Continual learning aims to equip deep neural networks (DNNs) with the capability to continuously learn new knowledge without catastrophic forgetting. Currently, there is significant attention on multimodal continual activity recognition from a egocentric perspective. However, the issue of modality imbalance can lead to exacerbated forgetting in multimodal continual learning. To address this, we propose an exemplar-free vision-sensor Attention-based Incremental Discriminability enhancement (AID) method. Firstly, we employ a Vision-Sensor attention module to enhance the time-frequency information of sensor modality and fuse them with vision modality. This alleviates the modality imbalance problem, yielding more discriminative and generalizable representations. Simultaneously, to prevent the classifier from overfitting to old class prototypes, we enhance old prototypes with features from new classes, thereby enhancing classifier discriminability. We validate the effectiveness of this method through numerous experiments with various task settings on the UESTC-MMEA-CL dataset.

Topic models have been widely used for text analysis. Previous topic models have enjoyed great success in mining the latent topic structure of text documents. With many efforts made on endowing the resulting document-topic distributions with different motivations, however, none of these models have paid any attention on the resulting topic-word distributions.Since topic-word distribution also plays an important role in the modeling performance,topic models which emphasize only the resulting document-topic representations but pay less attention to the topic-term distributions are limited. In this paper, we propose the Orthogonalized Topic Model(OTM) which imposes an orthogonality constraint on the topic-term distributions. We also propose a novel model fitting algorithm based on the generalized Expectation-Maximization algorithm and the Newthon-Raphson method. Quantitative evaluation of text classification demonstrates that OTM outperforms other baseline models and indicates the important role played by topic orthogonalizing.

Many Internet users have encountered serious information overload problem on social networks such as Facebook and Twitter, where users can consume the streams of social updates from their social connections. Traditional methods solving this problem include collaborative filtering and information diffusion modeling. Both methods answer the "who will adopt what" question from different perspective, while either of them only captures single-faceted knowledge of evidences. In this paper, we solve the personalized social update recommendation problem by proposing a framework which integrates the advantages of collaborative filtering and the characteristics of diffusion processes. The main contributions of this paper are three folds. First, we propose a plenty of diffusion features which capture the characteristics of diffusion processes. Second, we build a joint model which takes the advantages of both collaborative filtering and the characteristics of diffusion processes for recommendation. Finally, experiments on two real-world datasets show that our joint model outperforms the methods capturing single-faceted knowledge and several other baselines.

In this paper, we propose a set-oriented personalized ranking model for diversified top-N recommendation. Users may have various individual ranges of interests. For personalized top-N recommendation task, the combination of relevance and diversity in recommendation results would be desirable. For this purpose, we integrate the concept of diversity into traditional matrix factorization model to construct a set-oriented collaborative filtering model. By optimizing this model with a set-oriented pairwise ranking method, we directly achieve personalized top-N recommendation results which are both relevant and diversified. We also utilize category information explicitly for learning personalized diversity. Experimental results show that our model outperforms traditional models in terms of personalized diversity and maintains good performance on relevance prediction.

Many previous research works have focused on analyzing online social networks in many dimensions, as they bring large commercial value and provide significant references for many other subjects. Pinterest, a pinboard-style image sharing social service, has attracted much attention recently and become one of the most popular social networks. The special mechanism and style of Pinterest distinguish it from other previous popular social networks and shape totally different user behaviors, which makes it worth launching a new study on Pinterest. In this paper, we have an empirical study of user behaviors on Pinterest, based on a large Pinterest dataset containing 1.13 million users, 57 million following relations, 19 million boards and 933 million pins. We focus on studying the characteristics, manifestations and overall effects of user behaviors from many aspects, including the user interests, correlations between neighboring users, the common features of the most popular users, the topology of the network structure, etc. The most distinguishing characteristic of Pinterest is that users focus on everyday lives and are willing to collect many images about decoration, food, fashion, etc, which makes Pinterest an ideal advertising and marketing platform for retail companies. Many other qualitative and quantitative analysis on user behaviors have been discussed in our paper. We provide a comprehensive understanding of user behaviors on the Pinterest social network, which is our main contribution.

Twitter has rapidly grown to a popular social network in recent years and provides a large number of real-time messages for users. Tweets are presented in chronological order and users scan the followees' timelines to find what they are interested in. However, an information overload problem has troubled many users, especially those with many followees and thousands of tweets arriving every day. In this paper, we focus on recommending useful tweets that users are really interested in personally to reduce the users' effort to find useful information. Many kinds of information on Twitter are available for helping recommendation, including the user's own tweet history, retweet history and social relations between users. We propose a method of making tweet recommendations based on collaborative ranking to capture personal interests. It can also conveniently integrate the other useful contextual information. Our final method considers three major elements on Twitter: tweet topic level factors, user social relation factors and explicit features such as authority of the publisher and quality of the tweet. The experiments show that all the proposed elements are important and our method greatly outperforms several baseline methods.

With the rapid growing of Web 2.0, people spend more time on social networks such as Facebook and Twitter. In order to know the people they are interacting with, finding the web appearances of them will help the social network users to a great extent. We propose a novel and effective latent factor model to find web appearances of target social network users. Our method solves the name ambiguity problem by simultaneously exploring the link structure of social networks and the web. Experiments on real-world data show the superiority of our method over several baselines.