Dance generation, as a branch of human motion generation, has attracted increasing attention. Recently, a few works attempt to enhance dance expressiveness, which includes genre matching, beat alignment, and dance dynamics, from certain aspects. However, the enhancement is quite limited as they lack comprehensive consideration of the aforementioned three factors. In this paper, we propose ExpressiveBailando, a novel dance generation method designed to generate expressive dances, concurrently taking all three factors into account. Specifically, we mitigate the issue of speed homogenization by incorporating frequency information into VQ-VAE, thus improving dance dynamics. Additionally, we integrate music style information by extracting genre- and beat-related features with a pre-trained music model, hence achieving improvements in the other two factors. Extensive experimental results demonstrate that our proposed method can generate dances with high expressiveness and outperforms existing methods both qualitatively and quantitatively.
With the continuous increase of users and items, conventional recommender systems trained on static datasets can hardly adapt to changing environments. The high-throughput data requires the model to be updated in a timely manner for capturing the user interest dynamics, which leads to the emergence of streaming recommender systems. Due to the prevalence of deep learning-based recommender systems, the embedding layer is widely adopted to represent the characteristics of users, items, and other features in low-dimensional vectors. However, it has been proved that setting an identical and static embedding size is sub-optimal in terms of recommendation performance and memory cost, especially for streaming recommendations. To tackle this problem, we first rethink the streaming model update process and model the dynamic embedding size search as a bandit problem. Then, we analyze and quantify the factors that influence the optimal embedding sizes from the statistics perspective. Based on this, we propose the \textbf{D}ynamic \textbf{E}mbedding \textbf{S}ize \textbf{S}earch (\textbf{DESS}) method to minimize the embedding size selection regret on both user and item sides in a non-stationary manner. Theoretically, we obtain a sublinear regret upper bound superior to previous methods. Empirical results across two recommendation tasks on four public datasets also demonstrate that our approach can achieve better streaming recommendation performance with lower memory cost and higher time efficiency.
Personalized recommender systems have been widely studied and deployed to reduce information overload and satisfy users' diverse needs. However, conventional recommendation models solely conduct a one-time training-test fashion and can hardly adapt to evolving demands, considering user preference shifts and ever-increasing users and items in the real world. To tackle such challenges, the streaming recommendation is proposed and has attracted great attention recently. Among these, continual graph learning is widely regarded as a promising approach for the streaming recommendation by academia and industry. However, existing methods either rely on the historical data replay which is often not practical under increasingly strict data regulations, or can seldom solve the \textit{over-stability} issue. To overcome these difficulties, we propose a novel \textbf{D}ynamically \textbf{E}xpandable \textbf{G}raph \textbf{C}onvolution (DEGC) algorithm from a \textit{model isolation} perspective for the streaming recommendation which is orthogonal to previous methods. Based on the motivation of disentangling outdated short-term preferences from useful long-term preferences, we design a sequence of operations including graph convolution pruning, refining, and expanding to only preserve beneficial long-term preference-related parameters and extract fresh short-term preferences. Moreover, we model the temporal user preference, which is utilized as user embedding initialization, for better capturing the individual-level preference shifts. Extensive experiments on the three most representative GCN-based recommendation models and four industrial datasets demonstrate the effectiveness and robustness of our method.
Reinforcement learning (RL) techniques have shown great success in quantitative investment tasks, such as portfolio management and algorithmic trading. Especially, intraday trading is one of the most profitable and risky tasks because of the intraday behaviors of the financial market that reflect billions of rapidly fluctuating values. However, it is hard to apply existing RL methods to intraday trading due to the following three limitations: 1) overlooking micro-level market information (e.g., limit order book); 2) only focusing on local price fluctuation and failing to capture the overall trend of the whole trading day; 3) neglecting the impact of market risk. To tackle these limitations, we propose DeepScalper, a deep reinforcement learning framework for intraday trading. Specifically, we adopt an encoder-decoder architecture to learn robust market embedding incorporating both macro-level and micro-level market information. Moreover, a novel hindsight reward function is designed to provide the agent a long-term horizon for capturing the overall price trend. In addition, we propose a risk-aware auxiliary task by predicting future volatility, which helps the agent take market risk into consideration while maximizing profit. Finally, extensive experiments on two stock index futures and four treasury bond futures demonstrate that DeepScalper achieves significant improvement against many state-of-the-art approaches.
Current value-based multi-agent reinforcement learning methods optimize individual Q values to guide individuals' behaviours via centralized training with decentralized execution (CTDE). However, such expected, i.e., risk-neutral, Q value is not sufficient even with CTDE due to the randomness of rewards and the uncertainty in environments, which causes the failure of these methods to train coordinating agents in complex environments. To address these issues, we propose RMIX, a novel cooperative MARL method with the Conditional Value at Risk (CVaR) measure over the learned distributions of individuals' Q values. Specifically, we first learn the return distributions of individuals to analytically calculate CVaR for decentralized execution. Then, to handle the temporal nature of the stochastic outcomes during executions, we propose a dynamic risk level predictor for risk level tuning. Finally, we optimize the CVaR policies with CVaR values used to estimate the target in TD error during centralized training and the CVaR values are used as auxiliary local rewards to update the local distribution via Quantile Regression loss. Empirically, we show that our method significantly outperforms state-of-the-art methods on challenging StarCraft II tasks, demonstrating enhanced coordination and improved sample efficiency.
A common challenge in personalized user preference prediction is the cold-start problem. Due to the lack of user-item interactions, directly learning from the new users' log data causes serious over-fitting problem. Recently, many existing studies regard the cold-start personalized preference prediction as a few-shot learning problem, where each user is the task and recommended items are the classes, and the gradient-based meta learning method (MAML) is leveraged to address this challenge. However, in real-world application, the users are not uniformly distributed (i.e., different users may have different browsing history, recommended items, and user profiles. We define the major users as the users in the groups with large numbers of users sharing similar user information, and other users are the minor users), existing MAML approaches tend to fit the major users and ignore the minor users. To address this cold-start task-overfitting problem, we propose a novel personalized adaptive meta learning approach to consider both the major and the minor users with three key contributions: 1) We are the first to present a personalized adaptive learning rate meta-learning approach to improve the performance of MAML by focusing on both the major and minor users. 2) To provide better personalized learning rates for each user, we introduce a similarity-based method to find similar users as a reference and a tree-based method to store users' features for fast search. 3) To reduce the memory usage, we design a memory agnostic regularizer to further reduce the space complexity to constant while maintain the performance. Experiments on MovieLens, BookCrossing, and real-world production datasets reveal that our method outperforms the state-of-the-art methods dramatically for both the minor and major users.
With the rise of online e-commerce platforms, more and more customers prefer to shop online. To sell more products, online platforms introduce various modules to recommend items with different properties such as huge discounts. A web page often consists of different independent modules. The ranking policies of these modules are decided by different teams and optimized individually without cooperation, which might result in competition between modules. Thus, the global policy of the whole page could be sub-optimal. In this paper, we propose a novel multi-agent cooperative reinforcement learning approach with the restriction that different modules cannot communicate. Our contributions are three-fold. Firstly, inspired by a solution concept in game theory named correlated equilibrium, we design a signal network to promote cooperation of all modules by generating signals (vectors) for different modules. Secondly, an entropy-regularized version of the signal network is proposed to coordinate agents' exploration of the optimal global policy. Furthermore, experiments based on real-world e-commerce data demonstrate that our algorithm obtains superior performance over baselines.
Online recommendation services recommend multiple commodities to users. Nowadays, a considerable proportion of users visit e-commerce platforms by mobile devices. Due to the limited screen size of mobile devices, positions of items have a significant influence on clicks: 1) Higher positions lead to more clicks for one commodity. 2) The 'pseudo-exposure' issue: Only a few recommended items are shown at first glance and users need to slide the screen to browse other items. Therefore, some recommended items ranked behind are not viewed by users and it is not proper to treat this kind of items as negative samples. While many works model the online recommendation as contextual bandit problems, they rarely take the influence of positions into consideration and thus the estimation of the reward function may be biased. In this paper, we aim at addressing these two issues to improve the performance of online mobile recommendation. Our contributions are four-fold. First, since we concern the reward of a set of recommended items, we model the online recommendation as a contextual combinatorial bandit problem and define the reward of a recommended set. Second, we propose a novel contextual combinatorial bandit method called UBM-LinUCB to address two issues related to positions by adopting the User Browsing Model (UBM), a click model for web search. Third, we provide a formal regret analysis and prove that our algorithm achieves sublinear regret independent of the number of items. Finally, we evaluate our algorithm on two real-world datasets by a novel unbiased estimator. An online experiment is also implemented in Taobao, one of the most popular e-commerce platforms in the world. Results on two CTR metrics show that our algorithm outperforms the other contextual bandit algorithms.
Connectionist models such as neural networks suffer from catastrophic forgetting. In this work, we study this problem from the perspective of information theory and define forgetting as the increase of description lengths of previous data when they are compressed with a sequentially learned model. In addition, we show that continual learning approaches based on variational posterior approximation and generative replay can be considered as approximations to two prequential coding methods in compression, namely, the Bayesian mixture code and maximum likelihood (ML) plug-in code. We compare these approaches in terms of both compression and forgetting and empirically study the reasons that limit the performance of continual learning methods based on variational posterior approximation. To address these limitations, we propose a new continual learning method that combines ML plug-in and Bayesian mixture codes.