Papers by Mohammad Akbari
Proceedings of the 28th ACM International Conference on Information and Knowledge Management, 2019
When estimating the relevancy between a query and a document, ranking models largely neglect the ... more When estimating the relevancy between a query and a document, ranking models largely neglect the mutual information among documents. A common wisdom is that if two documents are similar in terms of the same query, they are more likely to have similar relevance score. To mitigate this problem, in this paper, we propose a multi-agent reinforced ranking model, named MarlRank. In particular, by considering each document as an agent, we formulate the ranking process as a multi-agent Markov Decision Process (MDP), where the mutual interactions among documents are incorporated in the ranking process. To compute the ranking list, each document predicts its relevance to a query considering not only its own query-document features but also its similar documents' features and actions. By defining reward as a function of NDCG, we can optimize our model directly on the ranking performance measure. Our experimental results on two LETOR benchmark datasets show that our model has significant performance gains over the state-of-art baselines. We also find that the NDCG shows an overall increasing trend along with the step of interactions, which demonstrates that the mutual information among documents helps improve the ranking performance. CCS CONCEPTS • Information systems → Learning to rank; Novelty in information retrieval.
Social media platforms have become the most popular means for users to share what is happening ar... more Social media platforms have become the most popular means for users to share what is happening around them. The abundance and growing usage of social media has resulted in a large repository of users' social posts, which provides a stethoscope for inferring individuals' lifestyle and wellness. As users' social accounts implicitly reflect their habits, preferences, and feelings, it is feasible for us to monitor and understand the wellness of users by harvesting social media data towards a healthier lifestyle. As a first step towards accomplishing this goal, we propose to automatically extract wellness events from users' published social contents. Existing approaches for event extraction are not applicable to personal wellness events due to its domain nature characterized by plenty of noise and variety in data, insufficient samples, and interrelation among events. To tackle these problems, we propose an optimization learning framework that utilizes the content information of microblogging messages as well as the relations between event categories. By imposing a sparse constraint on the learning model, we also tackle the problems arising from noise and variation in microblogging texts. Experimental results on a real-world dataset from Twitter have demonstrated the superior performance of our framework.
Users in social networks are often encouraged to complete their profile by providing personal att... more Users in social networks are often encouraged to complete their profile by providing personal attributes such as age, gender, interest, income, etc. Additionally, users are likely to join interest-based groups that are devoted to various topics: " 2016 University Graduates", "Accordions Singa-pore", etc. These profiles and groups are often used as a basis for rendering better online services, marketing, and advertisement. However, in practice, the majority of users are reluctant to provide actual personal attributes, while the group participation is often relevant to their friendship connections, rather than interests. As a solution, user profiling at the individual and group level is explored to mine the demography and mobility information of a user. In this paper, we discuss different user profiling approaches on social networks, highlight the challenges, techniques, and future trends. We explain the weakness and strength of these methods and introduce an analytic platform to bridge the gap between social media users, business intelligence and the Big Data.
Proceedings of the 38th International ACM SIGIR Conference on Research and Development in Information Retrieval - SIGIR '15, 2015
We are living in the era of social networks, where people throughout the world are connected and ... more We are living in the era of social networks, where people throughout the world are connected and organized by multiple social networks. The views revealed by different social networks may vary according to the different services they offer. They are complimentary to each other and comprehensively characterize a specific user from different perspectives. As compared to the scare knowledge conveyed by a single source, appropriate aggregation of multiple social networks offers us a better opportunity for deep user understanding. The challenges, however, co-exist with opportunities. The first challenge lies in the existence of block-wise missing data, caused by the fact that some users may be very active in certain social networks while inactive in others. The second challenge is how to collaboratively integrate multiple social networks. Towards this end, we first proposed a novel model for data missing completion by seamlessly exploring the knowledge from multiple sources. We then developed a robust multiple social network learning model, and applied it to the application of volunteerism tendency prediction. Extensive experiments on real world dataset verify the effectiveness of our scheme. The proposed scheme is applicable to many other domains, such as demographic inference and interest prediction.
Automatic Classification of Visual Evoked Potentials Based on Wavelet Analysis and Support Vector Machine
... 1, R. Azmi 2 1Islamic Azad University,Shahr-e-Qods Branch, [email protected] 2 Faculty M... more ... 1, R. Azmi 2 1Islamic Azad University,Shahr-e-Qods Branch, [email protected] 2 Faculty Member, Alzahra University, [email protected] ... a 30 to 50 Hz spectra range from the visual evoked potentials with reduced noise, the fuzzy ARTMAP (FA) method with the aid of noise ...
2010 2nd International Conference on Education Technology and Computer, 2010
2010 2nd International Conference on Education Technology and Computer, 2010
2011 Third International Conference on Computational Intelligence, Communication Systems and Networks, 2011
Tasks scheduling problem is a key factor for distributed systems to gain better performance. Even... more Tasks scheduling problem is a key factor for distributed systems to gain better performance. Even in the best conditions, the scheduling in distributed systems is known as an NP-complete problem. Hence, many genetic algorithms have been proposed for searching optimal solutions from entire solution space. However, these existing approaches are going to scan the entire solution space without considering the techniques that can reduce the complexity of the optimization. Spending too much time for doing scheduling is considered the main shortcoming of these approaches. Therefore, in this paper memetic algorithm has been used to cope with this shortcoming. With regard to load balancing efficiently, Bee Colony Optimization (BCO) has been applied as local search in the proposed memetic algorithm. Extended experimental results demonstrated that the proposed method outperform the existent GA-based method in term of Makespan.
Information reranking aims to recover the true order of the initial search results. Traditional r... more Information reranking aims to recover the true order of the initial search results. Traditional reranking approaches have achieved great success in uni-modal document retrieval. They, however, suffer from the following limitations when reranking multimodal documents: 1) they are unable to capture and model the relations among multiple modalities within the same document; 2) they usually concatenate diverse features extracted from different modalities into one single vector, rather than adaptively fusing them by considering their discriminative capabilities with respect to the given query; and 3) most of them consider the pairwise relations among documents but discard their higher-order grouping relations, which leads to information loss. Towards this end, we propose an adaptive multi-modal multi-view (aMM) reranking model. This model is able to jointly regularize the relatedness among modalities, the effects of feature views extracted from different modalities, as well as the complex relations among multi-modal documents. Extensive experiments on three datasets well validated the effectiveness and robustness of our proposed model.
User profile learning, such as mobility and demographic
profile learning, is of great importance ... more User profile learning, such as mobility and demographic
profile learning, is of great importance to various applications.
Meanwhile, the rapid growth of multiple social
platforms makes it possible to perform a comprehensive user
profile learning from different views. However, the research
efforts on user profile learning from multiple data sources
are still relatively sparse, and there is no large-scale dataset
released towards user profile learning. In our study, we
contribute such benchmark and perform an initial study on
user mobility and demographic profile learning. First, we
constructed and released a large-scale multi-source multimodal
dataset from three geographical areas. We then
applied our proposed ensemble model on this dataset to
learn user profile. Based on our experimental results, we
observed that multiple data sources mutually complement
each other and their appropriate fusion boosts the user
profiling performance.
Conference Presentations by Mohammad Akbari
User profile learning, such as mobility and demographic
profile learning, is of great importance... more User profile learning, such as mobility and demographic
profile learning, is of great importance to various applications.
Meanwhile, the rapid growth of multiple social
platforms makes it possible to perform a comprehensive user
profile learning from different views. However, the research
efforts on user profile learning from multiple data sources
are still relatively sparse, and there is no large-scale dataset
released towards user profile learning. In our study, we
contribute such benchmark and perform an initial study on
user mobility and demographic profile learning. First, we
constructed and released a large-scale multi-source multimodal
dataset from three geographical areas. We then
applied our proposed ensemble model on this dataset to
learn user profile. Based on our experimental results, we
observed that multiple data sources mutually complement
each other and their appropriate fusion boosts the user
profiling performance.
Uploads
Papers by Mohammad Akbari
profile learning, is of great importance to various applications.
Meanwhile, the rapid growth of multiple social
platforms makes it possible to perform a comprehensive user
profile learning from different views. However, the research
efforts on user profile learning from multiple data sources
are still relatively sparse, and there is no large-scale dataset
released towards user profile learning. In our study, we
contribute such benchmark and perform an initial study on
user mobility and demographic profile learning. First, we
constructed and released a large-scale multi-source multimodal
dataset from three geographical areas. We then
applied our proposed ensemble model on this dataset to
learn user profile. Based on our experimental results, we
observed that multiple data sources mutually complement
each other and their appropriate fusion boosts the user
profiling performance.
Conference Presentations by Mohammad Akbari
profile learning, is of great importance to various applications.
Meanwhile, the rapid growth of multiple social
platforms makes it possible to perform a comprehensive user
profile learning from different views. However, the research
efforts on user profile learning from multiple data sources
are still relatively sparse, and there is no large-scale dataset
released towards user profile learning. In our study, we
contribute such benchmark and perform an initial study on
user mobility and demographic profile learning. First, we
constructed and released a large-scale multi-source multimodal
dataset from three geographical areas. We then
applied our proposed ensemble model on this dataset to
learn user profile. Based on our experimental results, we
observed that multiple data sources mutually complement
each other and their appropriate fusion boosts the user
profiling performance.