Sayaka Kamei

In question answering (QA) for multi-constraint recommendation, the model must find every item that satisfies a request with several requirements. Still, training data that pair natural-language questions with complete answer sets are scarce. Such data can be synthesized by computing answers from an item catalog and using users’ ratings and reviews to select requests, yet the result may reveal whose evidence was used. We develop a QA data synthesis framework that protects these users using user-level differential privacy (DP), bounding each user’s total contribution and adding calibrated noise to the support statistics used to weight requests. Using one construction template, we build QA datasets for Movie, Beauty, and Recipe from pre-provided, rule-cleaned, and model-inferred attributes. In ablations without noise, an adversary who knows all other users’ data identifies, without false positives, every tested member whose evidence supports a request, up to 96% of members. Under DP with privacy budget ε=4, it flags at most 3.0% of members of these three datasets at a 1% false-positive rate, and an audit with repeated mechanism runs finds no evidence of privacy loss above ε. Models trained on private data retain at least 97% of the non-private ablation’s macro-averaged F1 on shared test questions.

Question-answering recipe recommendation tasks lack datasets with ground-truth labels. Existing methods often generate datasets from simple combinations of ingredient or tag constraints, leading to unnatural expressions and unreasonable constraints that are hard to reflect users’ real preferences. This paper proposes a construction method for a benchmark-style QA dataset for natural-language recipe recommendation. Driven by real user behavior, our method integrates external user query and review data to extract fine-grained preference signals by LLMs and maps them onto a knowledge-graphbased tag schema, thereby constructing QA data consisting of preference and ingredient constraints. Besides, a greedy strategy for constraint selection is also used to control the answer size, while tagbased re-ranking is applied to improve data quality. The generated dataset RecipeADQA contains natural-language questions, structured constraints, and answer sets, resulting in 128,465 instances. Experiments compare RecipeADQA with baseline datasets from two perspectives: data quality and retrieval-recommendation performance. The results show that ours outperforms existing methods on the same recipe knowledge graph in coverage, higher question quality in naturalness and constraint rationality, and better queryability. Moreover, we design a noise-augmented retrieve-and-rerank model, in which a lightweight parser first retrieves candidate recipes, and a small language model then selects and ranks relevant recipes from a noisy candidate pool. The model trained on RecipeADQA outperforms the same model trained on the baseline datasets. The relevant construction code and data have been open-sourced at a GitHub repository https://github.com/MorimoLab/RecipeADQA. Note: The paper has been accepted by "The 22nd International Conference on Advanced Data Mining and Applications 2026 (ADMA 2026)".

In a network , a set of processes is a total dominating set if and only if every process is neighboring to some member of . We introduce the dynamic total domination problem , a novel synchronization challenge that requires sustaining a total dominating set in a network over time. Unlike static approaches, this problem ensures that every process always has at least one neighbor in , while processes alternate between entering and exiting . This problem has practical applications, notably in environmental monitoring IoT systems powered by rechargeable batteries, where continuous sensing coverage is essential. In this paper, we propose two self‐stabilizing distributed algorithms for the dynamic total domination problem under a weakly fair distributed scheduler. The first algorithm utilizes unbounded timestamps, while the second employs bounded timestamps. Both algorithms guarantee convergence in rounds and ensure safety and liveness without centralized control. In the synchronized model (a special case of distributed scheduler), the waiting times of both algorithms are rounds.

Self-stabilization is a versatile methodology in the design of fault-tolerant distributed algorithms for transient faults. A self-stabilizing system automatically recovers from any kind and any finite number of transient faults. This property is specifically useful in modern distributed systems with a large number of components. In this paper, we propose a new communication and execution model named the R(1)W(1) model in which each process can read and write its own and neighbors' local variables in a single step. We propose self-stabilizing distributed algorithms in the R(1)W(1) model for the problems of maximal matching, minimal k-dominating set and maximal k-dependent set. Finally, we propose an example transformer, based on randomized distance-two local mutual exclusion, to simulate algorithms designed for the R(1)W(1) model in the synchronous message passing model with synchronized clocks.

Deep generative models, such as generative adversarial networks (GANs), have been employed for de~novo molecular generation in drug discovery. Most prior studies have utilized reinforcement learning (RL) algorithms, particularly Monte Carlo tree search (MCTS), to handle the discrete nature of molecular representations in GANs. However, due to the inherent instability in training GANs and RL models, along with the high computational cost associated with MCTS sampling, MCTS RL-based GANs struggle to scale to large chemical databases. To tackle these challenges, this study introduces a novel GAN based on actor-critic RL with instant and global rewards, called InstGAN, to generate molecules at the token-level with multi-property optimization. Furthermore, maximized information entropy is leveraged to alleviate the mode collapse. The experimental results demonstrate that InstGAN outperforms other baselines, achieves comparable performance to state-of-the-art models, and efficiently generates molecules with multi-property optimization. The code is available at: https://github.com/tang777777/InstGAN.