias-related information from the representations is first introduced. Subsequently, the calibration perturbations are generated to significantly deteriorate the bias-identifier’s performance, making the bias gradually disentangled from the calibrated representations. Therefore, without relying on notorious debiasing configurations, a bias-agnostic model is obtained under the guidance of the bias identifier. We further present its universality by subsuming the representative biases and their mixture under the proposed framework. Finally, extensive experiments on the real-world, synthetic, and semi-synthetic datasets have demonstrated the superiority of the proposed approach against a wide range of recommendation debiasing methods. The code is available at https://github.com/Zhidan-Wang/GBD .

This Practice Work-in-Progress paper presents an innovative approach for providing better evaluation and feedback for student-built Central Processing Units (CPUs) in Computer Organization course settings. A common lab project in such courses is the implementation of a simple CPU in Hardware Description Language (HDL). For example, students major in Computer Science at Tsinghua university are required to build a pipelined RISC-V processor during the autumn semester of their third year. However, due to the complexity of CPU internal states, debugging can be time-consuming for students, while assessing their designs and providing efficient feedback can be challenging for instructors. To overcome this challenge, we propose an automated verification framework using directed assembly code generation and trace comparison. Our framework uses two types of assembly test cases: one set specifically designed to trigger pipeline data and control hazards, and another set randomly generated with controlled instruction types and counts. In order to apply this industry-proven method to a wide variety of student designs, we also developed a technique for identifying common processor structures, such as register files and memory buses, that is essential for locating critical signals required for generating trace data via simulation. To evaluate the correctness of the student-designed CPUs, the recorded register and memory writing events are compared with the log generated by the Spike RISC-V ISA simulator, and the matching percentage between the two records is calculated. To provide feedback to students, we also present detailed information on the mismatches, which can help them identify bugs or areas for improvement in their designs. Tests on real student code demonstrate that our framework is more effective in detecting hidden logic errors, compared to traditional evaluation methods used in our teaching practice. The proposed method is beneficial for instructors as it saves time and improves the feedback loop in computer organization labs. Moreover, it provides additional data for assessing students' independent thinking and practical skills. With the growing popularity of the RISC-VISA in education, this approach is potentially applicable to the teaching of computer systems on a broader scale.

Session-based recommendation has recently attracted increasing attention from both industry and academic communities. Previous models mostly focus on designing different models to fit the observed data, which can be quite sparse in real-world scenarios. To alleviate this problem, in this paper, we propose a novel generative session-based recommendation framework. The main building block of our idea is to develop a generator to simulate user sequential behaviors, which are leveraged to train and improve the target sequential recommender model. In order to generate high quality samples, we consider two aspects: (1) the rationality as a sequence of user behaviors, and (2) the informativeness for training the target model. To satisfy these requirements, we design a doubly adversarial network. The first adversarial module aims to make the generated samples conform to the underlying patterns of the real user sequential preference (rationality requirement). The second adversarial module is targeted at widening the model experiences by generating samples which can induce larger model losses (informativeness requirement). In our model, the samples are generated based on a reinforcement learning strategy, where the reward is related with both of the above aspects. In order to stable the training process, we introduce a self-paced regularizer to learn the agent in an easy-to-hard manner. We conduct extensive experiments based on real-world datasets to demonstrate the effectiveness of our model.

This Research-to-Practice Work in Progress paper presents a type of Digital Logic Circuit experiment device like toys to attract the students' interest for the experiments. Digital Logic Circuit course is a course that emphasizes the actual hand-on experiment. Because it is fundamental course, its experiment maybe monotonous and boring for the students. The traditional experiment is hard to attract students. In this paper, we tried to turn the experimental device to the digital toys. We divided the whole experimental device into several kinds of modular blocks, which can perfectly cover the contents of the traditional experiments and greatly improve the fun of students' experiment. The experiment integrated the traditional chip connection type experiments and the programmable device experiments. The experiment blocks were colored, like the toy blocks, and it is easy to connect, so the experimental process is very interesting. The students can do the experiment like play toys, to build a simple and interesting digital circuit. We had used this device in the Digital Logic Lab course in a small scale, the students were more willing to do the experiment than others not using this device. The results proved that this kind of experiment is beneficial to train students in improving their hardware application ability, not only in mastering the knowledge effectively, but also in strengthening the ability of practice.

Adversarial robustness of machine learning has been widely studied in recent years, and a series of effective methods are proposed to resist adversarial attacks. However, less attention is paid to few-shot meta-learners which are much more vulnerable due to the lack of training samples. In this paper, we propose Task-based Adversarial Focal Loss (TAFL) to handle this tough challenge on a typical meta-learner called MAML. More concretely, we regard few-shot classification tasks as normal samples in learning models and apply focal loss mechanism on them. Our proposed method focuses more on adversarially fragile tasks, leading to improvement on overall model robustness. Results of extensive experiments on several benchmarks demonstrate that TAFL can effectively promote the performance of the meta-learner on adversarial examples with elaborately designed perturbations.

In this paper, we study collaborative filtering in an interactive setting, in which the recommender agents iterate between making recommendations and updating the user profile based on the interactive feedback. The most challenging problem in this scenario is how to suggest items when the user profile has not been well established, \ie recommend for cold-start users or warm-start users with taste drifting. Existing approaches either rely on overly pessimistic linear exploration strategy or adopt meta-learning based algorithms in a full exploitation way. In this work, to quickly catch up with the user's interests, we proposed to represent the exploration policy with a neural network and directly learn it from the feedback data. Specifically, the exploration policy is encoded in the weights of multi-channel stacked self-attention neural networks and trained with efficient Q-learning by maximizing users' overall satisfaction in the recommender systems. The key insight is that the satisfied recommendations triggered by the exploration recommendation can be viewed as the exploration bonus (delayed reward) for its contribution on improving the quality of the user profile. Therefore, the proposed exploration policy, to balance between learning the user profile and making accurate recommendations, can be directly optimized by maximizing users' long-term satisfaction with reinforcement learning. Extensive experiments and analysis conducted on three benchmark collaborative filtering datasets have demonstrated the advantage of our method over state-of-the-art methods.

We study the problem of efficient spatial visualization on a large data set stored in a database using SQL queries with ad-hoc range conditions on numerical attributes, for example, a spatial scatterplot of taxi pickup events in New York between 1/1/2015 and 3/10/2015. We present a novel middleware-based technique called Marviq. It divides the selection-attribute domain into intervals, and precomputes and stores a visualization for each interval. These results are called MVS and stored as tables in the database. We can compute an exact visualization for a request by accessing MVS and retrieving additional records from the base table. To further reduce the latter time, we present algorithms for using MVS to compute an approximate visualization that satisfies a user-specified similarity threshold. We show a family of functions with certain properties that can use this technique. We present an improvement by dividing the MVS intervals into smaller intervals and materializing low-resolution visualization for these intervals. We report the results of an extensive evaluation of Marviq, including a user study, and show its high performance in both space and time.

Applying reinforcement learning (RL) in recommender systems is attractive but costly due to the constraint of the interaction with real customers, where performing online policy learning through interacting with real customers usually harms customer experiences. A practical alternative is to build a recommender agent offline from logged data, whereas directly using logged data offline leads to the problem of selection bias between logging policy and the recommendation policy. The existing direct offline learning algorithms, such as Monte Carlo methods and temporal difference methods are either computationally expensive or unstable on convergence. To address these issues, we propose Pseudo Dyna-Q (PDQ). In PDQ, instead of interacting with real customers, we resort to a customer simulator, referred to as the World Model, which is designed to simulate the environment and handle the selection bias of logged data. During policy improvement, the World Model is constantly updated and optimized adaptively, according to the current recommendation policy. This way, the proposed PDQ not only avoids the instability of convergence and high computation cost of existing approaches but also provides unlimited interactions without involving real customers. Moreover, a proved upper bound of empirical error of reward function guarantees that the learned offline policy has lower bias and variance. Extensive experiments demonstrated the advantages of PDQ on two real-world datasets against state-of-the-arts methods.

Neural style transfer has drawn considerable attention from both academic and industrial field. Although visual effect and efficiency have been significantly improved, existing methods are unable to coordinate spatial distribution of visual attention between the content image and stylized image, or render diverse level of detail via different brush strokes. In this paper, we tackle these limitations by developing an attention-aware multi-stroke style transfer model. We first propose to assemble self-attention mechanism into a style-agnostic reconstruction autoencoder framework, from which the attention map of a content image can be derived. By performing multi-scale style swap on content features and style features, we produce multiple feature maps reflecting different stroke patterns. A flexible fusion strategy is further presented to incorporate the salient characteristics from the attention map, which allows integrating multiple stroke patterns into different spatial regions of the output image harmoniously. We demonstrate the effectiveness of our method, as well as generate comparable stylized images with multiple stroke patterns against the state-of-the-art methods.

Recommender systems provide users with a ranked list of items based on users' historical behavior. Existing methods usually embed users with their temporal dynamics, which may have lost their long-term, intrinsic preferences. RNN is widely adopted to model users' behaviors for its expressiveness on modeling sequential information. However, RNN-based methods are insufficient to capture users' intrinsic preferences due to short-term dependency issues. In this paper, we aim to make progress from two perspectives: 1. extract users' intrinsic preferences from their historical behaviors more effectively and robustly; 2. explore a fine-tuning way to combine users' intrinsic preferences and external dynamic interests. To do so, we propose a modification of Dynamic Memory Network with gating mechanism for generating a dynamic, precise representation for individual users. We also design an automatic and implicit method, and it utilizes the intrinsic preferences as a trigger signal to search the input sequences and retrieves the temporal dynamics of users in the memory module. As a result, a desirable combination of temporal dynamics and intrinsic preferences is achieved. Extensive experiments on three benchmark datasets have shown our model's superiority over the existing baseline method. Further analysis of the attention weights of each hop demonstrated the effectiveness of the proposed method.

Recommender systems play a crucial role in our daily lives. Feed streaming mechanism has been widely used in the recommender system, especially on the mobile Apps. The feed streaming setting provides users the interactive manner of recommendation in never-ending feeds. In such a manner, a good recommender system should pay more attention to user stickiness, which is far beyond classical instant metrics and typically measured by long-term user engagement. Directly optimizing long-term user engagement is a non-trivial problem, as the learning target is usually not available for conventional supervised learning methods. Though reinforcement learning~(RL) naturally fits the problem of maximizing the long term rewards, applying RL to optimize long-term user engagement is still facing challenges: user behaviors are versatile to model, which typically consists of both instant feedback (eg. clicks) and delayed feedback (eg. dwell time, revisit); in addition, performing effective off-policy learning is still immature, especially when combining bootstrapping and function approximation. To address these issues, in this work, we introduce a RL framework --- FeedRec to optimize the long-term user engagement. FeedRec includes two components: 1)~a Q-Network which designed in hierarchical LSTM takes charge of modeling complex user behaviors, and 2)~a S-Network, which simulates the environment, assists the Q-Network and voids the instability of convergence in policy learning. Extensive experiments on synthetic data and a real-world large scale data show that FeedRec effectively optimizes the long-term user engagement and outperforms state-of-the-arts.

In e-commerce, users' demands are not only conditioned by their profile and preferences, but also by their recent purchases that may generate new demands, as well as periodical demands that depend on purchases made some time ago. We call them respectively short-term demands and long-term demands. In this paper, we propose a novel self-attentive Continuous-Time Recommendation model (CTRec) for capturing the evolving demands of users over time. For modeling such time-sensitive demands, a Demand-aware Hawkes Process (DHP) framework is designed in CTRec to learn from the discrete purchase records of users. More specifically, a convolutional neural network is utilized to capture the short-term demands; and a self-attention mechanism is employed to capture the periodical purchase cycles of long-term demands. All types of demands are fused in DHP to make final continuous-time recommendations. We conduct extensive experiments on four real-world commercial datasets to demonstrate that CTRec is effective for general sequential recommendation problems, including next-item and next-session/basket recommendations. We observe in particular that CTRec is capable of learning the purchase cycles of products and estimating the purchase time of a product given a user.

Social Networks have experienced increased popularity and rapid growth in recent years. Recommendation is significant for users due to the extremely large amount of information in Social Networks. Most existing recommender systems rely on collaborative filtering techniques which focus on recommending the most relevant items to users based on past rating information of users or items. In Social Networks, the cold-start and data sparsity problems are very serious because new users and items are growing rapidly. Taking the Event Recommendation problem in Event-Based Social Networks as a scenario, many events are newly created and have few feedbacks. Existed collaborative filtering based methods will fail for Social Recommendation due to these problems. Therefore, a more sophisticated recommendation mechanism that can efficiently combine various contextual information to further improve recommendation quality is desired. In this paper, we propose a Context Aware Matrix Factorization model called CAMF which models implicit feedbacks and various contextual information simultaneously for Social Recommendation. Specifically, CAMF is a unified model that combines the Matrix Factorization model which models implicit feedbacks with the Linear Contextual Features model which models explicit contextual features. Extensive experiments on a large real-world dataset demonstrate that the CAMF model significantly outperforms state-of-the-art methods by 12.7% in terms of accuracy for the Event Recommendation problem.

Password-based user authentication service is widely used in Internet. Most of the password-based authentication protocols are constructed under the single-server structure that a authencitation server stores cleartext passwords or verification data derived from password and responds to users' authentication request. The security of single-server authentication system is very fragile. In particular, when the server is comprimised, all of users' verification data is exposed to the attacker. Nowadays, development of mobile Internet leads the demand of authentication on roaming device. In this scenario, easily memorable short password and simple secret is accepted by most people despite of its security limitation. The utilization of short password worsens the situation of single-server authentication protocol. Attackers controlling the system can launch off-line dictionary attack from internal of server side to obtain users' original password. Multi-server authentication protocols can improve the security of verification data by distributed storing data on the cluster. This approach increases the difficulty of internal attack and guarantees security even if a portion of servers in the cluster are controlled by adversary. But in practice, There are some problems in existing multi-server protocols. For example, communicating with multiple servers brings extra network and computational burden to client device. To address these problems, in this paper we propose a novel password-based multi-server authenication protocol which not only require less computation on client device but remain functional and secure even if adversary controls some servers and forces them collude to attack our protocol.

Understanding Activities of Human Daily Life is a fundamental and essential AI problem for Pervasive Computing and Human-Computer Interaction. Activity Sensing has attracted enormous research on activity recognition from mobile sensor data. However, there are two challenging problems: There is no standard taxonomy of activities and there is a lack of research on sensing high level activities. To this end, firstly, we built AHDL, the first knowledge base of Activities of Human Daily Life in this planet leveraging a large time use surveys. AHDL not only has a taxonomy of activities but also has common sense knowledge of these activities. Secondly, we designed ActivitySensor, a Conditional Random Fields based Sensor for sensing high level activities in AHDL. To be specific, ActivitySensor performs activity sensing using Conditional Random Fields model by combining contextual signals (time, location, previous activity and related person) and demographical signals. Extensive experiments demonstrated that ActivitySensor can improve the accuracy of activity recognition about 15% comparing to state-of-the-art methods on the same dataset. What's more, we revealed that ActivitySensor can predict what will you do next with high accuracy.

The rapid spread of smartphones has led to the increasing popularity of Location-Based Social Networks(LBSNs) like Foursquare, Gowalla, Facebook Places and so on where users can publish information about their current location. In LBSNs, identifying home locations of users is very important for various applications like effective location-based advertisement and recommendation. However, this problem is rather challenging because the location information in LBSNs is sparse and noisy: Only a small percentage of users share their home location information due to privacy concerns; users may check in at diverse places far from their home and make friends far away; many users even do not have any check-in information. In this paper, we propose a trust-based influence model, named as TSU to solve the problem. To be specific, TSU is a Trust-based unified probabilistic model that models edges in LBSNs based on signals from Social relationship data(social friendship, social trust) and User-centric data(check-in data) in LBSN. We proposed a Home Location Identification method based on TSU model and evaluate it on a large real-world LBSNs dataset. Extensive experiments demonstrate that our method significantly outperforms state-of-the-art methods.

The rapid spread of mobile internet and location-acquisition technologies have led to the increasing popularity of Location-Based Social Networks(LBSNs). Users in LBSNs can share their life by checking in at various venues at any time. In LBSNs, identifying home locations of users is significant for effective location-based services like personalized search, targeted advertisement, local recommendation and so on. In this paper, we propose a Home Location Global Positioning System called HLGPS to tackle with the home location identification problem in LBSNs. Firstly, HLGPS uses an influence model named as IME to model edges in LBSNs. Then HLGPS uses a global iteration algorithm based on IME model to position home location of users so that the joint probability of generating all the edges in LBSNs is maximum. Extensive experiments on a large real-world LBSN dataset demonstrate that HLGPS significantly outperforms state-of-the-art methods by 14.7%.

Enormous efforts of human volunteers have made Wikipedia become a treasure of textual knowledge. Relation extraction that aims at extracting structured knowledge in the unstructured texts in Wikipedia is an appealing but quite challenging problem because it's hard for machines to understand plain texts. Existing methods are not effective enough because they understand relation types in textual level without exploiting knowledge behind plain texts. In this paper, we propose a novel framework called Athena 2.0 leveraging Semantic Patterns which are patterns that can understand relation types in semantic level to solve this problem. Extensive experiments show that Athena 2.0 significantly outperforms existing methods.

Event-based Social Networks(EBSNs) which combine online interactions and offline events among users have experienced increased popularity and rapid growth recently. In EBSNs, event recommendation is significant for users due to the extremely large amount of events. However, the event recommendation problem is rather challenging because it faces a serious cold-start problem: Events have short life time and new events are registered by only a few users. What's more, there are only implicit feedback information. Existing approaches like collaborative filtering methods are not suitable for this scenario. In this paper, we propose a Context Aware Matrix Factorization model called AlphaMF to tackle with the problem. Specifically, AlphaMF is a unified model that combines the Matrix Factorization model which models implicit feedbacks with the Linear contextual features model which models explicit contextual features. Extensive experiments on a large real-world EBSN dataset demonstrate that the AlphaMF model significantly outperforms state-of-the-art methods by 11%.

In this paper, we develop a novel file sharing system based on a mixture distribution model working in the BitTorrentlike p2p networks. The BitTorrent's built-in “tit-for-tat” unchoking mechanism delays the initial file sharing process for newly joined peers as well as brings the problem of free-riding that peers only download from others but never contribute to the network. We demonstrate a file sharing mechanism which allows peers to share pieces according to different mixture distributions. The mechanism utilizes the historical contributions of peers in the network to inspire cooperation among peers, Along with the mixture distribution model, the peers can only obtain the whole file by contributing to the network continuously which deters the free-riding behaviors. We theoretically prove that the peers take the truthful revealing as their dominant strategy and our system can speed up the initial process of file sharing. The experiments show that the proposed system performs well and has good scalability, as well as prevents the free-riding problem elegantly.

The long propagation delay and low data rate of acoustic communication make the exchange of control messages time-consuming. Therefore, traditional handshaking-based Medium Access Control (MAC) protocols do not perform well in Underwater Acoustic Sensor Networks (UASN). In this paper, we propose Stentorian MAC for delay-tolerant UASN with heavy data load. Instead of handshaking, Stentorian MAC uses one-way declaration of transmission plans which can reach all contention peers of the sender. With slotted timing and separation between channel contention and data transmission, it employs a distributed and asynchronous planning strategy, which not only eliminates data collision, but also arranges as many concurrent transmissions as possible, in order to achieve high throughput. We evaluated the concurrency, throughput and packet delay of Stentorian MAC through simulation of random transmission and data aggregation, and confirmed that it has met our design goal.

Intricate malware can result in the failure of on-line Comprehensive Protection (CP) in distributed systems, and place the system in an unsafe state which is difficult to recover from. There lacks an effective scheme to defend against this extreme attack. In this paper, based on the Two-layer Protection and Cooperative Recovery (TPCRS) mechanism, we propose an efficient survivable scheme against malware attacks in distributed systems. The basic strategy is to deploy an Emergency Response/Recovery (ER) agent at each node to recognize the state of the system whenever the CP fails, and to carry out cooperative security among multiple nodes so that the infected nodes can be rapidly recovered. Furthermore, a Preventive Maintenance (PM) model is adopted to enhance the reliability of the distributed system. Simulation results demonstrate the practicality and efficiency of the proposed schemes.

In P2P file-sharing applications, distributed virtual payment mechanism is designed to encourage resource sharing among peers and thus restrain free-riding behaviors. However, it does not provide any protection on the security of the transaction process and the quality of the trading contents. We design a fair transaction mechanism for P2P file-sharing applications, in which a trusted third party is constructed and used to guarantee the atomic operation of the file-money exchange, in virtue of the property of distributed payment mechanism. The trading file is signed with the seller's private key, which can be used as proof in case of dissension. Performance analysis indicates that the costs of fair transaction mechanism are limited in both trading session latency and overhead to the system.

P2P applications suffer from free-riding. In economics terminology, free-riding is the rational behavior of the participants. So it's feasible to use game theory to analyze this problem and design countermeasures. Tit-For-Tat is a simple and efficient equilibrium strategy in repeated game environments. In this paper, we construct a game model in P2P environments and deduce the constraint under which the strict tit-for-tat is an equilibrium strategy. We then improve and adapt the tit-for-tat strategy to the dynamic property in P2P networks, and deduce the constraint under which it is still an equilibrium strategy. Finally we study through simulations the performance improvement of the enhanced tit-for-tat and give suggestion of how to choose proper system parameters under different network conditions.

Many P2P applications necessitate statistics aggregate computation of certain information among all individual peers. In contrast to methods of constructing aggregation tree, centralized computing and flooding, gossip-based mechanism has the advantages of good robustness and moderate communication and computing costs. Most algorithms of this type perform aggregate computation recursively on successive time slots called rounds. They require rounds to be globally synchronous on all the nodes, which complicates the algorithm realization. To eliminate the requirement for global round synchronization, we propose a loosely synchronized algorithm to compute global statistic average based on random event triggering mechanism, and prove that the convergence time is O(logN)tau. We then propose a robust method to estimate the number of peers in the network based on this algorithm. Finally, a framework is proposed to generalize the computation of SUM, AVG, MAX, MIN, and CNT(N).