Configurable Mirror Descent: Towards a Unification of Decision Making

Decision-making problems, categorized as single-agent, e.g., Atari, cooperative multi-agent, e.g., Hanabi, competitive multi-agent, e.g., Hold'em poker, and mixed cooperative and competitive, e.g., football, are ubiquitous in the real world. Various methods are proposed to address the specific decision-making problems. Despite the successes in specific categories, these methods typically evolve independently and cannot generalize to other categories. Therefore, a fundamental question for decision-making is: \emph{Can we develop \textbf{a single algorithm} to tackle \textbf{ALL} categories of decision-making problems?} There are several main challenges to address this question: i) different decision-making categories involve different numbers of agents and different relationships between agents, ii) different categories have different solution concepts and evaluation measures, and iii) there lacks a comprehensive benchmark covering all the categories. This work presents a preliminary attempt to address the question with three main contributions. i) We propose the generalized mirror descent (GMD), a generalization of MD variants, which considers multiple historical policies and works with a broader class of Bregman divergences. ii) We propose the configurable mirror descent (CMD) where a meta-controller is introduced to dynamically adjust the hyper-parameters in GMD conditional on the evaluation measures. iii) We construct the \textsc{GameBench} with 15 academic-friendly games across different decision-making categories. Extensive experiments demonstrate that CMD achieves empirically competitive or better outcomes compared to baselines while providing the capability of exploring diverse dimensions of decision making.

Self-adaptive PSRO: Towards an Automatic Population-based Game Solver

Policy-Space Response Oracles (PSRO) as a general algorithmic framework has achieved state-of-the-art performance in learning equilibrium policies of two-player zero-sum games. However, the hand-crafted hyperparameter value selection in most of the existing works requires extensive domain knowledge, forming the main barrier to applying PSRO to different games. In this work, we make the first attempt to investigate the possibility of self-adaptively determining the optimal hyperparameter values in the PSRO framework. Our contributions are three-fold: (1) Using several hyperparameters, we propose a parametric PSRO that unifies the gradient descent ascent (GDA) and different PSRO variants. (2) We propose the self-adaptive PSRO (SPSRO) by casting the hyperparameter value selection of the parametric PSRO as a hyperparameter optimization (HPO) problem where our objective is to learn an HPO policy that can self-adaptively determine the optimal hyperparameter values during the running of the parametric PSRO. (3) To overcome the poor performance of online HPO methods, we propose a novel offline HPO approach to optimize the HPO policy based on the Transformer architecture. Experiments on various two-player zero-sum games demonstrate the superiority of SPSRO over different baselines.

Modality-Aware Integration with Large Language Models for Knowledge-based Visual Question Answering

Knowledge-based visual question answering (KVQA) has been extensively studied to answer visual questions with external knowledge, e.g., knowledge graphs (KGs). While several attempts have been proposed to leverage large language models (LLMs) as an implicit knowledge source, it remains challenging since LLMs may generate hallucinations. Moreover, multiple knowledge sources, e.g., images, KGs and LLMs, cannot be readily aligned for complex scenarios. To tackle these, we present a novel modality-aware integration with LLMs for KVQA (MAIL). It carefully leverages multimodal knowledge for both image understanding and knowledge reasoning. Specifically, (i) we propose a two-stage prompting strategy with LLMs to densely embody the image into a scene graph with detailed visual features; (ii) We construct a coupled concept graph by linking the mentioned entities with external facts. (iii) A tailored pseudo-siamese graph medium fusion is designed for sufficient multimodal fusion. We utilize the shared mentioned entities in two graphs as mediums to bridge a tight inter-modal exchange, while maximally preserving insightful intra-modal learning by constraining the fusion within mediums. Extensive experiments on two benchmark datasets show the superiority of MAIL with 24x less resources.

Structure Guided Large Language Model for SQL Generation

Generating accurate Structured Querying Language (SQL) is a long-standing problem, especially in matching users' semantic queries with structured databases and then generating structured SQL. Existing models typically input queries and database schemas into the LLM and rely on the LLM to perform semantic-structure matching and generate structured SQL. However, such solutions overlook the structural information within user queries and databases, which can be utilized to enhance the generation of structured SQL. This oversight can lead to inaccurate or unexecutable SQL generation. To fully exploit the structure, we propose a structure-to-SQL framework, which leverages the inherent structure information to improve the SQL generation of LLMs. Specifically, we introduce our Structure Guided SQL~(SGU-SQL) generation model. SGU-SQL first links user queries and databases in a structure-enhanced manner. It then decomposes complicated linked structures with grammar trees to guide the LLM to generate the SQL step by step. Extensive experiments on two benchmark datasets illustrate that SGU-SQL can outperform sixteen SQL generation baselines.

Knowledge-to-SQL: Enhancing SQL Generation with Data Expert LLM

Generating accurate SQL for user queries (text-to-SQL) is a long-standing problem since the generation of the SQL requires comprehending the query and database and retrivale the accurate data from the database accordingly. Existing models rely on the comprehensive ability of Large Language Models (LLMs) to generate the SQL according to the database schema. However, there is some necessary knowledge that is not explicitly included in the database schema or has been learned by LLMs. Thus, the generated SQL of the knowledge-insufficient queries may be inaccurate, which negatively impacts the robustness of the text-to-SQL models. To deal with this situation, we propose the Knowledge-to-SQL framework, which employs tailored Data Expert LLM (DELLM) to provide helpful knowledge for all types of text-to-SQL models. Specifically, we provide the detailed design of DELLM, in terms of table reading, and the basic fine-tuning process. We further provide a Reinforcement Learning via Database Feedback (RLDBF) training strategy to guide the DELLM to generate more helpful knowledge for LLMs. Extensive experiments verify DELLM can enhance the state-of-the-art LLMs on text-to-SQL tasks. The model structure and the parameter weight of DELLM are released for further research.

Multi-Behavior Collaborative Filtering with Partial Order Graph Convolutional Networks

Representing the information of multiple behaviors in the single graph collaborative filtering (CF) vector has been a long-standing challenge. This is because different behaviors naturally form separate behavior graphs and learn separate CF embeddings. Existing models merge the separate embeddings by appointing the CF embeddings for some behaviors as the primary embedding and utilizing other auxiliaries to enhance the primary embedding. However, this approach often results in the joint embedding performing well on the main tasks but poorly on the auxiliary ones. To address the problem arising from the separate behavior graphs, we propose the concept of Partial Order Graphs (POG). POG defines the partial order relation of multiple behaviors and models behavior combinations as weighted edges to merge separate behavior graphs into a joint POG. Theoretical proof verifies that POG can be generalized to any given set of multiple behaviors. Based on POG, we propose the tailored Partial Order Graph Convolutional Networks (POGCN) that convolute neighbors' information while considering the behavior relations between users and items. POGCN also introduces a partial-order BPR sampling strategy for efficient and effective multiple-behavior CF training. POGCN has been successfully deployed on the homepage of Alibaba for two months, providing recommendation services for over one billion users. Extensive offline experiments conducted on three public benchmark datasets demonstrate that POGCN outperforms state-of-the-art multi-behavior baselines across all types of behaviors. Furthermore, online A/B tests confirm the superiority of POGCN in billion-scale recommender systems.

Macro Graph Neural Networks for Online Billion-Scale Recommender Systems

Predicting Click-Through Rate (CTR) in billion-scale recommender systems poses a long-standing challenge for Graph Neural Networks (GNNs) due to the overwhelming computational complexity involved in aggregating billions of neighbors. To tackle this, GNN-based CTR models usually sample hundreds of neighbors out of the billions to facilitate efficient online recommendations. However, sampling only a small portion of neighbors results in a severe sampling bias and the failure to encompass the full spectrum of user or item behavioral patterns. To address this challenge, we name the conventional user-item recommendation graph as "micro recommendation graph" and introduce a more suitable MAcro Recommendation Graph (MAG) for billion-scale recommendations. MAG resolves the computational complexity problems in the infrastructure by reducing the node count from billions to hundreds. Specifically, MAG groups micro nodes (users and items) with similar behavior patterns to form macro nodes. Subsequently, we introduce tailored Macro Graph Neural Networks (MacGNN) to aggregate information on a macro level and revise the embeddings of macro nodes. MacGNN has already served Taobao's homepage feed for two months, providing recommendations for over one billion users. Extensive offline experiments on three public benchmark datasets and an industrial dataset present that MacGNN significantly outperforms twelve CTR baselines while remaining computationally efficient. Besides, online A/B tests confirm MacGNN's superiority in billion-scale recommender systems.

Developing Flying Explorer for Autonomous Digital Modelling in Wild Unknowns

This work presents an innovative solution for robotic odometry, path planning and exploration in wild unknown environments, focusing on digital modelling. The approach uses a minimum cost formulation with pseudo-randomly generated objectives, integrating multi-path planning and evaluation, with emphasis on full coverage of unknown maps based on feasible boundaries of interest. The evaluation carried out on a robotic platform with a lightweight 3D LiDAR sensor model, assesses the consistency and efficiency in exploring completely unknown subterranean-like areas. The algorithm allows for dynamic changes to the desired target and behaviour. At the same time, the paper details the design of AREX, highlighting its robust localisation, mapping and efficient exploration target selection capabilities, with a focus on continuity in exploration direction for increased efficiency and reduced odometry errors. The real-time, high-precision environmental perception module is identified as critical for accurate obstacle avoidance and exploration boundary identification.

KnowGPT: Black-Box Knowledge Injection for Large Language Models

Generative Large Language Models (LLMs), such as ChatGPT, offer interactive APIs that can answer common questions at a human-expert level. However, these models often give inaccurate or incorrect responses when faced with questions requiring domain-specific or professional-specific knowledge not covered in their training corpus. Furthermore, many state-of-the-art LLMs are not open-source, making it challenging to inject knowledge with model APIs only. In this work, we introduce KnowGPT, a black-box knowledge injection framework for LLMs in question answering. KnowGPT leverages deep reinforcement learning (RL) to extract relevant knowledge from Knowledge Graphs (KGs) and use Multi-Armed Bandit (MAB) to construct the most suitable prompt for each question. Our extensive experiments on three benchmark datasets showcase that KnowGPT significantly enhances the existing methods. Notably, KnowGPT achieves an average improvement of 23.7% over ChatGPT and an average improvement of 2.9% over GPT-4. Additionally, KnowGPT attains a 91.6% accuracy on the OpenbookQA official leaderboard, which is comparable to human-level performance.

XRMDN: A Recurrent Mixture Density Networks-based Architecture for Short-Term Probabilistic Demand Forecasting in Mobility-on-Demand Systems with High Volatility

In real Mobility-on-Demand (MoD) systems, demand is subject to high and dynamic volatility, which is difficult to predict by conventional time-series forecasting approaches. Most existing forecasting approaches yield the point value as the prediction result, which ignores the uncertainty that exists in the forecasting result. This will lead to the forecasting result severely deviating from the true demand value due to the high volatility existing in demand. To fill the gap, we propose an extended recurrent mixture density network (XRMDN), which extends the weight and mean neural networks to recurrent neural networks. The recurrent neurons for mean and variance can capture the trend of the historical data-series data, which enables a better forecasting result in dynamic and high volatility. We conduct comprehensive experiments on one taxi trip record and one bike-sharing real MoD data set to validate the performance of XRMDN. Specifically, we compare our model to three types of benchmark models, including statistical, machine learning, and deep learning models on three evaluation metrics. The validation results show that XRMDN outperforms the three groups of benchmark models in terms of the evaluation metrics. Most importantly, XRMDN substantially improves the forecasting accuracy with the demands in strong volatility. Last but not least, this probabilistic demand forecasting model contributes not only to the demand prediction in MoD systems but also to other optimization application problems, especially optimization under uncertainty, in MoD applications.