Zhe Wang

Julien Perolat, Bart de Vylder, Daniel Hennes et al.

We introduce DeepNash, an autonomous agent capable of learning to play the imperfect information game Stratego from scratch, up to a human expert level. Stratego is one of the few iconic board games that Artificial Intelligence (AI) has not yet mastered. This popular game has an enormous game tree on the order of $10^{535}$ nodes, i.e., $10^{175}$ times larger than that of Go. It has the additional complexity of requiring decision-making under imperfect information, similar to Texas hold'em poker, which has a significantly smaller game tree (on the order of $10^{164}$ nodes). Decisions in Stratego are made over a large number of discrete actions with no obvious link between action and outcome. Episodes are long, with often hundreds of moves before a player wins, and situations in Stratego can not easily be broken down into manageably-sized sub-problems as in poker. For these reasons, Stratego has been a grand challenge for the field of AI for decades, and existing AI methods barely reach an amateur level of play. DeepNash uses a game-theoretic, model-free deep reinforcement learning method, without search, that learns to master Stratego via self-play. The Regularised Nash Dynamics (R-NaD) algorithm, a key component of DeepNash, converges to an approximate Nash equilibrium, instead of 'cycling' around it, by directly modifying the underlying multi-agent learning dynamics. DeepNash beats existing state-of-the-art AI methods in Stratego and achieved a yearly (2022) and all-time top-3 rank on the Gravon games platform, competing with human expert players.

Yifang Qin, Yifan Wang, Fang Sun et al.

Point-of-Interest (POI) recommendation plays a vital role in various location-aware services. It has been observed that POI recommendation is driven by both sequential and geographical influences. However, since there is no annotated label of the dominant influence during recommendation, existing methods tend to entangle these two influences, which may lead to sub-optimal recommendation performance and poor interpretability. In this paper, we address the above challenge by proposing DisenPOI, a novel Disentangled dual-graph framework for POI recommendation, which jointly utilizes sequential and geographical relationships on two separate graphs and disentangles the two influences with self-supervision. The key novelty of our model compared with existing approaches is to extract disentangled representations of both sequential and geographical influences with contrastive learning. To be specific, we construct a geographical graph and a sequential graph based on the check-in sequence of a user. We tailor their propagation schemes to become sequence-/geo-aware to better capture the corresponding influences. Preference proxies are extracted from check-in sequence as pseudo labels for the two influences, which supervise the disentanglement via a contrastive loss. Extensive experiments on three datasets demonstrate the superiority of the proposed model.

Ziyan Yin, Zhe Wang, Jun Li et al.

The explosive growth of dynamic and heterogeneous data traffic brings great challenges for 5G and beyond mobile networks. To enhance the network capacity and reliability, we propose a learning-based dynamic time-frequency division duplexing (D-TFDD) scheme that adaptively allocates the uplink and downlink time-frequency resources of base stations (BSs) to meet the asymmetric and heterogeneous traffic demands while alleviating the inter-cell interference. We formulate the problem as a decentralized partially observable Markov decision process (Dec-POMDP) that maximizes the long-term expected sum rate under the users' packet dropping ratio constraints. In order to jointly optimize the global resources in a decentralized manner, we propose a federated reinforcement learning (RL) algorithm named federated Wolpertinger deep deterministic policy gradient (FWDDPG) algorithm. The BSs decide their local time-frequency configurations through RL algorithms and achieve global training via exchanging local RL models with their neighbors under a decentralized federated learning framework. Specifically, to deal with the large-scale discrete action space of each BS, we adopt a DDPG-based algorithm to generate actions in a continuous space, and then utilize Wolpertinger policy to reduce the mapping errors from continuous action space back to discrete action space. Simulation results demonstrate the superiority of our proposed algorithm to benchmark algorithms with respect to system sum rate.

Zhe Wang, Tingkai Yan

With the development of the Internet of Vehicles (IoV), vehicle wireless communication poses serious cybersecurity challenges. Faulty information, such as fake vehicle positions and speeds sent by surrounding vehicles, could cause vehicle collisions, traffic jams, and even casualties. Additionally, private vehicle data leakages, such as vehicle trajectory and user account information, may damage user property and security. Therefore, achieving a cyberattack-defense scheme in the IoV system with faulty data saturation is necessary. This paper proposes a Federated Learning-based Vehicle Trajectory Prediction Algorithm against Cyberattacks (FL-TP) to address the above problems. The FL-TP is intensively trained and tested using a publicly available Vehicular Reference Misbehavior (VeReMi) dataset with five types of cyberattacks: constant, constant offset, random, random offset, and eventual stop. The results show that the proposed FL-TP algorithm can improve cyberattack detection and trajectory prediction by up to 6.99% and 54.86%, respectively, under the maximum cyberattack permeability scenarios compared with benchmark methods.

Shangfeng Dai, Haobin Lin, Zhichen Zhao et al.

Recommendation for new users, also called user cold start, has been a well-recognized challenge for online recommender systems. Most existing methods view the crux as the lack of initial data. However, in this paper, we argue that there are neglected problems: 1) New users' behaviour follows much different distributions from regular users. 2) Although personalized features are involved, heavily imbalanced samples prevent the model from balancing new/regular user distributions, as if the personalized features are overwhelmed. We name the problem as the "submergence" of personalization. To tackle this problem, we propose a novel module: Personalized COld Start MOdules (POSO). Considering from a model architecture perspective, POSO personalizes existing modules by introducing multiple user-group-specialized sub-modules. Then, it fuses their outputs by personalized gates, resulting in comprehensive representations. In such way, POSO projects imbalanced features to even modules. POSO can be flexibly integrated into many existing modules and effectively improves their performance with negligible computational overheads. The proposed method shows remarkable advantage in industrial scenario. It has been deployed on the large-scale recommender system of Kwai, and improves new user Watch Time by a large margin (+7.75%). Moreover, POSO can be further generalized to regular users, inactive users and returning users (+2%-3% on Watch Time), as well as item cold start (+3.8% on Watch Time). Its effectiveness has also been verified on public dataset (MovieLens 20M). We believe such practical experience can be well generalized to other scenarios.

Zhe Wang, Liqin Zhao, Biye Jiang et al.

Multi-stage cascade architecture exists widely in many industrial systems such as recommender systems and online advertising, which often consists of sequential modules including matching, pre-ranking, ranking, etc. For a long time, it is believed pre-ranking is just a simplified version of the ranking module, considering the larger size of the candidate set to be ranked. Thus, efforts are made mostly on simplifying ranking model to handle the explosion of computing power for online inference. In this paper, we rethink the challenge of the pre-ranking system from an algorithm-system co-design view. Instead of saving computing power with restriction of model architecture which causes loss of model performance, here we design a new pre-ranking system by joint optimization of both the pre-ranking model and the computing power it costs. We name it COLD (Computing power cost-aware Online and Lightweight Deep pre-ranking system). COLD beats SOTA in three folds: (i) an arbitrary deep model with cross features can be applied in COLD under a constraint of controllable computing power cost. (ii) computing power cost is explicitly reduced by applying optimization tricks for inference acceleration. This further brings space for COLD to apply more complex deep models to reach better performance. (iii) COLD model works in an online learning and severing manner, bringing it excellent ability to handle the challenge of the data distribution shift. Meanwhile, the fully online pre-ranking system of COLD provides us with a flexible infrastructure that supports efficient new model developing and online A/B testing.Since 2019, COLD has been deployed in almost all products involving the pre-ranking module in the display advertising system in Alibaba, bringing significant improvements.

Pi Qi, Xiaoqiang Zhu, Guorui Zhou et al.

Rich user behavior data has been proven to be of great value for click-through rate prediction tasks, especially in industrial applications such as recommender systems and online advertising. Both industry and academy have paid much attention to this topic and propose different approaches to modeling with long sequential user behavior data. Among them, memory network based model MIMN proposed by Alibaba, achieves SOTA with the co-design of both learning algorithm and serving system. MIMN is the first industrial solution that can model sequential user behavior data with length scaling up to 1000. However, MIMN fails to precisely capture user interests given a specific candidate item when the length of user behavior sequence increases further, say, by 10 times or more. This challenge exists widely in previously proposed approaches. In this paper, we tackle this problem by designing a new modeling paradigm, which we name as Search-based Interest Model (SIM). SIM extracts user interests with two cascaded search units: (i) General Search Unit acts as a general search from the raw and arbitrary long sequential behavior data, with query information from candidate item, and gets a Sub user Behavior Sequence which is relevant to candidate item; (ii) Exact Search Unit models the precise relationship between candidate item and SBS. This cascaded search paradigm enables SIM with a better ability to model lifelong sequential behavior data in both scalability and accuracy. Apart from the learning algorithm, we also introduce our hands-on experience on how to implement SIM in large scale industrial systems. Since 2019, SIM has been deployed in the display advertising system in Alibaba, bringing 7.1\% CTR and 4.4\% RPM lift, which is significant to the business. Serving the main traffic in our real system now, SIM models user behavior data with maximum length reaching up to 54000, pushing SOTA to 54x.

Chen Luo, Wei Pang, Zhe Wang

Collaborative filtering algorithms haven been widely used in recommender systems. However, they often suffer from the data sparsity and cold start problems. With the increasing popularity of social media, these problems may be solved by using social-based recommendation. Social-based recommendation, as an emerging research area, uses social information to help mitigate the data sparsity and cold start problems, and it has been demonstrated that the social-based recommendation algorithms can efficiently improve the recommendation performance. However, few of the existing algorithms have considered using multiple types of relations within one social network. In this paper, we investigate the social-based recommendation algorithms on heterogeneous social networks and proposed Hete-CF, a Social Collaborative Filtering algorithm using heterogeneous relations. Distinct from the exiting methods, Hete-CF can effectively utilize multiple types of relations in a heterogeneous social network. In addition, Hete-CF is a general approach and can be used in arbitrary social networks, including event based social networks, location based social networks, and any other types of heterogeneous information networks associated with social information. The experimental results on two real-world data sets, DBLP (a typical heterogeneous information network) and Meetup (a typical event based social network) show the effectiveness and efficiency of our algorithm.