Hong Qian

Hong Qian, Yuanhao Liu, Zihan Zhou et al.

While LLM-based agents excel at individual tasks, effective collaboration with realistic human partners remains challenging. Most of the existing conversation-level collaborative studies lack grounded interaction and behavioral execution, motivating the need for cooperative game environments that enable contextualized and immersive collaboration. To this end, this paper proposes CollabBench, a benchmark for evaluating and training collaborative agents in cooperative games. CollabBench features a Diverse Player Profile Simulation pipeline to model varied players behaviors, and a Collaborative Agentic Training paradigm that unifies reasoning, communication, and action via agentic rollouts, optimized with a hybrid reward balancing task efficiency and affective adaptation. We further extend classic environments to CWAH-MultiPlayer and Cook-MultiPlayer for systematic evaluation under diverse personalities. Experiments with efficiency and affective metrics show that our trained models outperform base models, achieving 19.5% higher efficiency and 24.4% improved affective performance. Further analysis reveals key collaborative limitations of existing models and offers insights for future collaborative training.

Haochen Yang, Ke Zhao, Mengyuan Ma et al.

Leveraging Large Language Models (LLMs) to automatically formulate and solve optimization problems from natural language has emerged as an efficient paradigm for automated optimization. However, existing methods still exhibit limited generalization: they are sensitive to superficial narrative variations, reuse experience mainly at the case level, and struggle to adapt to shifted or emerging problem types. We propose OptSkills, an archetype-centric skill learning and reasoning agent system for optimization modeling and solving. To improve robust generalization, our system clusters problems by their underlying archetypes rather than surface narratives. To improve in-distribution generalization, it explores diverse modeling paradigms and solver configurations within each cluster, then distills successful trajectories into reusable workflow-level skills. To improve out-of-distribution generalization, it refines existing skills or expands the skill library using newly obtained trajectories. Our system achieves a state-of-the-art micro-averaged accuracy of 68.27% on datasets encompassing diverse problem types and scenarios. In addition, on MIPLIB-NL, a highly challenging large-scale and high-dimensional benchmark, it achieves 26.91% accuracy, outperforming DeepSeek-V3.2-Thinking by 4.53%. After skill learning on Nano-CO, it reaches 72.79% on the OOD NLCO benchmark. Code and skills are available at https://github.com/fujiwaranoM0kou/OptSkills.

Tianxiang Sun, Zhengfu He, Hong Qian et al.

Most downstream adaptation methods tune all or part of the parameters of pre-trained models (PTMs) through gradient descent, where the tuning cost increases linearly with the growth of the model size. By contrast, gradient-free methods only require the forward computation of the PTM to tune the prompt, retaining the benefits of efficient tuning and deployment. Though, past work on gradient-free tuning often introduces gradient descent to seek a good initialization of prompt and lacks versatility across tasks and PTMs. In this paper, we present BBTv2, an improved version of Black-Box Tuning, to drive PTMs for few-shot learning. We prepend continuous prompts to every layer of the PTM and propose a divide-and-conquer gradient-free algorithm to optimize the prompts at different layers alternately. Extensive experiments across various tasks and PTMs show that BBTv2 can achieve comparable performance to full model tuning and state-of-the-art parameter-efficient methods (e.g., Adapter, LoRA, BitFit, etc.) under few-shot settings while maintaining much fewer tunable parameters.

Yulei Ye, Wenhao Li, Zhong Wen et al.

Despite the rapid deployment of LLMs into classrooms, validating educational AI remains uniquely intractable: interventions act on developing learners whose cognitive and social trajectories are irreversibly shaped, while real-world trials are slow, ethically constrained, and institutionally locked. LLM-based educational simulators have emerged as a potential remedy, but many still collapse learning into persona-conditioned role-play and, when optimized only to reproduce existing classrooms, can structurally penalize the institutional novelty that pedagogical reform requires. In this work, we introduce AgentSchool, an LLM-driven multi-agent simulator that models learning as state transition rather than prompted behavior. AgentSchool couples cognitively growable student agents -- equipped with weighted subject knowledge graphs, thinking-workflow pools, and explicit misconceptions -- with adaptive teacher agents that plan, scaffold, and reflect along the Zone of Proximal Development, embedded in a configurable scenery generator that situates instruction within both formal and informal learning fields, and a multi-scale simulator that decouples interaction scale, temporal granularity, and simulation duration. Experiments show that structured student agents produce more differentiated mastery and misconception traces than a baseline simulator, while teacher-agent comparisons show backbone-dependent patterns consistent with ZPD-informed adaptation. Further, AgentSchool generates plausible traces of peripheral participation, clique formation, aggressor-induced cohesion, and opinion-leader emergence consistent with classroom social theories. Beyond its role as an educational research instrument, AgentSchool frames education as a socially meaningful testbed for long-horizon memory, multi-agent coordination, and future institutional reasoning under organizational pressure.

Rong-Jun Qin, Fan-Ming Luo, Hong Qian et al.

This paper addresses policy learning in non-stationary environments and games with continuous actions. Rather than the classical reward maximization mechanism, inspired by the ideas of follow-the-regularized-leader (FTRL) and mirror descent (MD) update, we propose a no-regret style reinforcement learning algorithm PORL for continuous action tasks. We prove that PORL has a last-iterate convergence guarantee, which is important for adversarial and cooperative games. Empirical studies show that, in stationary environments such as MuJoCo locomotion controlling tasks, PORL performs equally well as, if not better than, the soft actor-critic (SAC) algorithm; in non-stationary environments including dynamical environments, adversarial training, and competitive games, PORL is superior to SAC in both a better final policy performance and a more stable training process.

You Zhou, Xiujing Lin, Xiang Zhang et al.

Artificial Intelligence (AI) has achieved significant advancements in technology and research with the development over several decades, and is widely used in many areas including computing vision, natural language processing, time-series analysis, speech synthesis, etc. During the age of deep learning, especially with the arise of Large Language Models, a large majority of researchers' attention is paid on pursuing new state-of-the-art (SOTA) results, resulting in ever increasing of model size and computational complexity. The needs for high computing power brings higher carbon emission and undermines research fairness by preventing small or medium-sized research institutions and companies with limited funding in participating in research. To tackle the challenges of computing resources and environmental impact of AI, Green Computing has become a hot research topic. In this survey, we give a systematic overview of the technologies used in Green Computing. We propose the framework of Green Computing and devide it into four key components: (1) Measures of Greenness, (2) Energy-Efficient AI, (3) Energy-Efficient Computing Systems and (4) AI Use Cases for Sustainability. For each components, we discuss the research progress made and the commonly used techniques to optimize the AI efficiency. We conclude that this new research direction has the potential to address the conflicts between resource constraints and AI development. We encourage more researchers to put attention on this direction and make AI more environmental friendly.

Hong Qian, Xiang Shu, Xiang Xia et al.

Bayesian optimization is widely employed for optimizing complex black-box functions but struggles with the curse of dimensionality. Random embedding, as a dimension reduction strategy, simplifies tasks that possess the effective dimension by optimizing within a low-dimensional subspace. However, determining the effective dimension of a task in advance remains a significant challenge, which influences the selection of the subspace dimensionality and the optimization performance. Traditional methods use fixed subspace dimensions provided by experts or rely on trial and error to estimate subspace dimensions with resources consumed. To this end, this paper proposes an automated random embedding for high-dimensional Bayesian optimization with unknown effective dimension, called Dynamic Shared Embedding Bayesian Optimization (DSEBO). DSEBO starts with a low dimension and switches to a higher subspace if the solutions in the current subspace show preliminary convergence. DSEBO dynamically determines the dimension of the next subspace based on the quality of the solutions in different subspaces and shares the queried solutions with the new subspace for a better initialization. Theoretically, we derive a regret bound for DSEBO and demonstrate that DSEBO can better balance approximation and optimization errors. Extensive experiments on functions with dimensionality of varying magnitudes and real-world tasks with unknown effective dimensions reveal that, compared with state-of-the-art methods, alternating optimization across different subspaces results in significant improvements in high-dimensional optimization, both in terms of optimization regret and time.

Caigao Jiang, Xiang Shu, Hong Qian et al.

Optimization problems are prevalent across various scenarios. Formulating and then solving optimization problems described by natural language often requires highly specialized human expertise, which could block the widespread application of optimization-based decision making. To automate problem formulation and solving, leveraging large language models (LLMs) has emerged as a potential way. However, this kind of approach suffers from the issue of optimization generalization. Namely, the accuracy of most current LLM-based methods and the generality of optimization problem types that they can model are still limited. In this paper, we propose a unified learning-based framework called LLMOPT to boost optimization generalization. Starting from the natural language descriptions of optimization problems and a pre-trained LLM, LLMOPT constructs the introduced five-element formulation as a universal model for learning to define diverse optimization problem types. Then, LLMOPT employs the multi-instruction tuning to enhance both problem formalization and solver code generation accuracy and generality. After that, to prevent hallucinations in LLMs, such as sacrificing solving accuracy to avoid execution errors, the model alignment and self-correction mechanism are adopted in LLMOPT. We evaluate the optimization generalization ability of LLMOPT and compared methods across six real-world datasets covering roughly 20 fields such as health, environment, energy and manufacturing, etc. Extensive experiment results show that LLMOPT is able to model various optimization problem types such as linear/nonlinear programming, mixed integer programming, and combinatorial optimization, and achieves a notable 11.08% average solving accuracy improvement compared with the state-of-the-art methods. The code is available at https://github.com/caigaojiang/LLMOPT.

Yixuan Wang, Yue Huang, Hong Qian et al.

Creativity has become a core competence in the era of LLMs and human-AI collaboration, underpinning innovation in real-world problem solving. Crucially, the systematic improvement of creativity necessitates scientifically valid assessment instruments. Psychometric research recognizes context-based assessment as an effective way to measure creative thinking. However, high-quality expert-designed contexts remain scarce. Existing LLM-based generators often struggle with insufficient assessment cues, weak narrative coherence, limited stylistic diversity, and poor support for creative thinking. To address these challenges, we propose AlphaContext, an evolutionary tree-based psychometric context generator for creativity assessment. First, the HyperTree Outline Planner formalizes expert-designed outlining as a rule-guided hypertree and performs top-down hierarchical planning. The MCTS-based Context Generator fills the outline via MCTS to balance global structure and local quality. Then, the Evolutionary Context Optimizer evolves contexts with MAP-Elites by repeatedly updating niche elites to jointly improve diversity and quality. Finally, the Assessment-Guided Evolution Refiner simulates virtual participants with diverse styles and recycles weak contexts for further evolution. Experiments show that AlphaContext yields an average improvement of 8% over competitive methods across 6 quality metrics.

Jiajun Cui, Hong Qian, Chanjin Zheng et al.

Knowledge tracing (KT) is a crucial task in computer-aided education and intelligent tutoring systems, predicting students' performance on new questions from their responses to prior ones. An accurate KT model can capture a student's mastery level of different knowledge topics, as reflected in their predicted performance on different questions. This helps improve the learning efficiency by suggesting appropriate new questions that complement students' knowledge states. However, current KT models have significant drawbacks that they neglect the imbalanced discrimination of historical responses. A significant proportion of question responses provide limited information for discerning students' knowledge mastery, such as those that demonstrate uniform performance across different students. Optimizing the prediction of these cases may increase overall KT accuracy, but also negatively impact the model's ability to trace personalized knowledge states, especially causing a deceptive surge of performance. Towards this end, we propose a framework to reweight the contribution of different responses based on their discrimination in training. Additionally, we introduce an adaptive predictive score fusion technique to maintain accuracy on less discriminative responses, achieving proper balance between student knowledge mastery and question difficulty. Experimental results demonstrate that our framework enhances the performance of three mainstream KT methods on three widely-used datasets.

Shuo Liu, An Zhang, Guoqing Hu et al.

Recommender systems predict personalized item rankings based on user preference distributions derived from historical behavior data. Recently, diffusion models (DMs) have gained attention in recommendation for their ability to model complex distributions, yet current DM-based recommenders often rely on traditional objectives like mean squared error (MSE) or recommendation objectives, which are not optimized for personalized ranking tasks or fail to fully leverage DM's generative potential. To address this, we propose PreferDiff, a tailored optimization objective for DM-based recommenders. PreferDiff transforms BPR into a log-likelihood ranking objective and integrates multiple negative samples to better capture user preferences. Specifically, we employ variational inference to handle the intractability through minimizing the variational upper bound and replaces MSE with cosine error to improve alignment with recommendation tasks. Finally, we balance learning generation and preference to enhance the training stability of DMs. PreferDiff offers three key benefits: it is the first personalized ranking loss designed specifically for DM-based recommenders and it improves ranking and faster convergence by addressing hard negatives. We also prove that it is theoretically connected to Direct Preference Optimization which indicates that it has the potential to align user preferences in DM-based recommenders via generative modeling. Extensive experiments across three benchmarks validate its superior recommendation performance and commendable general sequential recommendation capabilities. Our codes are available at https://github.com/lswhim/PreferDiff.

Viswa Virinchi Muppirala, Hong Qian

The manifold of empirical mean values of statistical data ad infinitum has a geometric shape that depends on the probability measure that governs the generating model. Large deviation theory produces entropy functions that depend on both the probability measure and the statistical data; we use entropy to study the geometry of the data space rather than that of the space of probability distributions. It is well known, since Rao's work, that the Fisher-Rao metric makes the probability simplex into a sphere. From our perspective, that result translates to the space of empirical singleton counting frequencies under an i.i.d. assumption. Following our ideas and going beyond i.i.d., the choice of measure curves the space. When we study the pairwise statistics, the spherical geometry breaks down entirely. We show that the information projection, defined in information geometry as divergence minimization, coincides with the information projection in Kolmogorov's probability theory. This identification holds under both i.i.d. and Markovian assumptions and connects information geometry to the foundations of probability theory.

Jiajun Cui, Hong Qian, Bo Jiang et al.

Knowledge tracing (KT) is a crucial task in intelligent education, focusing on predicting students' performance on given questions to trace their evolving knowledge. The advancement of deep learning in this field has led to deep-learning knowledge tracing (DLKT) models that prioritize high predictive accuracy. However, many existing DLKT methods overlook the fundamental goal of tracking students' dynamical knowledge mastery. These models do not explicitly model knowledge mastery tracing processes or yield unreasonable results that educators find difficulty to comprehend and apply in real teaching scenarios. In response, our research conducts a preliminary analysis of mainstream KT approaches to highlight and explain such unreasonableness. We introduce GRKT, a graph-based reasonable knowledge tracing method to address these issues. By leveraging graph neural networks, our approach delves into the mutual influences of knowledge concepts, offering a more accurate representation of how the knowledge mastery evolves throughout the learning process. Additionally, we propose a fine-grained and psychological three-stage modeling process as knowledge retrieval, memory strengthening, and knowledge learning/forgetting, to conduct a more reasonable knowledge tracing process. Comprehensive experiments demonstrate that GRKT outperforms eleven baselines across three datasets, not only enhancing predictive accuracy but also generating more reasonable knowledge tracing results. This makes our model a promising advancement for practical implementation in educational settings. The source code is available at https://github.com/JJCui96/GRKT.

Shuo Liu, Junhao Shen, Hong Qian et al.

Cognitive diagnosis aims to gauge students' mastery levels based on their response logs. Serving as a pivotal module in web-based online intelligent education systems (WOIESs), it plays an upstream and fundamental role in downstream tasks like learning item recommendation and computerized adaptive testing. WOIESs are open learning environment where numerous new students constantly register and complete exercises. In WOIESs, efficient cognitive diagnosis is crucial to fast feedback and accelerating student learning. However, the existing cognitive diagnosis methods always employ intrinsically transductive student-specific embeddings, which become slow and costly due to retraining when dealing with new students who are unseen during training. To this end, this paper proposes an inductive cognitive diagnosis model (ICDM) for fast new students' mastery levels inference in WOIESs. Specifically, in ICDM, we propose a novel student-centered graph (SCG). Rather than inferring mastery levels through updating student-specific embedding, we derive the inductive mastery levels as the aggregated outcomes of students' neighbors in SCG. Namely, SCG enables to shift the task from finding the most suitable student-specific embedding that fits the response logs to finding the most suitable representations for different node types in SCG, and the latter is more efficient since it no longer requires retraining. To obtain this representation, ICDM consists of a construction-aggregation-generation-transformation process to learn the final representation of students, exercises and concepts. Extensive experiments across real-world datasets show that, compared with the existing cognitive diagnosis methods that are always transductive, ICDM is much more faster while maintains the competitive inference performance for new students.

Junhao Shen, Hong Qian, Wei Zhang et al.

Cognitive diagnosis assessment is a fundamental and crucial task for student learning. It models the student-exercise interaction, and discovers the students' proficiency levels on each knowledge attribute. In real-world intelligent education systems, generalization and interpretability of cognitive diagnosis methods are of equal importance. However, most existing methods can hardly make the best of both worlds due to the complicated student-exercise interaction. To this end, this paper proposes a symbolic cognitive diagnosis~(SCD) framework to simultaneously enhance generalization and interpretability. The SCD framework incorporates the symbolic tree to explicably represent the complicated student-exercise interaction function, and utilizes gradient-based optimization methods to effectively learn the student and exercise parameters. Meanwhile, the accompanying challenge is that we need to tunnel the discrete symbolic representation and continuous parameter optimization. To address this challenge, we propose to hybridly optimize the representation and parameters in an alternating manner. To fulfill SCD, it alternately learns the symbolic tree by derivative-free genetic programming and learns the student and exercise parameters via gradient-based Adam. The extensive experimental results on various real-world datasets show the superiority of SCD on both generalization and interpretability. The ablation study verifies the efficacy of each ingredient in SCD, and the case study explicitly showcases how the interpretable ability of SCD works.

Bingdong Li, Zixiang Di, Yongfan Lu et al.

Multi-objective Bayesian optimization (MOBO) has shown promising performance on various expensive multi-objective optimization problems (EMOPs). However, effectively modeling complex distributions of the Pareto optimal solutions is difficult with limited function evaluations. Existing Pareto set learning algorithms may exhibit considerable instability in such expensive scenarios, leading to significant deviations between the obtained solution set and the Pareto set (PS). In this paper, we propose a novel Composite Diffusion Model based Pareto Set Learning algorithm, namely CDM-PSL, for expensive MOBO. CDM-PSL includes both unconditional and conditional diffusion model for generating high-quality samples. Besides, we introduce an information entropy based weighting method to balance different objectives of EMOPs. This method is integrated with the guiding strategy, ensuring that all the objectives are appropriately balanced and given due consideration during the optimization process; Extensive experimental results on both synthetic benchmarks and real-world problems demonstrates that our proposed algorithm attains superior performance compared with various state-of-the-art MOBO algorithms.

Yuanhao Liu, Shuo Liu, Yimeng Liu et al.

Cognitive diagnosis model (CDM) is a fundamental and upstream component in intelligent education. It aims to infer students' mastery levels based on historical response logs. However, existing CDMs usually follow the ID-based embedding paradigm, which could often diminish the effectiveness of CDMs in open student learning environments. This is mainly because they can hardly directly infer new students' mastery levels or utilize new exercises or knowledge without retraining. Textual semantic information, due to its unified feature space and easy accessibility, can help alleviate this issue. Unfortunately, directly incorporating semantic information may not benefit CDMs, since it does not capture response-relevant features and thus discards the individual characteristics of each student. To this end, this paper proposes a dual-fusion cognitive diagnosis framework (DFCD) to address the challenge of aligning two different modalities, i.e., textual semantic features and response-relevant features. Specifically, in DFCD, we first propose the exercise-refiner and concept-refiner to make the exercises and knowledge concepts more coherent and reasonable via large language models. Then, DFCD encodes the refined features using text embedding models to obtain the semantic information. For response-related features, we propose a novel response matrix to fully incorporate the information within the response logs. Finally, DFCD designs a dual-fusion module to merge the two modal features. The ultimate representations possess the capability of inference in open student learning environments and can be also plugged in existing CDMs. Extensive experiments across real-world datasets show that DFCD achieves superior performance by integrating different modalities and strong adaptability in open student learning environments.

Yongfan Lu, Zixiang Di, Bingdong Li et al.

Multi-objective combinatorial optimization (MOCO) problems are prevalent in various real-world applications. Most existing neural MOCO methods rely on problem decomposition to transform an MOCO problem into a series of singe-objective combinatorial optimization (SOCO) problems and train attention models based on a single-step and deterministic greedy rollout. However, inappropriate decomposition and undesirable short-sighted behaviors of previous methods tend to induce a decline in diversity. To address the above limitation, we design a Context-aware Diversity Enhancement algorithm named CDE, which casts the neural MOCO problems as conditional sequence modeling via autoregression (node-level context awareness) and establishes a direct relationship between the mapping of preferences and diversity indicator of reward based on hypervolume expectation maximization (solution-level context awareness). Based on the solution-level context awareness, we further propose a hypervolume residual update strategy to enable the Pareto attention model to capture both local and non-local information of the Pareto set/front. The proposed CDE can effectively and efficiently grasp the context information, resulting in diversity enhancement. Experimental results on three classic MOCO problems demonstrate that our CDE outperforms several state-of-the-art baselines.

Shuo Liu, Zihan Zhou, Yuanhao Liu et al.

Cognitive diagnosis aims to infer students' mastery levels based on their historical response logs. However, existing cognitive diagnosis models (CDMs), which rely on ID embeddings, often have to train specific models on specific domains. This limitation may hinder their directly practical application in various target domains, such as different subjects (e.g., Math, English and Physics) or different education platforms (e.g., ASSISTments, Junyi Academy and Khan Academy). To address this issue, this paper proposes the language representation favored zero-shot cross-domain cognitive diagnosis (LRCD). Specifically, LRCD first analyzes the behavior patterns of students, exercises and concepts in different domains, and then describes the profiles of students, exercises and concepts using textual descriptions. Via recent advanced text-embedding modules, these profiles can be transformed to vectors in the unified language space. Moreover, to address the discrepancy between the language space and the cognitive diagnosis space, we propose language-cognitive mappers in LRCD to learn the mapping from the former to the latter. Then, these profiles can be easily and efficiently integrated and trained with existing CDMs. Extensive experiments show that training LRCD on real-world datasets can achieve commendable zero-shot performance across different target domains, and in some cases, it can even achieve competitive performance with some classic CDMs trained on the full response data on target domains. Notably, we surprisingly find that LRCD can also provide interesting insights into the differences between various subjects (such as humanities and sciences) and sources (such as primary and secondary education).

Yuanhao Liu, Zihan Zhou, Kaiying Wu et al.

Learner-item cognitive modeling plays a central role in the web-based online intelligent education system by enabling cognitive diagnosis (CD) across diverse online educational scenarios. Although ID embedding remains the mainstream approach in cognitive modeling due to its effectiveness and flexibility, recent advances in language models (LMs) have introduced new possibilities for incorporating rich semantic representations to enhance CD performance. This highlights the need for a comprehensive analysis of how LMs enhance embeddings through semantic integration across mainstream CD tasks. This paper identifies two key challenges in fully leveraging LMs in existing work: Misalignment between the training objectives of LMs and CD models creates a distribution gap in feature spaces; A unified framework is essential for integrating textual embeddings across varied CD tasks while preserving the strengths of existing cognitive modeling paradigms to ensure the robustness of embedding enhancement. To address these challenges, this paper introduces EduEmbed, a unified embedding enhancement framework that leverages fine-tuned LMs to enrich learner-item cognitive modeling across diverse CD tasks. EduEmbed operates in two stages. In the first stage, we fine-tune LMs based on role-specific representations and an interaction diagnoser to bridge the semantic gap of CD models. In the second stage, we employ a textual adapter to extract task-relevant semantics and integrate them with existing modeling paradigms to improve generalization. We evaluate the proposed framework on four CD tasks and computerized adaptive testing (CAT) task, achieving robust performance. Further analysis reveals the impact of semantic information across diverse tasks, offering key insights for future research on the application of LMs in CD for online intelligent education systems.

Bingdong Li, Mei Jiang, Hong Qian et al.

Evolutionary Reinforcement Learning (ERL), training the Reinforcement Learning (RL) policies with Evolutionary Algorithms (EAs), have demonstrated enhanced exploration capabilities and greater robustness than using traditional policy gradient. However, ERL suffers from the high computational costs and low search efficiency, as EAs require evaluating numerous candidate policies with expensive simulations, many of which are ineffective and do not contribute meaningfully to the training. One intuitive way to reduce the ineffective evaluations is to adopt the surrogates. Unfortunately, existing ERL policies are often modeled as deep neural networks (DNNs) and thus naturally represented as high-dimensional vectors containing millions of weights, which makes the building of effective surrogates for ERL policies extremely challenging. This paper proposes a novel surrogate-assisted ERL that integrates Autoencoders (AE) and Hyperbolic Neural Networks (HNN). Specifically, AE compresses high-dimensional policies into low-dimensional representations while extracting key features as the inputs for the surrogate. HNN, functioning as a classification-based surrogate model, can learn complex nonlinear relationships from sampled data and enable more accurate pre-selection of the sampled policies without real evaluations. The experiments on 10 Atari and 4 Mujoco games have verified that the proposed method outperforms previous approaches significantly. The search trajectories guided by AE and HNN are also visually demonstrated to be more effective, in terms of both exploration and convergence. This paper not only presents the first learnable policy embedding and surrogate-modeling modules for high-dimensional ERL policies, but also empirically reveals when and why they can be successful.

Bingdong Li, Zixiang Di, Yanting Yang et al.

In this paper, we introduce a novel approach for addressing the multi-objective optimization problem in large language model merging via black-box multi-objective optimization algorithms. The goal of model merging is to combine multiple models, each excelling in different tasks, into a single model that outperforms any of the individual source models. However, model merging faces two significant challenges: First, existing methods rely heavily on human knowledge or intuition. Second, it's difficult to obtain the great model merging configuration in limited evaluations. To address these challenges, we formalize model merging as a multi-objective optimization problem and propose an automated optimization approach named MM-MO. This method leverages multi-objective optimization algorithms to autonomously search for optimal merging configurations across various tasks, alleviating the need for human intervention. In MM-MO, a weak-to-strong method is employed to enhance the acquisition function, allowing previously evaluated superior configurations to guide the search for new ones. Meanwhile, Fisher information is applied to screen these configurations, increasing the possibility of identifying high-quality merging configuration. Additionally, we designed a sparsity metric as an additional optimization objective to enhance the model's generalization performance across different tasks. We conducted comprehensive experiments with other mainstream model merging methods, demonstrating that the proposed MM-MO algorithm is competitive and effective in achieving high-quality model merging.

Hong Qian, Shuo Liu, Mingjia Li et al.

Cognitive diagnosis models (CDMs) are designed to learn students' mastery levels using their response logs. CDMs play a fundamental role in online education systems since they significantly influence downstream applications such as teachers' guidance and computerized adaptive testing. Despite the success achieved by existing CDMs, we find that they suffer from a thorny issue that the learned students' mastery levels are too similar. This issue, which we refer to as oversmoothing, could diminish the CDMs' effectiveness in downstream tasks. CDMs comprise two core parts: learning students' mastery levels and assessing mastery levels by fitting the response logs. This paper contends that the oversmoothing issue arises from that existing CDMs seldom utilize response signals on exercises in the learning part but only use them as labels in the assessing part. To this end, this paper proposes an oversmoothing-resistant cognitive diagnosis framework (ORCDF) to enhance existing CDMs by utilizing response signals in the learning part. Specifically, ORCDF introduces a novel response graph to inherently incorporate response signals as types of edges. Then, ORCDF designs a tailored response-aware graph convolution network (RGC) that effectively captures the crucial response signals within the response graph. Via ORCDF, existing CDMs are enhanced by replacing the input embeddings with the outcome of RGC, allowing for the consideration of response signals on exercises in the learning part. Extensive experiments on real-world datasets show that ORCDF not only helps existing CDMs alleviate the oversmoothing issue but also significantly enhances the models' prediction and interpretability performance. Moreover, the effectiveness of ORCDF is validated in the downstream task of computerized adaptive testing.

Yu-Peng Wu, Hong Qian, Rong-Jun Qin et al.

In the field of security, multi-objective security games (MOSGs) allow defenders to simultaneously protect targets from multiple heterogeneous attackers. MOSGs aim to simultaneously maximize all the heterogeneous payoffs, e.g., life, money, and crime rate, without merging heterogeneous attackers. In real-world scenarios, the number of heterogeneous attackers and targets to be protected may exceed the capability of most existing state-of-the-art methods, i.e., MOSGs are limited by the issue of scalability. To this end, this paper proposes a general framework called SDES based on many-objective evolutionary search to scale up MOSGs to large-scale targets and heterogeneous attackers. SDES consists of four consecutive key components, i.e., discretization, optimization, evaluation, and refinement. Specifically, SDES first discretizes the originally high-dimensional continuous solution space to the low-dimensional discrete one by the maximal indifference property in game theory. This property helps evolutionary algorithms (EAs) bypass the high-dimensional step function and ensure a well-convergent Pareto front. Then, a many-objective EA is used for optimization in the low-dimensional discrete solution space to obtain a well-spaced Pareto front. To evaluate solutions, SDES restores solutions back to the original space via greedily optimizing a novel divergence measurement. Finally, the refinement in SDES boosts the optimization performance with acceptable cost. Theoretically, we prove the optimization consistency and convergence of SDES. Experiment results show that SDES is the first linear-time MOSG algorithm for both large-scale attackers and targets. SDES is able to solve up to 20 attackers and 100 targets MOSG problems, while the state-of-the-art (SOTA) methods can only solve up to 8 attackers and 25 targets ones. Ablation study verifies the necessity of all components in SDES.

Tianxiang Sun, Yunfan Shao, Hong Qian et al.

Extremely large pre-trained language models (PTMs) such as GPT-3 are usually released as a service. It allows users to design task-specific prompts to query the PTMs through some black-box APIs. In such a scenario, which we call Language-Model-as-a-Service (LMaaS), the gradients of PTMs are usually unavailable. Can we optimize the task prompts by only accessing the model inference APIs? This paper proposes the black-box tuning framework to optimize the continuous prompt prepended to the input text via derivative-free optimization. Instead of optimizing in the original high-dimensional prompt space, which is intractable for traditional derivative-free optimization, we perform optimization in a randomly generated subspace due to the low intrinsic dimensionality of large PTMs. The experimental results show that the black-box tuning with RoBERTa on a few labeled samples not only significantly outperforms manual prompt and GPT-3's in-context learning, but also surpasses the gradient-based counterparts, i.e., prompt tuning and full model tuning.

Hong Qian, Yang Yu

Reinforcement learning is about learning agent models that make the best sequential decisions in unknown environments. In an unknown environment, the agent needs to explore the environment while exploiting the collected information, which usually forms a sophisticated problem to solve. Derivative-free optimization, meanwhile, is capable of solving sophisticated problems. It commonly uses a sampling-and-updating framework to iteratively improve the solution, where exploration and exploitation are also needed to be well balanced. Therefore, derivative-free optimization deals with a similar core issue as reinforcement learning, and has been introduced in reinforcement learning approaches, under the names of learning classifier systems and neuroevolution/evolutionary reinforcement learning. Although such methods have been developed for decades, recently, derivative-free reinforcement learning exhibits attracting increasing attention. However, recent survey on this topic is still lacking. In this article, we summarize methods of derivative-free reinforcement learning to date, and organize the methods in aspects including parameter updating, model selection, exploration, and parallel/distributed methods. Moreover, we discuss some current limitations and possible future directions, hoping that this article could bring more attentions to this topic and serve as a catalyst for developing novel and efficient approaches.

Yu-Ren Liu, Yi-Qi Hu, Hong Qian et al.

Recent advances in derivative-free optimization allow efficient approximation of the global-optimal solutions of sophisticated functions, such as functions with many local optima, non-differentiable and non-continuous functions. This article describes the ZOOpt (Zeroth Order Optimization) toolbox that provides efficient derivative-free solvers and is designed easy to use. ZOOpt provides single-machine parallel optimization on the basis of python core and multi-machine distributed optimization for time-consuming tasks by incorporating with the Ray framework -- a famous platform for building distributed applications. ZOOpt particularly focuses on optimization problems in machine learning, addressing high-dimensional and noisy problems such as hyper-parameter tuning and direct policy search. The toolbox is maintained toward a ready-to-use tool in real-world machine learning tasks.

Felix X. -F. Ye, Yi-an Ma, Hong Qian

Inference in hidden Markov model has been challenging in terms of scalability due to dependencies in the observation data. In this paper, we utilize the inherent memory decay in hidden Markov models, such that the forward and backward probabilities can be carried out with subsequences, enabling efficient inference over long sequences of observations. We formulate this forward filtering process in the setting of the random dynamical system and there exist Lyapunov exponents in the i.i.d random matrices production. And the rate of the memory decay is known as $λ_2-λ_1$, the gap of the top two Lyapunov exponents almost surely. An efficient and accurate algorithm is proposed to numerically estimate the gap after the soft-max parametrization. The length of subsequences $B$ given the controlled error $ε$ is $B=\log(ε)/(λ_2-λ_1)$. We theoretically prove the validity of the algorithm and demonstrate the effectiveness with numerical examples. The method developed here can be applied to widely used algorithms, such as mini-batch stochastic gradient method. Moreover, the continuity of Lyapunov spectrum ensures the estimated $B$ could be reused for the nearby parameter during the inference.

Yang Yu, Hong Qian

Evolutionary algorithms (EAs), a large class of general purpose optimization algorithms inspired from the natural phenomena, are widely used in various industrial optimizations and often show excellent performance. This paper presents an attempt towards revealing their general power from a statistical view of EAs. By summarizing a large range of EAs into the sampling-and-learning framework, we show that the framework directly admits a general analysis on the probable-absolute-approximate (PAA) query complexity. We particularly focus on the framework with the learning subroutine being restricted as a binary classification, which results in the sampling-and-classification (SAC) algorithms. With the help of the learning theory, we obtain a general upper bound on the PAA query complexity of SAC algorithms. We further compare SAC algorithms with the uniform search in different situations. Under the error-target independence condition, we show that SAC algorithms can achieve polynomial speedup to the uniform search, but not super-polynomial speedup. Under the one-side-error condition, we show that super-polynomial speedup can be achieved. This work only touches the surface of the framework. Its power under other conditions is still open.