Influence maximization (IM) aims to select a small set of seed nodes whose activation triggers a maximal cascade. Existing methods typically assume access to the network topology or a reliable surrogate, which is often unavailable in practice due to noisy, privacy-protected, or partially observed links. These settings pose two challenges: (1) the lack of explicit topology removes a key inductive constraint for diffusion modeling, undermining influence estimation, and (2) nonlinear, temporally dependent node interactions yield complex multivariate time series that hinder topology inference. We propose DynaFLUX, an end-to-end generative framework for IM under hidden topology. DynaFLUX learns a compact surrogate of latent dynamics directly from observed time series, and jointly optimizes a seed-selection policy via reinforcement learning. A self-attention pointer network captures long-range dependencies for seed generation, while an influence-prediction module infers a surrogate topology and uses Monte Carlo diffusion to provide policy-gradient rewards. Experiments show that DynaFLUX accurately identifies influential spreaders and consistently outperforms state-of-the-art baselines in unseen topology scenarios.

Fourier Neural Operators (FNO) have emerged as promising solutions for efficiently solving partial differential equations (PDEs) by learning infinite-dimensional function mappings through frequency domain transformations. However, the sparsity of high-frequency signals limits computational efficiency for high-dimensional inputs, and fixed-pattern truncation often causes high-frequency signal loss, reducing performance in scenarios such as high-resolution inputs or long-term predictions. To address these challenges, we propose FreqMoE, an efficient and progressive training framework that exploits the dependency of high-frequency signals on low-frequency components. The model first learns low-frequency weights and then applies a sparse upward-cycling strategy to construct a mixture of experts (MoE) in the frequency domain, effectively extending the learned weights to high-frequency regions. Experiments on both regular and irregular grid PDEs demonstrate that FreqMoE achieves up to 16.6 percent accuracy improvement while using merely 2.1 percent parameters (47.32x reduction) compared to dense FNO. Furthermore, the approach demonstrates remarkable stability in long-term predictions and generalizes seamlessly to various FNO variants and grid structures, establishing a new Low frequency Pretraining, High frequency Fine-tuning'' paradigm for solving PDEs.

Designing accurate reward functions for reinforcement learning (RL) has long been challenging. Preference-based RL (PbRL) offers a promising approach by using human preferences to train agents, eliminating the need for manual reward design. While successful in single-agent tasks, extending PbRL to complex multi-agent scenarios is nontrivial. Existing PbRL methods lack the capacity to comprehensively capture both temporal and cooperative aspects, leading to inadequate reward functions. This work introduces an advanced multi-agent preference learning framework that effectively addresses these limitations. Based on a cascading Transformer architecture, our approach captures both temporal and cooperative dependencies, alleviating issues related to reward uniformity and intricate interactions among agents. Experimental results demonstrate substantial performance improvements in multi-agent cooperative tasks, and the reconstructed reward function closely resembles expert-defined reward functions. The source code is available at https://github.com/catezi/MAPT.

Safe reinforcement learning (RL) requires the agent to finish a given task while obeying specific constraints. Giving constraints in natural language form has great potential for practical scenarios due to its flexible transfer capability and accessibility. Previous safe RL methods with natural language constraints typically need to design cost functions manually for each constraint, which requires domain expertise and lacks flexibility. In this paper, we harness the dual role of text in this task, using it not only to provide constraint but also as a training signal. We introduce the Trajectory-level Textual Constraints Translator (TTCT) to replace the manually designed cost function. Our empirical results demonstrate that TTCT effectively comprehends textual constraint and trajectory, and the policies trained by TTCT can achieve a lower violation rate than the standard cost function. Extra studies are conducted to demonstrate that the TTCT has zero-shot transfer capability to adapt to constraint-shift environments.

Chunyang Jiang, Tianchen Zhu, Haoyi Zhou, Chang Liu, Ting Deng, Chunming Hu, Jianxin Li. Proceedings of the 17th Conference of the European Chapter of the Association for Computational Linguistics. 2023.

Recently, Decision Transformer (DT) pioneered the offline RL into a contextual conditional sequence modeling paradigm, which leverages self-attended autoregression to learn from global target rewards, states, and actions. However, many applications have a severe delay of the above signals, such as the agent can only obtain a reward signal at the end of each trajectory. This delay causes an unwanted bias cumulating in autoregressive learning global signals. In this paper, we focused its virtual example on episodic reinforcement learning with trajectory feedback. We propose a new reward redistribution algorithm for learning parameterized reward functions, and it decomposes the long-delayed reward onto each timestep. To improve the redistributing's adaptation ability, we formulate the previous decomposition as a bi-level optimization problem for global optimal. We extensively evaluate the proposed method on various benchmarks and demonstrate an overwhelming performance improvement under long-delayed settings.

The AI inspired methods have entirely changed the network QoS landscape and brought better demand-guided experiences for the end-users. However, the increasing demands of satisfactory experiences require larger AI models, whose inference efficiency becomes the non-negligible drawback in the time-sensitive network QoS. In this work, we defined this challenge as the inference-QoS (iQoS) problem of the network QoS itself, which balances inference efficiency and performance for AI services. We design a unified iQoS metric to evaluate the AI-enhanced QoS frameworks with considerations on model performance, inference latency, and input scale. Then, we propose a two-stage pipeline as the exemplar for leveraging the iQoS metric in QoS-aware AI services: (i) enhance reconstruction ability, pretraining masked autoencoder extracts intrinsic data correlations by multi-scale masking; (ii) improve inference efficiency, forecasting masked decoder uses the data scale pruning in terms of spatial and temporal dimension for prediction. Comprehensive experiments on our method demonstrate its superior inference latency and overwhelming traffic matrix prediction performance.

Ranked list truncation aims to cut the ranked results in short considering user-defined objectives, which balances the overall utility and user efforts over retrieval results. The exact selection of an optimal cut-off position brings potential benefits in various real-world applications, such as patent search and legal search. However, there is significant retrieval bias in the ranked list. The result scores and the disorder of document sequences cause difficulties in judging the relevance between the queries and documents -- alleviating the existing methods' performance improvement. In this work, we investigate the characteristics of retrieval bias on altering truncation and propose a multi-task truncation model, MtCut. It employs two auxiliary tasks to make complementary for the retrieval bias. As a practical evaluation, we explore its performance on two datasets, and the results show that MtCut outperforms the state-of-the-art methods on both F1-score and DCG metrics.

Relevance measure in both homogeneous and heterogeneous networks has been extensively studied. However, how to measure the relevance among different-typed objects in weighted signed heterogeneous information networks remains an open problem. It is challenging to incorporate both positive and negative multi-typed relationships simultaneously in signed heterogeneous networks due to the opposite opinions implied by them. To this end, this paper proposes a random walk based approach for relevance measure by utilizing and modeling the rich semantic information in weighted signed heterogeneous networks. Particularly, we first transform a signed network into a non-signed network according to the different semantic meanings represented by positive and negative relationships. This paves the way to properly utilize negative relationships. Next, we conduct random walk from the source object to the target object based on a bunch of single meta-paths separately. Finally, we combine multiple meta-paths together to obtain a more comprehensive relatedness between the source object and the target object. Extensive experiments on real datasets demonstrate the superior performance of the proposed approach.

How to model the influence propagation accurately in social network is a critical and challenge task. Although numerous attempts have been made for this topic, few of them consider the user’s negative influence. Positive influence will encourage people to perform some action while the negative one will degrade the probability. Thus, it is meaningful to model the influence propagation by considering both the positive and negative influence. What’s more, previous research is mostly based on the assumption that the influence probabilities between users are known, however, they are typically unknown in real-world social networks. To address these problems, a novel Multipolar Factors aware Independent Cascade model (MFIC) is proposed to outline the information diffusion in social network. Then, the user-to-user influence probability is learnt with the users’ behavior logs based on the EM algorithm. We also apply the discovered influence probabilities to user behavior prediction. Experiments are conducted over real data sets, Flixster and Digg, validating the effectiveness of our methods.