Figure 1: LayerFlow supports the analysis of contextual word embedding properties. T o increase the awareness of the potential uncertainty within the transformation, representation, and interpretation steps of the used processing pipeline, we utilize multiple visual components such as cluster convex-hulls, pairwise distances, cluster summaries, projection quality metrics, and connections of k-nearest neighbors.Abstract Large language models (LLMs) represent words through contextual word embeddings encoding different language properties like semantics and syntax. Understanding these properties is crucial, especially for researchers investigating language model capabilities, employing embeddings for tasks related to text similarity, or evaluating the reasons behind token importance as measured through attribution methods. Applications for embedding exploration frequently involve dimensionality reduction techniques, which reduce high-dimensional vectors to two dimensions used as coordinates in a scatterplot. This data transformation step introduces uncertainty that can be propagated to the visual representation and influence users' interpretation of the data. T o communicate such uncertainties, we present LayerFlow - a visual analytics workspace that displays embeddings in an interlinked projection design and communicates the transformation, representation, and interpretation uncertainty. In particular, to hint at potential data distortions and uncertainties, the workspace includes several visual components, such as convex hulls showing 2D and HD clusters, data point pairwise distances, cluster summaries, and projection quality metrics. W e show the usability of the presented workspace through replication and expert case studies that highlight the need to communicate uncertainty through multiple visual components and different data perspectives. CCS Concepts Human-centered computing Visual analytics; Mathematics of computing Dimensionality reduction;1 Introduction In recent years, a large number of deep-learning-based language models (e.g., BERT [DCL T19]) have emerged, demonstrating remarkable performance in natural language processing (NLP) and understanding tasks. These models learn from large text datasets, acquiring language structures in an unsupervised manner. Thereby, they produce contextual word embeddings, representing words through vectors encoding different language properties. Extensive research has been conducted to understand the linguistic properties embedded in these vectors. For instance, research indicates that BERT's middle layers capture syntactic features like dependency trees while early layers encode lexical features [RKR20]. Analyzing these properties helps researchers better understand how language models process data and aids in developing models that generalize well, reducing biases and improving inclusivity.

Understanding how residue variations affect protein stability is crucial for designing functional proteins and deciphering the molecular mechanisms underlying disease-related mutations. Recent advances in protein language models (PLMs) have revolutionized computational protein analysis, enabling, among other things, more accurate predictions of mutational effects. In this work, we introduce JanusDDG, a deep learning framework that leverages PLM-derived embeddings and a bidirectional cross-attention transformer architecture to predict $ΔΔG$ of single and multiple-residue mutations while simultaneously being constrained to respect fundamental thermodynamic properties, such as antisymmetry and transitivity. Unlike conventional self-attention, JanusDDG computes queries (Q) and values (V) as the difference between wild-type and mutant embeddings, while keys (K) alternate between the two. This cross-interleaved attention mechanism enables the model to capture mutation-induced perturbations while preserving essential contextual information. Experimental results show that JanusDDG achieves state-of-the-art performance in predicting $ΔΔG$ from sequence alone, matching or exceeding the accuracy of structure-based methods for both single and multiple mutations. Code Availability:https://github.com/compbiomed-unito/JanusDDG

Automated Machine Learning (AutoML) automatically builds machine learning (ML) models on data. The de facto standard for evaluating new AutoML frameworks for tabular data is the AutoML Benchmark (AMLB). AMLB proposed to evaluate AutoML frameworks using 1-and 4-hour time budgets across 104 tasks. We argue that shorter time constraints should be considered for the benchmark because of their practical value, such as when models need to be retrained with high frequency, and to make AMLB more accessible. This work considers two ways in which to reduce the overall computation used in the benchmark: smaller time constraints and the use of early stopping. We conduct evaluations of 11 AutoML frameworks on 104 tasks with different time constraints and find the relative ranking of AutoML frameworks is fairly consistent across time constraints, but that using early-stopping leads to a greater variety in model performance. In Machine Learning (ML), manually creating good models is time-consuming and knowledge-intensive. Automated Machine Learning (AutoML) employs efficient automated search methods to create models for new data, often reducing the computational costs in the process Hutter et al. (2019); Hollmann et al. (2022). The AutoML Benchmark (AMLB, Gijsbers et al. 2024) has become the standard for the evaluation of AutoML frameworks on tabular data, greatly increasing reproducibility and comparability in AutoML research. We identified that the time budgets proposed by Gijsbers et al. (2024) were based on what seemed "practically reasonable" at the time, as signified by many frameworks' default time budget of one hour. While the authors motivate evaluating methods on two time budgets as a proxy for anytime performance, they do not motivate the particular choice of 1 hour and 4 hours. AutoML frameworks behave under different time constraints. We conduct similar experiments and analyses for frameworks with early-stopping, offering insights into its potential to reduce energy consumption in AutoML systems. However, we often see that the original benchmarking suite or time constraints (1 hour and 4 hour) are not used as proposed.

Bipartite ranking is a fundamental supervised learning problem, with the goal of learning a ranking over instances with maximal area under the ROC curve (AUC) against a single binary target label. However, one may often observe multiple binary target labels, e.g., from distinct human annotators. How can one synthesize such labels into a single coherent ranking? In this work, we formally analyze two approaches to this problem -- loss aggregation and label aggregation -- by characterizing their Bayes-optimal solutions. Based on this, we show that while both methods can yield Pareto-optimal solutions, loss aggregation can exhibit label dictatorship: one can inadvertently (and undesirably) favor one label over others. This suggests that label aggregation can be preferable to loss aggregation, which we empirically verify.

Continuous generation of streaming data from diverse sources, such as online transactions and digital interactions, necessitates timely fraud detection. Traditional batch processing methods often struggle to capture the rapidly evolving patterns of fraudulent activities. This paper highlights the critical importance of processing streaming data for effective fraud detection. To address the inherent challenges of latency, scalability, and concept drift in streaming environments, we propose a robust online streaming fraud detection (ROSFD) framework. Our proposed framework comprises two key stages: (i) Stage One: Offline Model Initialization. In this initial stage, a model is built in offline settings using incremental learning principles to overcome the "cold-start" problem. (ii) Stage Two: Real-time Model Adaptation. In this dynamic stage, drift detection algorithms (viz.,, DDM, EDDM, and ADWIN) are employed to identify concept drift in the incoming data stream and incrementally train the model accordingly. This "train-only-when-required" strategy drastically reduces the number of retrains needed without significantly impacting the area under the receiver operating characteristic curve (AUC). Overall, ROSFD utilizing ADWIN as the drift detection method demonstrated the best performance among the employed methods. In terms of model efficacy, Adaptive Random Forest consistently outperformed other models, achieving the highest AUC in four out of five datasets.

Federated Graph Learning (FGL) enables privacy-preserving, distributed training of graph neural networks without sharing raw data. Among its approaches, subgraph-FL has become the dominant paradigm, with most work focused on improving overall node classification accuracy. However, these methods often overlook fairness due to the complexity of node features, labels, and graph structures. In particular, they perform poorly on nodes with disadvantaged properties, such as being in the minority class within subgraphs or having heterophilous connections (neighbors with dissimilar labels or misleading features). This reveals a critical issue: high accuracy can mask degraded performance on structurally or semantically marginalized nodes. To address this, we advocate for two fairness goals: (1) improving representation of minority class nodes for class-wise fairness and (2) mitigating topological bias from heterophilous connections for topology-aware fairness. We propose FairFGL, a novel framework that enhances fairness through fine-grained graph mining and collaborative learning. On the client side, the History-Preserving Module prevents overfitting to dominant local classes, while the Majority Alignment Module refines representations of heterophilous majority-class nodes. The Gradient Modification Module transfers minority-class knowledge from structurally favorable clients to improve fairness. On the server side, FairFGL uploads only the most influenced subset of parameters to reduce communication costs and better reflect local distributions. A cluster-based aggregation strategy reconciles conflicting updates and curbs global majority dominance . Extensive evaluations on eight benchmarks show FairFGL significantly improves minority-group performance , achieving up to a 22.62 percent Macro-F1 gain while enhancing convergence over state-of-the-art baselines.

Sentiment analysis is a crucial task in natural language processing (NLP) that enables the extraction of meaningful insights from textual data, particularly from dynamic platforms like Twitter and IMDB. This study explores a hybrid framework combining transformer-based models, specifically BERT, GPT-2, RoBERTa, XLNet, and DistilBERT, to improve sentiment classification accuracy and robustness. The framework addresses challenges such as noisy data, contextual ambiguity, and generalization across diverse datasets by leveraging the unique strengths of these models. BERT captures bidirectional context, GPT-2 enhances generative capabilities, RoBERTa optimizes contextual understanding with larger corpora and dynamic masking, XLNet models dependency through permutation-based learning, and DistilBERT offers efficiency with reduced computational overhead while maintaining high accuracy. We demonstrate text cleaning, tokenization, and feature extraction using Term Frequency Inverse Document Frequency (TF-IDF) and Bag of Words (BoW), ensure high-quality input data for the models. The hybrid approach was evaluated on benchmark datasets Sentiment140 and IMDB, achieving superior accuracy rates of 94\% and 95\%, respectively, outperforming standalone models. The results validate the effectiveness of combining multiple transformer models in ensemble-like setups to address the limitations of individual architectures. This research highlights its applicability to real-world tasks such as social media monitoring, customer sentiment analysis, and public opinion tracking which offers a pathway for future advancements in hybrid NLP frameworks.

Peer review at AI conferences is stressed by rapidly rising submission volumes, leading to deteriorating review quality and increased author dissatisfaction. To address these issues, we developed Review Feedback Agent, a system leveraging multiple large language models (LLMs) to improve review clarity and actionability by providing automated feedback on vague comments, content misunderstandings, and unprofessional remarks to reviewers. Implemented at ICLR 2025 as a large randomized control study, our system provided optional feedback to more than 20,000 randomly selected reviews. To ensure high-quality feedback for reviewers at this scale, we also developed a suite of automated reliability tests powered by LLMs that acted as guardrails to ensure feedback quality, with feedback only being sent to reviewers if it passed all the tests. The results show that 27% of reviewers who received feedback updated their reviews, and over 12,000 feedback suggestions from the agent were incorporated by those reviewers. This suggests that many reviewers found the AI-generated feedback sufficiently helpful to merit updating their reviews. Incorporating AI feedback led to significantly longer reviews (an average increase of 80 words among those who updated after receiving feedback) and more informative reviews, as evaluated by blinded researchers. Moreover, reviewers who were selected to receive AI feedback were also more engaged during paper rebuttals, as seen in longer author-reviewer discussions. This work demonstrates that carefully designed LLM-generated review feedback can enhance peer review quality by making reviews more specific and actionable while increasing engagement between reviewers and authors. The Review Feedback Agent is publicly available at https://github.com/zou-group/review_feedback_agent.

Urban datasets such as citizen transportation modes often contain disproportionately distributed classes, posing significant challenges to the classification of under-represented samples using data-driven models. In the literature, various resampling methods have been developed to create synthetic data for minority classes (oversampling) or remove samples from majority classes (undersampling) to alleviate class imbalance. However, oversampling approaches tend to overgeneralize minor classes that are closely clustered and neglect sparse regions which may contain crucial information. Conversely, undersampling methods potentially remove useful information on certain subgroups. Hence, a resampling approach that takes the inherent distribution of data into consideration is required to ensure appropriate synthetic data creation. This study proposes an adaptive cluster-based synthetic minority oversampling technique. Density-based spatial clustering is applied on minority classes to identify subgroups based on their input features. The classes in each of these subgroups are then oversampled according to the ratio of data points of their local cluster to the largest majority class. When used in conjunction with machine learning models such as random forest and extreme gradient boosting, this oversampling method results in significantly higher F1 scores for the minority classes compared to other resampling techniques. These improved models provide accurate classification of transportation modes.

Environmental exposure to fluoride is a major public health concern, particularly in regions with naturally elevated fluoride concentrations. Accurate modeling of fluoride-related health risks, such as dental fluorosis, requires spatially aware learning frameworks capable of capturing both geographic and semantic heterogeneity. In this work, we propose Spatially Directional Dual-Attention Graph Attention Network (SDD-GAT), a novel spatial graph neural network designed for fine-grained health risk prediction. SDD-GAT introduces a dual-graph architecture that disentangles geographic proximity and attribute similarity, and incorporates a directional attention mechanism that explicitly encodes spatial orientation and distance into the message passing process. To further enhance spatial coherence, we introduce a spatial smoothness regularization term that enforces consistency in predictions across neighboring locations. We evaluate SDD-GAT on a large-scale dataset covering over 50,000 fluoride monitoring samples and fluorosis records across Guizhou Province, China. Results show that SDD-GAT significantly outperforms traditional models and state-of-the-art GNNs in both regression and classification tasks, while also exhibiting improved spatial autocorrelation as measured by Moran's I. Our framework provides a generalizable foundation for spatial health risk modeling and geospatial learning under complex environmental settings.