Jun Wang

Zhihao Lin, Wei Ma, Tao Lin et al.

Large Language Models (LLMs) have become instrumental in advancing software engineering (SE) tasks, showcasing their efficacy in code understanding and beyond. Like traditional SE tools, open-source collaboration is key in realising the excellent products. However, with AI models, the essential need is in data. The collaboration of these AI-based SE models hinges on maximising the sources of high-quality data. However, data especially of high quality, often holds commercial or sensitive value, making it less accessible for open-source AI-based SE projects. This reality presents a significant barrier to the development and enhancement of AI-based SE tools within the software engineering community. Therefore, researchers need to find solutions for enabling open-source AI-based SE models to tap into resources by different organisations. Addressing this challenge, our position paper investigates one solution to facilitate access to diverse organizational resources for open-source AI models, ensuring privacy and commercial sensitivities are respected. We introduce a governance framework centered on federated learning (FL), designed to foster the joint development and maintenance of open-source AI code models while safeguarding data privacy and security. Additionally, we present guidelines for developers on AI-based SE tool collaboration, covering data requirements, model architecture, updating strategies, and version control. Given the significant influence of data characteristics on FL, our research examines the effect of code data heterogeneity on FL performance.

Mengyue Yang, Quanyu Dai, Zhenhua Dong et al.

Top-N recommendation, which aims to learn user ranking-based preference, has long been a fundamental problem in a wide range of applications. Traditional models usually motivate themselves by designing complex or tailored architectures based on different assumptions. However, the training data of recommender system can be extremely sparse and imbalanced, which poses great challenges for boosting the recommendation performance. To alleviate this problem, in this paper, we propose to reformulate the recommendation task within the causal inference framework, which enables us to counterfactually simulate user ranking-based preferences to handle the data scarce problem. The core of our model lies in the counterfactual question: "what would be the user's decision if the recommended items had been different?". To answer this question, we firstly formulate the recommendation process with a series of structural equation models (SEMs), whose parameters are optimized based on the observed data. Then, we actively indicate many recommendation lists (called intervention in the causal inference terminology) which are not recorded in the dataset, and simulate user feedback according to the learned SEMs for generating new training samples. Instead of randomly intervening on the recommendation list, we design a learning-based method to discover more informative training samples. Considering that the learned SEMs can be not perfect, we, at last, theoretically analyze the relation between the number of generated samples and the model prediction error, based on which a heuristic method is designed to control the negative effect brought by the prediction error. Extensive experiments are conducted based on both synthetic and real-world datasets to demonstrate the effectiveness of our framework.

Xidong Feng, Chen Chen, Dong Li et al.

Practical recommender systems experience a cold-start problem when observed user-item interactions in the history are insufficient. Meta learning, especially gradient based one, can be adopted to tackle this problem by learning initial parameters of the model and thus allowing fast adaptation to a specific task from limited data examples. Though with significant performance improvement, it commonly suffers from two critical issues: the non-compatibility with mainstream industrial deployment and the heavy computational burdens, both due to the inner-loop gradient operation. These two issues make them hard to be applied in practical recommender systems. To enjoy the benefits of meta learning framework and mitigate these problems, we propose a recommendation framework called Contextual Modulation Meta Learning (CMML). CMML is composed of fully feed-forward operations so it is computationally efficient and completely compatible with the mainstream industrial deployment. CMML consists of three components, including a context encoder that can generate context embedding to represent a specific task, a hybrid context generator that aggregates specific user-item features with task-level context, and a contextual modulation network, which can modulate the recommendation model to adapt effectively. We validate our approach on both scenario-specific and user-specific cold-start setting on various real-world datasets, showing CMML can achieve comparable or even better performance with gradient based methods yet with much higher computational efficiency and better interpretability.

Simon Stiebellehner, Jun Wang, Shuai Yuan

Players in the online ad ecosystem are struggling to acquire the user data required for precise targeting. Audience look-alike modeling has the potential to alleviate this issue, but models' performance strongly depends on quantity and quality of available data. In order to maximize the predictive performance of our look-alike modeling algorithms, we propose two novel hybrid filtering techniques that utilize the recent neural probabilistic language model algorithm doc2vec. We apply these methods to data from a large mobile ad exchange and additional app metadata acquired from the Apple App store and Google Play store. First, we model mobile app users through their app usage histories and app descriptions (user2vec). Second, we introduce context awareness to that model by incorporating additional user and app-related metadata in model training (context2vec). Our findings are threefold: (1) the quality of recommendations provided by user2vec is notably higher than current state-of-the-art techniques. (2) User representations generated through hybrid filtering using doc2vec prove to be highly valuable features in supervised machine learning models for look-alike modeling. This represents the first application of hybrid filtering user models using neural probabilistic language models, specifically doc2vec, in look-alike modeling. (3) Incorporating context metadata in the doc2vec model training process to introduce context awareness has positive effects on performance and is superior to directly including the data as features in the downstream supervised models.

Yaodong Yang, Lantao Yu, Yiwei Bai et al.

We conduct an empirical study on discovering the ordered collective dynamics obtained by a population of intelligence agents, driven by million-agent reinforcement learning. Our intention is to put intelligent agents into a simulated natural context and verify if the principles developed in the real world could also be used in understanding an artificially-created intelligent population. To achieve this, we simulate a large-scale predator-prey world, where the laws of the world are designed by only the findings or logical equivalence that have been discovered in nature. We endow the agents with the intelligence based on deep reinforcement learning (DRL). In order to scale the population size up to millions agents, a large-scale DRL training platform with redesigned experience buffer is proposed. Our results show that the population dynamics of AI agents, driven only by each agent's individual self-interest, reveals an ordered pattern that is similar to the Lotka-Volterra model studied in population biology. We further discover the emergent behaviors of collective adaptations in studying how the agents' grouping behaviors will change with the environmental resources. Both of the two findings could be explained by the self-organization theory in nature.

Jun Wang, Qiang Tang

Probabilistic graphic model is an elegant framework to compactly present complex real-world observations by modeling uncertainty and logical flow (conditionally independent factors). In this paper, we present a probabilistic framework of neighborhood-based recommendation methods (PNBM) in which similarity is regarded as an unobserved factor. Thus, PNBM leads the estimation of user preference to maximizing a posterior over similarity. We further introduce a novel multi-layer similarity descriptor which models and learns the joint influence of various features under PNBM, and name the new framework MPNBM. Empirical results on real-world datasets show that MPNBM allows very accurate estimation of user preferences.

Phong Nguyen, Jun Wang, Alexandros Kalousis

Recommendation systems often rely on point-wise loss metrics such as the mean squared error. However, in real recommendation settings only few items are presented to a user. This observation has recently encouraged the use of rank-based metrics. LambdaMART is the state-of-the-art algorithm in learning to rank which relies on such a metric. Despite its success it does not have a principled regularization mechanism relying in empirical approaches to control model complexity leaving it thus prone to overfitting. Motivated by the fact that very often the users' and items' descriptions as well as the preference behavior can be well summarized by a small number of hidden factors, we propose a novel algorithm, LambdaMART Matrix Factorization (LambdaMART-MF), that learns a low rank latent representation of users and items using gradient boosted trees. The algorithm factorizes lambdaMART by defining relevance scores as the inner product of the learned representations of the users and items. The low rank is essentially a model complexity controller; on top of it we propose additional regularizers to constraint the learned latent representations that reflect the user and item manifolds as these are defined by their original feature based descriptors and the preference behavior. Finally we also propose to use a weighted variant of NDCG to reduce the penalty for similar items with large rating discrepancy. We experiment on two very different recommendation datasets, meta-mining and movies-users, and evaluate the performance of LambdaMART-MF, with and without regularization, in the cold start setting as well as in the simpler matrix completion setting. In both cases it outperforms in a significant manner current state of the art algorithms.

Jagadeesh Gorla, Stephen Robertson, Jun Wang et al.

In this work, we propose a theory for information matching. It is motivated by the observation that retrieval is about the relevance matching between two sets of properties (features), namely, the information need representation and information item representation. However, many probabilistic retrieval models rely on fixing one representation and optimizing the other (e.g. fixing the single information need and tuning the document) but not both. Therefore, it is difficult to use the available related information on both the document and the query at the same time in calculating the probability of relevance. In this paper, we address the problem by hypothesizing the relevance as a logical relationship between the two sets of properties; the relationship is defined on two separate mappings between these properties. By using the hypothesis we develop a unified probabilistic relevance model which is capable of using all the available information. We validate the proposed theory by formulating and developing probabilistic relevance ranking functions for both ad-hoc text retrieval and collaborative filtering. Our derivation in text retrieval illustrates the use of the theory in the situation where no relevance information is available. In collaborative filtering, we show that the resulting recommender model unifies the user and item information into a relevance ranking function without applying any dimensionality reduction techniques or computing explicit similarity between two different users (or items), in contrast to the state-of-the-art recommender models.