论文周报 | 推荐系统领域最新研究进展
1. Multi-Graph based Multi-Scenario Recommendation in Large-scale Online Video Services
2. FedSPLIT: One-Shot Federated Recommendation System Based on Non-negative Joint Matrix Factorization and Knowledge Distillation
3. A Review on Pushing the Limits of Baseline Recommendation Systems with the integration of Opinion Mining & Information Retrieval Techniques
4. When Multi-Level Meets Multi-Interest: A Multi-Grained Neural Model for Sequential Recommendation
5. Knowledge Graph Contrastive Learning for Recommendation
6. An Analysis of the Features Considerable for NFT Recommendations
7. FairSR: Fairness-aware Sequential Recommendation through Multi-Task Learning with Preference Graph Embeddings
8. Designing a Sequential Recommendation System for Heterogeneous Interactions Using Transformers
9. Doubting AI Predictions: Influence-Driven Second Opinion Recommendation
10. Joint Multisided Exposure Fairness for Recommendation
11. User-controllable Recommendation Against Filter Bubbles
12. Utility-Based Context-Aware Multi-Agent Recommendation System for Energy Efficiency in Residential Buildings
13. Analyzing and Simulating User Utterance Reformulation in Conversational Recommender Systems
1. Multi-Graph based Multi-Scenario Recommendation in Large-scale Online Video Services
Fan Zhang, Qiuying Peng, Yulin Wu, Zheng Pan, Rong Zeng, Da Lin, Yue Qi
https://arxiv.org/abs/2205.02446
Recently, industrial recommendation services have been boosted by the continual upgrade of deep learning methods. However, they still face de-biasing challenges such as exposure bias and cold-start problem, where circulations of machine learning training on human interaction history leads algorithms to repeatedly suggest exposed items while ignoring less-active ones. Additional problems exist in multi-scenario platforms, e.g. appropriate data fusion from subsidiary scenarios, which we observe could be alleviated through graph structured data integration via message passing.
2. FedSPLIT: One-Shot Federated Recommendation System Based on Non-negative Joint Matrix Factorization and Knowledge Distillation
Maksim E. Eren, Luke E. Richards, Manish Bhattarai, Roberto Yus, Charles Nicholas, Boian S. Alexandrov
https://arxiv.org/abs/2205.02359
Non-negative matrix factorization (NMF) with missing-value completion is a well-known effective Collaborative Filtering (CF) method used to provide personalized user recommendations. However, traditional CF relies on the privacy-invasive collection of users' explicit and implicit feedback to build a central recommender model. One-shot federated learning has recently emerged as a method to mitigate the privacy problem while addressing the traditional communication bottleneck of federated learning. In this paper, we present the first unsupervised one-shot federated CF implementation, named FedSPLIT, based on NMF joint factorization. In our solution, the clients first apply local CF in-parallel to build distinct client-specific recommenders. Then, the privacy-preserving local item patterns and biases from each client are shared with the processor to perform joint factorization in order to extract the global item patterns. Extracted patterns are then aggregated to each client to build the local models via knowledge distillation. In our experiments, we demonstrate the feasibility of our approach with standard recommendation datasets. FedSPLIT can obtain similar results than the state of the art (and even outperform it in certain situations) with a substantial decrease in the number of communications.
3. A Review on Pushing the Limits of Baseline Recommendation Systems with the integration of Opinion Mining & Information Retrieval Techniques
Dinuka Ravijaya Piyadigama, Guhanathan Poravi
https://arxiv.org/abs/2205.01802
Recommendations Systems allow users to identify trending items among a community while being timely and relevant to the user's expectations. When the purpose of various Recommendation Systems differs, the required type of recommendations also differs for each use case. While one Recommendation System may focus on recommending popular items, another may focus on recommending items that are comparable to the user's interests. Content-based filtering, user-to-user & item-to-item Collaborative filtering, and more recently; Deep Learning methods have been brought forward by the researchers to achieve better quality recommendations.
4. When Multi-Level Meets Multi-Interest: A Multi-Grained Neural Model for Sequential Recommendation
Yu Tian, Jianxin Chang, Yannan Niu, Yang Song, Chenliang Li
https://arxiv.org/abs/2205.01286
Sequential recommendation aims at identifying the next item that is preferred by a user based on their behavioral history. Compared to conventional sequential models that leverage attention mechanisms and RNNs, recent efforts mainly follow two directions for improvement: multi-interest learning and graph convolutional aggregation. Specifically, multi-interest methods such as ComiRec and MIMN, focus on extracting different interests for a user by performing historical item clustering, while graph convolution methods including TGSRec and SURGE elect to refine user preferences based on multi-level correlations between historical items. Unfortunately, neither of them realizes that these two types of solutions can mutually complement each other, by aggregating multi-level user preference to achieve more precise multi-interest extraction for a better recommendation. To this end, in this paper, we propose a unified multi-grained neural model(named MGNM) via a combination of multi-interest learning and graph convolutional aggregation. Concretely, MGNM first learns the graph structure and information aggregation paths of the historical items for a user. It then performs graph convolution to derive item representations in an iterative fashion, in which the complex preferences at different levels can be well captured. Afterwards, a novel sequential capsule network is proposed to inject the sequential patterns into the multi-interest extraction process, leading to a more precise interest learning in a multi-grained manner.
5. Knowledge Graph Contrastive Learning for Recommendation
Yuhao Yang, Chao Huang, Lianghao Xia, Chenliang Li
https://arxiv.org/abs/2205.00976
Knowledge Graphs (KGs) have been utilized as useful side information to improve recommendation quality. In those recommender systems, knowledge graph information often contains fruitful facts and inherent semantic relatedness among items. However, the success of such methods relies on the high quality knowledge graphs, and may not learn quality representations with two challenges: i) The long-tail distribution of entities results in sparse supervision signals for KG-enhanced item representation; ii) Real-world knowledge graphs are often noisy and contain topic-irrelevant connections between items and entities. Such KG sparsity and noise make the item-entity dependent relations deviate from reflecting their true characteristics, which significantly amplifies the noise effect and hinders the accurate representation of user's preference.
6. An Analysis of the Features Considerable for NFT Recommendations
Dinuka Piyadigama, Guhanathan Poravi
https://arxiv.org/abs/2205.00456
This research explores the methods that NFTs can be recommended to people who interact with NFT-marketplaces to explore NFTs of preference and similarity to what they have been searching for. While exploring past methods that can be adopted for recommendations, the use of NFT traits for recommendations has been explored. The outcome of the research highlights the necessity of using multiple Recommender Systems to present the user with the best possible NFTs when interacting with decentralized systems.
7. FairSR: Fairness-aware Sequential Recommendation through Multi-Task Learning with Preference Graph Embeddings
Cheng-Te Li, Cheng Hsu, Yang Zhang
https://arxiv.org/abs/2205.00313
Sequential recommendation (SR) learns from the temporal dynamics of user-item interactions to predict the next ones. Fairness-aware recommendation mitigates a variety of algorithmic biases in the learning of user preferences. This paper aims at bringing a marriage between SR and algorithmic fairness. We propose a novel fairness-aware sequential recommendation task, in which a new metric, interaction fairness, is defined to estimate how recommended items are fairly interacted by users with different protected attribute groups. We propose a multi-task learning based deep end-to-end model, FairSR, which consists of two parts. One is to learn and distill personalized sequential features from the given user and her item sequence for SR. The other is fairness-aware preference graph embedding (FPGE). The aim of FPGE is two-fold: incorporating the knowledge of users' and items' attributes and their correlation into entity representations, and alleviating the unfair distributions of user attributes on items. Extensive experiments conducted on three datasets show FairSR can outperform state-of-the-art SR models in recommendation performance. In addition, the recommended items by FairSR also exhibit promising interaction fairness.
8. Designing a Sequential Recommendation System for Heterogeneous Interactions Using Transformers
Mehdi Soleiman Nejad, Meysam Varasteh, Hadi Moradi, Mohammad Amin Sadeghi
https://arxiv.org/abs/2205.00265
While many production-ready and robust algorithms are available for the task of recommendation systems, many of these systems do not take the order of user's consumption into account. The order of consumption can be very useful and matters in many scenarios. One such scenario is an educational content recommendation, where users generally follow a progressive path towards more advanced courses. Researchers have used RNNs to build sequential recommendation systems and other models that deal with sequences. Sequential Recommendation systems try to predict the next event for the user by reading their history. With the massive success of Transformers in Natural Language Processing and their usage of Attention Mechanism to better deal with sequences, there have been attempts to use this family of models as a base for a new generation of sequential recommendation systems. In this work, by converting each user's interactions with items into a series of events and basing our architecture on Transformers, we try to enable the use of such a model that takes different types of events into account. Furthermore, by recognizing that some events have to occur before some other types of events take place, we try to modify the architecture to reflect this dependency relationship and enhance the model's performance.
9. Doubting AI Predictions: Influence-Driven Second Opinion Recommendation
Maria De-Arteaga, Alexandra Chouldechova, Artur Dubrawski
https://arxiv.org/abs/2205.00072
Effective human-AI collaboration requires a system design that provides humans with meaningful ways to make sense of and critically evaluate algorithmic recommendations. In this paper, we propose a way to augment human-AI collaboration by building on a common organizational practice: identifying experts who are likely to provide complementary opinions. When machine learning algorithms are trained to predict human-generated assessments, experts' rich multitude of perspectives is frequently lost in monolithic algorithmic recommendations. The proposed approach aims to leverage productive disagreement by (1) identifying whether some experts are likely to disagree with an algorithmic assessment and, if so, (2) recommend an expert to request a second opinion from.
10. Joint Multisided Exposure Fairness for Recommendation
Haolun Wu, Bhaskar Mitra, Chen Ma, Fernando Diaz, Xue Liu
https://arxiv.org/abs/2205.00048
Prior research on exposure fairness in the context of recommender systems has focused mostly on disparities in the exposure of individual or groups of items to individual users of the system. The problem of how individual or groups of items may be systemically under or over exposed to groups of users, or even all users, has received relatively less attention. However, such systemic disparities in information exposure can result in observable social harms, such as withholding economic opportunities from historically marginalized groups (allocative harm) or amplifying gendered and racialized stereotypes (representational harm). Previously, Diaz et al. developed the expected exposure metric -- that incorporates existing user browsing models that have previously been developed for information retrieval -- to study fairness of content exposure to individual users. We extend their proposed framework to formalize a family of exposure fairness metrics that model the problem jointly from the perspective of both the consumers and producers. Specifically, we consider group attributes for both types of stakeholders to identify and mitigate fairness concerns that go beyond individual users and items towards more systemic biases in recommendation. Furthermore, we study and discuss the relationships between the different exposure fairness dimensions proposed in this paper, as well as demonstrate how stochastic ranking policies can be optimized towards said fairness goals.
11. User-controllable Recommendation Against Filter Bubbles
Wenjie Wang, Fuli Feng, Liqiang Nie, Tat-Seng Chua
https://arxiv.org/abs/2204.13844
Recommender systems usually face the issue of filter bubbles: overrecommending homogeneous items based on user features and historical interactions. Filter bubbles will grow along the feedback loop and inadvertently narrow user interests. Existing work usually mitigates filter bubbles by incorporating objectives apart from accuracy such as diversity and fairness. However, they typically sacrifice accuracy, hurting model fidelity and user experience. Worse still, users have to passively accept the recommendation strategy and influence the system in an inefficient manner with high latency, e.g., keeping providing feedback (e.g., like and dislike) until the system recognizes the user intention.
12. Utility-Based Context-Aware Multi-Agent Recommendation System for Energy Efficiency in Residential Buildings
Valentyna Riabchuk, Leon Hagel, Felix Germaine, Alona Zharova
https://arxiv.org/abs/2205.02704
A significant part of CO2 emissions is due to high electricity consumption in residential buildings. Using load shifting can help to improve the households' energy efficiency. To nudge changes in energy consumption behavior, simple but powerful architectures are vital. This paper presents a novel algorithm of a recommendation system generating device usage recommendations and suggests a framework for evaluating its performance by analyzing potential energy cost savings. As a utility-based recommender system, it models user preferences depending on habitual device usage patterns, user availability, and device usage costs. As a context-aware system, it requires an external hourly electricity price signal and appliance-level energy consumption data. Due to a multi-agent architecture, it provides flexibility and allows for adjustments and further enhancements. Empirical results show that the system can provide energy cost savings of 18% and more for most studied households.
13. Analyzing and Simulating User Utterance Reformulation in Conversational Recommender Systems
Shuo Zhang, Mu-Chun Wang, Krisztian Balog
https://arxiv.org/abs/2205.01763
User simulation has been a cost-effective technique for evaluating conversational recommender systems. However, building a human-like simulator is still an open challenge. In this work, we focus on how users reformulate their utterances when a conversational agent fails to understand them. First, we perform a user study, involving five conversational agents across different domains, to identify common reformulation types and their transition relationships. A common pattern that emerges is that persistent users would first try to rephrase, then simplify, before giving up. Next, to incorporate the observed reformulation behavior in a user simulator, we introduce the task of reformulation sequence generation: to generate a sequence of reformulated utterances with a given intent (rephrase or simplify). We develop methods by extending transformer models guided by the reformulation type and perform further filtering based on estimated reading difficulty. We demonstrate the effectiveness of our approach using both automatic and human evaluation.欢迎干货投稿 \ 论文宣传 \ 合作交流
推荐阅读
由于公众号试行乱序推送，您可能不再准时收到机器学习与推荐算法的推送。为了第一时间收到本号的干货内容， 请将本号设为星标，以及常点文末右下角的“在看”。
由于公众号试行乱序推送，您可能不再准时收到机器学习与推荐算法的推送。为了第一时间收到本号的干货内容， 请将本号设为星标，以及常点文末右下角的“在看”。