Membership Inference Attack (MIA) aims to determine whether a specific data sample was included in the training dataset of a target model. Traditional MIA approaches rely on shadow models to mimic target model behavior, but their effectiveness diminishes for Large Language Model (LLM)- based recommendation systems due to the scale and complexity of training data. This paper introduces a novel knowledge distillation-based MIA paradigm tailored for LLM-based recommendation systems. Our method constructs a reference model via distillation, applying distinct strategies for member and non-member data to enhance discriminative capabilities. The paradigm extracts fused features (e.g., confidence, entropy, loss, and hidden layer vectors) from the reference model to train an attack model, overcoming limitations of individual features. Extensive experiments on extended datasets (Last.FM, MovieLens, Book-Crossing, Delicious) and diverse LLMs (T5, GPT -2, LLaMA3) demonstrate that our approach significantly outperforms shadow model-based MIAs and individual-feature baselines. The results show its practicality for privacy attacks in LLM-driven recommender systems.

Large language models (LLMs) are increasingly used to simulate humans, with applications ranging from survey prediction to decision-making. However, are LLMs strictly necessary, or can smaller, domain-grounded models suffice? We identify a large class of simulation problems in which individuals make choices among discrete options, where a graph neural network (GNN) can match or surpass strong LLM baselines despite being three orders of magnitude smaller. We introduce Graph-basEd Models for human Simulation (GEMS), which casts discrete choice simulation tasks as a link prediction problem on graphs, leveraging relational knowledge while incorporating language representations only when needed. Evaluations across three key settings on three simulation datasets show that GEMS achieves comparable or better accuracy than LLMs, with far greater efficiency, interpretability, and transparency, highlighting the promise of graph-based modeling as a lightweight alternative to LLMs for human simulation. Our code is available at https://github.com/schang-lab/gems.

This paper presents a novel technique for incorporating user input when learning and inferring In high stakes decision settings such as credit scoring, processing user preferences. When trying to provide users bail applications, or making hiring decisions, applicants of black-box machine learning models with actionable often seek recourse to correct unfavourable predicted recourse, we often wish to incorporate outcomes for the future. In these scenarios, since there their personal preferences about the ease of modifying can be multiple possible recourses for each individual, feasibility each individual feature. These recourse considerations, user preferences, and heuristics to finding algorithms usually require an exhaustive minimize the size of the proposed modifications are used to set of tuples associating each feature to its cost guide the search for appropriate recourses (Poyiadzi et al., of modification. Since it is hard to obtain such 2020; Pawelczyk et al., 2020; Joshi et al., 2019). Recourse costs by directly surveying humans, in this paper, search algorithms thus return the best possible recourse we propose the use of the Bradley-Terry model based on these considerations by performing a search over to automatically infer feature-wise costs using the feature-space of the model.

Most of these data are multivariate, with multiple values at each time step (Wilms, Rombouts, & Croux, 2021; Lee, Kim & Sim, 2024). Consequently, utilizing multivariate time series data for knowledge extraction and application to societal issues is becoming increasingly prevalent, making multivariate time series prediction a challenging task widely regarded across most industries (Bidarkota, 1998). The traditional approach to addressing multivariate time series prediction problems involves using statistical methods, such as vector autoregression and autoregressive distributed lag (ARDL) models (Qu, Huang, She, Liad, & Lai, 2024). However, statistical methods may struggle to capture complex sequence patterns in the data because of irregularities and nonlinearities among the features (Salinas, Flunkert, Gasthaus, & Januschowski, 2020). Therefore, layer-based deep-learning models incorporating recurrent layers (Rumelhart, Hinton, & Williams, 1986), long short-term memory layers (Hochreiter & Schmidhuber, 1997), gated recurrent units (Chung, Gulcehre, Cho & Bengio, 2014), and attention mechanisms (Vaswani, Shazeer, Parmar, Uszkoreit, Jones, Gomez, & Polosukhin, 2017) have been widely explored in multivariate time series prediction (Catania, Grassi, & Ravazzolo, 2019). Deep learning-based models effectively learn sequential patterns in time series data and can outperform traditional statistical models, demonstrating superior prediction performance (Ortega, Otero, Solomon, Otero, & Fabregas, 2023). Another approach for improving the accuracy of multivariate time series prediction is to utilize models based on transformers, such as informers (Zhou, Zhang, Peng, Zhang, Li, Xiong, & Zhang, 2021) and autoformers (Wu, Xu, Wang, & Long, 2021). Transformer-based models effectively capture long-and short-term patterns in multivariate time series data and have surpassed traditional approaches in terms of prediction performance (Costa & Machado, 2023).

Modern classification tasks usually involve many class labels and can be informed by a broad range of features. Many of these tasks are tackled by constructing a set of classifiers, which are then applied at test time and then pieced together in a fixed procedure determined in advance or at training time. We present an active classification process at the test time, where each classifier in a large ensemble is viewed as a potential observation that might inform our classification process. Observations are then selected dynamically based on previous observations, using a value-theoretic computation that balances an estimate of the expected classification gain from each observation as well as its computational cost. The expected classification gain is computed using a probabilistic model that uses the outcome from previous observations. This active classification process is applied at test time for each individual test instance, resulting in an efficient instance-specific decision path. We demonstrate the benefit of the active scheme on various real-world datasets, and show that it can achieve comparable or even higher classification accuracy at a fraction of the computational costs of traditional methods.

While long term human visual memory can store a remarkable amount of visual information, it tends to degrade over time. Recent works have shown that image memorability is an intrinsic property of an image that can be reliably estimated using state-of-the-art image features and machine learning algorithms. However, the class of features and image information that is forgotten has not been explored yet. In this work, we propose a probabilistic framework that models how and which local regions from an image may be forgotten using a data-driven approach that combines local and global images features. The model automatically discovers memorability maps of individual images without any human annotation. We incorporate multiple image region attributes in our algorithm, leading to improved memorability prediction of images as compared to previous works.

This paper explores privacy-compliant group-level emotion recognition ''in-the-wild'' within the EmotiW Challenge 2023. Group-level emotion recognition can be useful in many fields including social robotics, conversational agents, e-coaching and learning analytics. This research imposes itself using only global features avoiding individual ones, i.e. all features that can be used to identify or track people in videos (facial landmarks, body poses, audio diarization, etc.). The proposed multimodal model is composed of a video and an audio branches with a cross-attention between modalities. The video branch is based on a fine-tuned ViT architecture. The audio branch extracts Mel-spectrograms and feed them through CNN blocks into a transformer encoder. Our training paradigm includes a generated synthetic dataset to increase the sensitivity of our model on facial expression within the image in a data-driven way. The extensive experiments show the significance of our methodology. Our privacy-compliant proposal performs fairly on the EmotiW challenge, with 79.24% and 75.13% of accuracy respectively on validation and test set for the best models. Noticeably, our findings highlight that it is possible to reach this accuracy level with privacy-compliant features using only 5 frames uniformly distributed on the video.

Odor sensory evaluation has a broad application in food, clothing, cosmetics, and other fields. Traditional artificial sensory evaluation has poor repeatability, and the machine olfaction represented by the electronic nose (E-nose) is difficult to reflect human feelings. Olfactory electroencephalogram (EEG) contains odor and individual features associated with human olfactory preference, which has unique advantages in odor sensory evaluation. However, the difficulty of cross-subject olfactory EEG recognition greatly limits its application. It is worth noting that E-nose and olfactory EEG are more advantageous in representing odor information and individual emotions, respectively. In this paper, an E-nose and olfactory EEG multimodal learning method is proposed for cross-subject olfactory preference recognition. Firstly, the olfactory EEG and E-nose multimodal data acquisition and preprocessing paradigms are established. Secondly, a complementary multimodal data mining strategy is proposed to effectively mine the common features of multimodal data representing odor information and the individual features in olfactory EEG representing individual emotional information. Finally, the cross-subject olfactory preference recognition is achieved in 24 subjects by fusing the extracted common and individual features, and the recognition effect is superior to the state-of-the-art recognition methods. Furthermore, the advantages of the proposed method in cross-subject olfactory preference recognition indicate its potential for practical odor evaluation applications.

Early warning systems (EWS) are predictive tools at the center of recent efforts to improve graduation rates in public schools across the United States. These systems assist in targeting interventions to individual students by predicting which students are at risk of dropping out. Despite significant investments in their widespread adoption, there remain large gaps in our understanding of the efficacy of EWS, and the role of statistical risk scores in education. In this work, we draw on nearly a decade's worth of data from a system used throughout Wisconsin to provide the first large-scale evaluation of the long-term impact of EWS on graduation outcomes. We present empirical evidence that the prediction system accurately sorts students by their dropout risk. We also find that it may have caused a single-digit percentage increase in graduation rates, though our empirical analyses cannot reliably rule out that there has been no positive treatment effect. Going beyond a retrospective evaluation of DEWS, we draw attention to a central question at the heart of the use of EWS: Are individual risk scores necessary for effectively targeting interventions? We propose a simple mechanism that only uses information about students' environments -- such as their schools, and districts -- and argue that this mechanism can target interventions just as efficiently as the individual risk score-based mechanism. Our argument holds even if individual predictions are highly accurate and effective interventions exist. In addition to motivating this simple targeting mechanism, our work provides a novel empirical backbone for the robust qualitative understanding among education researchers that dropout is structurally determined. Combined, our insights call into question the marginal value of individual predictions in settings where outcomes are driven by high levels of inequality.

Financial data are often available in the form of time series. These time series are often highly dimensional with complex relationships between them. The complexity of financial data can be demonstrated in different aspects. Firstly, training data are often limited and the number of features that researchers can create is often much greater than the number of observations. In some research, such as [1], the ratio of the number of features over the number of observations, defined as model complexity can increase up to hundreds for financial instruments with a limited amount of history. Traditional setups in machine learning are not well-equipped for these data-scarce environments.