Multi-interest Diversification for End-to-end Sequential Recommendation

Sequential recommenders capture dynamic aspects of users’ interests by modeling sequential behavior. Previous studies on sequential recommendations mostly aim to identify users’ main recent interests to optimize the recommendation accuracy; they often neglect the fact that users display multiple interests over extended periods of time, which could be used to improve the diversity of lists of recommended items. Existing work related to diversified recommendation typically assumes that users’ preferences are static and depend on post-processing the candidate list of recommended items. However, those conditions are not suitable when applied to sequential recommendations. We tackle sequential recommendation as a list generation process and propose a unified approach to take accuracy as well as diversity into consideration, called multi-interest, diversified, sequential recommendation . Particularly, an implicit interest mining module is first used to mine users’ multiple interests, which are reflected in users’ sequential behavior. Then an interest-aware, diversity promoting decoder is designed to produce recommendations that cover those interests. For training, we introduce an interest-aware, diversity promoting loss function that can supervise the model to learn to recommend accurate as well as diversified items. We conduct comprehensive experiments on four public datasets and the results show that our proposal outperforms state-of-the-art methods regarding diversity while producing comparable or better accuracy for sequential recommendation.

The influence of mayors as candidates in the 2017 parliamentary elections on voter decision-making in Czechia

Local activities of electoral candidates represent one of the key factors influencing voting behaviour. Many studies have shown an elevated electoral support for candidates in the municipality of their residence and the surrounding region. By using the example of mayors who candidated in the 2017 Czech parliamentary elections, this article proves that this voting behaviour is manifested not only through the territorial concentration of preferential votes, but also through higher local electoral support of political parties represented by these candidates. This so-called friends and neighbours effect is stronger in smaller, less populous municipalities. Its spatial extent is not necessarily limited to the respective municipality, but if a well-known and popular mayor appears at the top of the regional candidate list, it can affect voters living many kilometers away, especially in non-metropolitan areas.

Problematics of Affirmative Action Policy Implementation of Women's Representation Quota in Surabaya City Election

The development of an increasingly modern era is no longer a guarantee that a society's culture can be freedom from patriarchy as a whole. The women's equality has increasingly opened up opportunities for women to be active in both the domestic and public areas. The policy for affirming the quota for women's representation was also formulated by following developments. The 30% quota policy for women's representation in political parties is one of the affirmative policies in realizing women's equality in politics in Indonesia. By using descriptive quantitative research methods, this study tries to describe how the implementation of the affirmation policy on the quota of women's representation can work. The results that can be obtained in this study include: (1) in every election process, both the registration process for prospective DPRD members, the process of establishing a temporary candidate list (DCS) and the process of determining the permanent candidate list (DCT) as a whole has complied with quota of 30% women's representation (2) However, it cannot be denied that at every stage of implementation of the policy, there are still many problems

Recommending Relevant Tutorial Fragments for API-Related Natural Language Questions

Application Programming Interface (API) tutorial is an important API learning resource. To help developers learn APIs, an API tutorial is often split into a number of consecutive units that describe the same topic (i.e. tutorial fragment). We regard a tutorial fragment explaining an API as a relevant fragment of the API. Automatically recommending relevant tutorial fragments can help developers learn how to use an API. However, existing approaches often employ supervised or unsupervised manner to recommend relevant fragments, which suffers from much manual annotation effort or inaccurate recommended results. Furthermore, these approaches only support developers to input exact API names. In practice, developers often do not know which APIs to use so that they are more likely to use natural language to describe API-related questions. In this paper, we propose a novel approach, called Tutorial Fragment Recommendation (TuFraRec), to effectively recommend relevant tutorial fragments for API-related natural language questions, without much manual annotation effort. For an API tutorial, we split it into fragments and extract APIs from each fragment to build API-fragment pairs. Given a question, TuFraRec first generates several clarification APIs that are related to the question. We use clarification APIs and API-fragment pairs to construct candidate API-fragment pairs. Then, we design a semi-supervised metric learning (SML)-based model to find relevant API-fragment pairs from the candidate list, which can work well with a few labeled API-fragment pairs and a large number of unlabeled API-fragment pairs. In this way, the manual effort for labeling the relevance of API-fragment pairs can be reduced. Finally, we sort and recommend relevant API-fragment pairs based on the recommended strategy. We evaluate TuFraRec on 200 API-related natural language questions and two public tutorial datasets (Java and Android). The results demonstrate that on average TuFraRec improves NDCG@5 by 0.06 and 0.09, and improves Mean Reciprocal Rank (MRR) by 0.07 and 0.09 on two tutorial datasets as compared with the state-of-the-art approach.

Revamping the menu – or just offering what’s in stock? Candidate list volatility in open-list PR systems. Evidence from Finland

Why do parties change candidate lists between elections? Although candidate list volatility is an important indicator of the responsiveness of electoral representation, it has received little attention in research. We offer a critical case study of party list volatility in Finland, using a candidate-centred open-list proportional (PR) electoral system with ideal conditions for ‘ultra-strategic’ party behaviour. Our explorative two-stage research design begins with party elite interviews, to extract factors that can affect list volatility, which in the following step are tested in a regression analysis of 564 party lists in parliamentary elections 1983–2019. Our results show that list formation is a complex phenomenon, where demand and supply factors interact in a contingent fashion. Following trends of voter dealignment, personalization and ‘electoral-professionalization’ of parties, volatility has increased over time. Electoral defeats and declining party membership increase volatility, but a member-driven mass-party heritage that limits party elites’ strategic capacity has a stabilizing effect.

Explainable recommendation based on knowledge graph and multi-objective optimization

Recommendation system is a technology that can mine user's preference for items. Explainable recommendation is to produce recommendations for target users and give reasons at the same time to reveal reasons for recommendations. The explainability of recommendations that can improve the transparency of recommendations and the probability of users choosing the recommended items. The merits about explainability of recommendations are obvious, but it is not enough to focus solely on explainability of recommendations in field of explainable recommendations. Therefore, it is essential to construct an explainable recommendation framework to improve the explainability of recommended items while maintaining accuracy and diversity. An explainable recommendation framework based on knowledge graph and multi-objective optimization is proposed that can optimize the precision, diversity and explainability about recommendations at the same time. Knowledge graph connects users and items through different relationships to obtain an explainable candidate list for target user, and the path between target user and recommended item is used as an explanation basis. The explainable candidate list is optimized through multi-objective optimization algorithm to obtain the final recommendation list. It is concluded from the results about experiments that presented explainable recommendation framework provides high-quality recommendations that contains high accuracy, diversity and explainability.

Searching for solar siblings in APOGEE and Gaia DR2 with N-body simulations

ABSTRACT We make use of APOGEE and $Gaia\,$ data to identify stars that are consistent with being born in the same association or star cluster as the Sun. We limit our analysis to stars that match solar abundances within their uncertainties, as they could have formed from the same giant molecular cloud (GMC) as the Sun. We constrain the range of orbital actions that solar siblings can have with a suite of simulations of solar birth clusters evolved in static and time-dependent tidal fields. The static components of each galaxy model are the bulge, disc, and halo, while the various time-dependent components include a bar, spiral arms, and GMCs. In galaxy models without GMCs, simulated solar siblings all have JR < 122 km $\rm s^{-1}$ kpc, 990 < Lz < 1986 km $\rm s^{-1}$ kpc, and 0.15 < Jz < 0.58 km $\rm s^{-1}$ kpc. Given the actions of stars in APOGEE and $Gaia\,$, we find 104 stars that fall within this range. One candidate in particular, Solar Sibling 1, has both chemistry and actions similar enough to the solar values that strong interactions with the bar or spiral arms are not required for it to be dynamically associated with the Sun. Adding GMCs to the potential can eject solar siblings out of the plane of the disc and increase their Jz, resulting in a final candidate list of 296 stars. The entire suite of simulations indicate that solar siblings should have JR < 122 km $\rm s^{-1}$ kpc, 353 < Lz < 2110 km $\rm s^{-1}$ kpc, and Jz < 0.8 km $\rm s^{-1}$ kpc. Given these criteria, it is most likely that the association or cluster that the Sun was born in has reached dissolution and is not the commonly cited open cluster M67.

Deep Active Learning for Surface Defect Detection

Most of the current object detection approaches deliver competitive results with an assumption that a large number of labeled data are generally available and can be fed into a deep network at once. However, due to expensive labeling efforts, it is difficult to deploy the object detection systems into more complex and challenging real-world environments, especially for defect detection in real industries. In order to reduce the labeling efforts, this study proposes an active learning framework for defect detection. First, an Uncertainty Sampling is proposed to produce the candidate list for annotation. Uncertain images can provide more informative knowledge for the learning process. Then, an Average Margin method is designed to set the sampling scale for each defect category. In addition, an iterative pattern of training and selection is adopted to train an effective detection model. Extensive experiments demonstrate that the proposed method can render the required performance with fewer labeled data.