Industrial recommender systems usually consist of the matching stage and the ranking stage, in order to handle the billion-scale of users and items. The matching stage retrieves candidate items relevant to user interests, while the ranking stage sorts candidate items by user interests. Thus, the most critical ability is to model and represent user interests for either stage. Most of the existing deep learning-based models represent one user as a single vector which is insufficient to capture the varying nature of user's interests. In this paper, we approach this problem from a different view, to represent one user with multiple vectors encoding the different aspects of the user's interests. We propose the Multi-Interest Network with Dynamic routing (MIND) for dealing with user's diverse interests in the matching stage. Specifically, we design a multi-interest extractor layer based on capsule routing mechanism, which is applicable for clustering historical behaviors and extracting diverse interests. Furthermore, we develop a technique named label-aware attention to help learn a user representation with multiple vectors. Through extensive experiments on several public benchmarks and one large-scale industrial dataset from Tmall, we demonstrate that MIND can achieve superior performance than state-of-the-art methods for recommendation. Currently, MIND has been deployed for handling major online traffic at the homepage on Mobile Tmall App.
Nanjing University of Science and Technology（南京理工大学）
Resource constraints, e.g. limited product inventory or financial strength, may affect consumers' choices or preferences in some recommendation tasks but are usually ignored in previous recommendation methods. In this paper, we aim to mine the cue of user preferences in resource-limited recommendation tasks, for which purpose we specifically build a large used car transaction dataset possessing resource-limitation characteristics. Accordingly, we propose an interest-behavior multiplicative network to predict the user's future interaction based on dynamic connections between users and items. To…
We consider the following variant of contextual linear bandits motivated by routing applications in navigational engines and recommendation systems. We wish to learn a hidden $d$-dimensional value $w^*$. Every round, we are presented with a subset $\mathcal{X}_t \subseteq \mathbb{R}^d$ of possible actions. If we choose (i.e. recommend to the user) action $x_t$, we obtain utility $\langle x_t, w^* \rangle$ but only learn the identity of the best action $\arg\max_{x \in \mathcal{X}_t} \langle x, w^* \rangle$. We design algorithms for this problem which achieve regret $O(d\log T)$ and $\exp(O(d \…
Large-scale commercial platforms usually involve numerous business domains for diverse business strategies and expect their recommendation systems to provide click-through rate (CTR) predictions for multiple domains simultaneously. Existing promising and widely-used multi-domain models discover domain relationships by explicitly constructing domain-specific networks, but the computation and memory boost significantly with the increase of domains. To reduce computational complexity, manually grouping domains with particular business strategies is common in industrial applications. However, this…
A route recommendation system can provide better recommendation if it also takes collected user reviews into account, e.g. places that generally get positive reviews may be preferred. However, to classify sentiment, many classification algorithms existing today suffer in handling small data items such as short written reviews. In this paper we propose a model for a strongly relevant route recommendation system that is based on an MDL-based (Minimum Description Length) sentiment classification and show that such a system is capable of handling small data items (short user reviews). Another high…
University of Southern California（南加州大学）；Xtelligent, Inc.（Xtelligent公司）
We study route choice in a repeated routing game where an uncertain state of nature determines link latency functions, and agents receive private route recommendation. The state is sampled in an i.i.d. manner in every round from a publicly known distribution, and the recommendations are generated by a randomization policy whose mapping from the state is known publicly. In a one-shot setting, the agents are said to obey recommendation if it gives the smallest travel time in a posteriori expectation. A plausible extension to repeated setting is that the likelihood of following recommendation in …
GTR-Mamba: Geometry-to-Tangent Routing Mamba for Hyperbolic POI Recommendation
College of Computer Science and Technology, Tongji University（同济大学计算机科学与技术学院）；College of Information Engineering, Zhejiang University of Technology（浙江工业大学信息工程学院）；Shanghai Ballsnow Intelligent Technology Co., Ltd（上海 Ballsnow 智能科技有限公司）；Hunan University（湖南大学）
PHKT:Personalized Dynamic Hypergraph-enhanced KAN-Transformer for Multi-behavior Sequential Recommendation
Hangzhou Dianzi University（杭州电子科技大学）；School of Computer Science and Technology, Hangzhou Dianzi University（杭州电子科技大学计算机科学与技术学院）；Sanya Traditional Chinese Medicine Hospital（三亚市中医医院）；Combat Support College, Rocket Force University of Engineering（火箭军工程大学勤务学院）；Fuxi AI Lab, NetEase Games, NetEase Inc.（网易伏羲实验室，网易游戏，网易公司）
We focus on Maximum Inner Product Search (MIPS), which is an essential problem in many machine learning communities. Given a query, MIPS finds the most similar items with the maximum inner products. Methods for Nearest Neighbor Search (NNS) which is usually defined on metric space don't exhibit the satisfactory performance for MIPS problem since inner product is a non-metric function. However, inner products exhibit many good properties compared with metric functions, such as avoiding vanishing and exploding gradients. As a result, inner product is widely used in many recommendation systems, w…
Hangzhou Dianzi University（杭州电子科技大学）；University of Illinois at Chicago（伊利诺伊大学芝加哥分校）
This paper proposes a novel neural network, joint training capsule network (JTCN), for the cold start recommendation task. We propose to mimic the high-level user preference other than the raw interaction history based on the side information for the fresh users. Specifically, an attentive capsule layer is proposed to aggregate high-level user preference from the low-level interaction history via a dynamic routing-by-agreement mechanism. Moreover, JTCN jointly trains the loss for mimicking the user preference and the softmax loss for the recommendation together in an end-to-end manner. Experim…
CogRec: Structure-Cognitive Fast-and-Slow Reasoning for Generative Recommendation
Institute of Information Engineering, Chinese Academy of Sciences（中国科学院信息工程研究所）；School of Cyber Security, University of Chinese Academy of Sciences（中国科学院大学网络安全学院）；School of Artificial Intelligence, Beijing Normal University（北京师范大学人工智能学院）
Sequential Recommender Systems (SRSs) aim to predict the next item that users will consume, by modeling the user interests within their item sequences. While most existing SRSs focus on a single type of user behavior, only a few pay attention to multi-behavior sequences, although they are very common in real-world scenarios. It is challenging to effectively capture the user interests within multi-behavior sequences, because the information about user interests is entangled throughout the sequences in complex relationships. To this end, we first address the characteristics of multi-behavior seq…
Our goal is to build general representation (embedding) for each user and each product item across Alibaba's businesses, including Taobao and Tmall which are among the world's biggest e-commerce websites. The representation of users and items has been playing a critical role in various downstream applications, including recommendation system, search, marketing, demand forecasting and so on. Inspired from the BERT model in natural language processing (NLP) domain, we propose a GUIM (General User Item embedding with Mixture of representation) model to achieve the goal with massive, structured, m…
FindRec: Stein-Guided Entropic Flow for Multi-Modal Sequential Recommendation
City University of Hong Kong（香港城市大学）；Beihang University（北京航空航天大学）；University of Technology Sydney（悉尼科技大学）；The University of Queensland（昆士兰大学）；Fudan University（复旦大学）
Deep learning has brought significant breakthroughs in sequential recommendation (SR) for capturing dynamic user interests. A series of recent research revealed that models with more parameters usually achieve optimal performance for SR tasks, inevitably resulting in great challenges for deploying them in real systems. Following the simple assumption that light networks might already suffice for certain users, in this work, we propose CANet, a conceptually simple yet very scalable framework for assigning adaptive network architecture in an input-dependent manner to reduce unnecessary computati…
Question Routing in Community-based Question Answering websites aims at recommending newly posted questions to potential users who are most likely to provide "accepted answers". Most of the existing approaches predict users' expertise based on their past question answering behavior and the content of new questions. However, these approaches suffer from challenges in three aspects: 1) sparsity of users' past records results in lack of personalized recommendation that at times does not match users' interest or domain expertise, 2) modeling based on all questions and answers content makes periodi…
The explosively generated micro-videos on content sharing platforms call for recommender systems to permit personalized micro-video discovery with ease. Recent advances in micro-video recommendation have achieved remarkable performance in mining users' current preference based on historical behaviors. However, most of them neglect the dynamic and time-evolving nature of users' preference, and the prediction on future micro-videos with historically mined preference may deteriorate the effectiveness of recommender systems. In this paper, we propose the DMR framework to explicitly model dynamic m…
User reviews contain rich semantics towards the preference of users to features of items. Recently, many deep learning based solutions have been proposed by exploiting reviews for recommendation. The attention mechanism is mainly adopted in these works to identify words or aspects that are important for rating prediction. However, it is still hard to understand whether a user likes or dislikes an aspect of an item according to what viewpoint the user holds and to what extent, without examining the review details. Here, we consider a pair of a viewpoint held by a user and an aspect of an item a…
Multi-types of behaviors (e.g., clicking, adding to cart, purchasing, etc.) widely exist in most real-world recommendation scenarios, which are beneficial to learn users' multi-faceted preferences. As dependencies are explicitly exhibited by the multiple types of behaviors, effectively modeling complex behavior dependencies is crucial for multi-behavior prediction. The state-of-the-art multi-behavior models learn behavior dependencies indistinguishably with all historical interactions as input. However, different behaviors may reflect different aspects of user preference, which means that some…
