Domain adaptation in medical image segmentation enables pre-trained models to generalize to new target domains. Given limited annotated data and privacy constraints, Source-Free Active Domain Adaptation (SFADA) methods provide promising solutions by selecting a few target samples for labeling without accessing source samples. However, in a fully source-free setting, existing works have not fully explored how to select these target samples in a class-balanced manner and how to conduct robust model adaptation using both labeled and unlabeled samples. In this study, we discover that boundary samples with source-like semantics but sharp predictive discrepancies are beneficial for SFADA. We define these samples as the most influential points and propose a slice-wise framework using influential points learning to explore them. Specifically, we detect source-like samples to retain source-specific knowledge. For each target sample, an adaptive K-nearest neighbor algorithm based on local density is introduced to construct neighborhoods of source-like samples for knowledge transfer. We then propose a class-balanced Kullback-Leibler divergence for these neighborhoods, calculating it to obtain an influential score ranking. A diverse subset of the highest-ranked target samples (considered influential points) is manually annotated. Furthermore, we design a progressive teacher model to facilitate SFADA for medical image segmentation. With the guidance of influential points, this model independently generates and utilizes pseudo-labels to mitigate error accumulation. To further suppress noise, curriculum learning is incorporated into the model to progressively leverage reliable supervision signals from pseudo-labels. Experiments on multiple benchmarks demonstrate that our method outperforms state-of-the-art methods even with only 2.5% of the labeling budget.

Large language models (LLMs) have shown remarkable generalization capability with exceptional performance in various language modeling tasks. However, they still exhibit inherent limitations in precisely capturing and returning grounded knowledge. While existing work has explored utilizing knowledge graphs (KGs) to enhance language modeling via joint training and customized model architectures, applying this to LLMs is problematic owing to their large number of parameters and high computational cost. Therefore, how to enhance pre-trained LLMs using grounded knowledge, e.g., retrieval-augmented generation, remains an open question. In this work, we propose Graph Neural Prompting (GNP), a novel plug-and-play method to assist pre-trained LLMs in learning beneficial knowledge from KGs. GNP encompasses various designs, including a standard graph neural network encoder, a cross-modality pooling module, a domain projector, and a self-supervised link prediction objective. Extensive experiments on multiple datasets demonstrate the superiority of GNP on both commonsense and biomedical reasoning tasks across different LLM sizes and settings. Code is available at https://github.com/meettyj/GNP.

Artificial Intelligence (AI) has enabled breakthroughs on sports analytics in recent years by allowing the extraction of valuable insights and new understandings from vast amounts of sports data. However, due to the highly interdisciplinary nature of the topic, cross-pollination of ideas and methodologies between AI and sports science as well as across different sports remain limited. To address the gap, we propose the first KDD workshop on Data Science and AI for Sports. We aim to bring together researchers and practitioners working on a broad array of sports-related AI/ML use cases, to exchange research ideas, draw connection among various disciplines, and identify challenges and new research questions for future work.

Real-world machine learning applications need to be thoroughly evaluated to meet critical product requirements for model release, to ensure fairness for different groups or individuals, and to achieve a consistent performance in various scenarios. For example, in autonomous driving, an object classification model should achieve high detection rates under different conditions of weather, distance, etc. Similarly, in the financial setting, credit-scoring models must not discriminate against minority groups. These conditions or groups are called as "Data Slices". In product MLOps cycles, product developers must identify such critical data slices and adapt models to mitigate data slice problems. Discovering where models fail, understanding why they fail, and mitigating these problems, are therefore essential tasks in the MLOps life-cycle. In this paper, we present SliceTeller, a novel tool that allows users to debug, compare and improve machine learning models driven by critical data slices. SliceTeller automatically discovers problematic slices in the data, helps the user understand why models fail. More importantly, we present an efficient algorithm, SliceBoosting, to estimate trade-offs when prioritizing the optimization over certain slices. Furthermore, our system empowers model developers to compare and analyze different model versions during model iterations, allowing them to choose the model version best suitable for their applications. We evaluate our system with three use cases, including two real-world use cases of product development, to demonstrate the power of SliceTeller in the debugging and improvement of product-quality ML models.

Graphs are a ubiquitous data structure to model processes and relations in a wide range of domains. Examples include control-flow graphs in programs and semantic scene graphs in images. Identifying subgraph patterns in graphs is an important approach to understand their structural properties. We propose a visual analytics system GraphQ to support human-in-the-loop, example-based, subgraph pattern search in a database containing many individual graphs. To support fast, interactive queries, we use graph neural networks (GNNs) to encode a graph as fixed-length latent vector representation, and perform subgraph matching in the latent space. Due to the complexity of the problem, it is still difficult to obtain accurate one-to-one node correspondences in the matching results that are crucial for visualization and interpretation. We, therefore, propose a novel GNN for node-alignment called NeuroAlign, to facilitate easy validation and interpretation of the query results. GraphQ provides a visual query interface with a query editor and a multi-scale visualization of the results, as well as a user feedback mechanism for refining the results with additional constraints. We demonstrate GraphQ through two example usage scenarios: analyzing reusable subroutines in program workflows and semantic scene graph search in images. Quantitative experiments show that NeuroAlign achieves 19%-29% improvement in node-alignment accuracy compared to baseline GNN and provides up to 100× speedup compared to combinatorial algorithms. Our qualitative study with domain experts confirms the effectiveness for both usage scenarios.

Modern data analysis pipelines are becoming increasingly complex due to the presence of multiview information sources. While graphs are effective in modeling complex relationships, in many scenarios, a single graph is rarely sufficient to succinctly represent all interactions, and hence, multilayered graphs have become popular. Though this leads to richer representations, extending solutions from the single-graph case is not straightforward. Consequently, there is a strong need for novel solutions to solve classical problems, such as node classification, in the multilayered case. In this article, we consider the problem of semisupervised learning with multilayered graphs. Though deep network embeddings, e.g., DeepWalk, are widely adopted for community discovery, we argue that feature learning with random node attributes, using graph neural networks, can be more effective. To this end, we propose to use attention models for effective feature learning and develop two novel architectures, GrAMME-SG and GrAMME-Fusion, that exploit the interlayer dependences for building multilayered graph embeddings. Using empirical studies on several benchmark data sets, we evaluate the proposed approaches and demonstrate significant performance improvements in comparison with the state-of-the-art network embedding strategies. The results also show that using simple random features is an effective choice, even in cases where explicit node attributes are not available.

Inferencing with graph data necessitates the mapping of its nodes into a vector space, where the relationships are preserved. However, with multi-layered graphs, where multiple types of relationships exist for the same set of nodes, it is crucial to exploit the information shared between layers, in addition to the distinct aspects of each layer. In this paper, we propose a novel approach that first obtains node embeddings in all layers jointly via DeepWalk on a supra graph, which allows interactions between layers, and then fine-tunes the embeddings to encourage cohesive structure in the latent space. With empirical studies in node classification, link prediction and multi-layered community detection, we show that the proposed approach outperforms existing single-and multi-layered graph embedding algorithms on several benchmarks. In addition to effectively scaling to a large number of layers (tested up to 37), our approach consistently produces highly modular community structure, even when compared to methods that directly optimize for the modularity function.

State-of-the-art speaker diarization systems utilize knowledge from external data, in the form of a pre-trained distance metric, to effectively determine relative speaker identities to unseen data. However, much of recent focus has been on choosing the appropriate feature extractor, ranging from pre-trained i-vectors to representations learned via different sequence modeling architectures (e.g. 1D-CNNs, LSTMs, attention models), while adopting off-the-shelf metric learning solutions. In this paper, we argue that, regardless of the feature extractor, it is crucial to carefully design a metric learning pipeline, namely the loss function, the sampling strategy and the discriminative margin parameter, for building robust diarization systems. Furthermore, we propose to adopt a fine-grained validation process to obtain a comprehensive evaluation of the generalization power of metric learning pipelines. To this end, we measure diarization performance across different language speakers, and variations in the number of speakers in a recording. Using empirical studies, we provide interesting insights into the effectiveness of different design choices and make recommendations.

With widespread adoption of electronic health records, there is an increased emphasis for predictive models that can effectively deal with clinical time-series data. Powered by Recurrent Neural Network (RNN) architectures with Long Short-Term Memory (LSTM) units, deep neural networks have achieved state-of-the-art results in several clinical prediction tasks. Despite the success of RNN, its sequential nature prohibits parallelized computing, thus making it inefficient particularly when processing long sequences. Recently, architectures which are based solely on attention mechanisms have shown remarkable success in transduction tasks in NLP, while being computationally superior. In this paper, for the first time, we utilize attention models for clinical time-series modeling, thereby dispensing recurrence entirely. We develop the SAnD (Simply Attend and Diagnose) architecture, which employs a masked, self-attention mechanism, and uses positional encoding and dense interpolation strategies for incorporating temporal order. Furthermore, we develop a multi-task variant of SAnD to jointly infer models with multiple diagnosis tasks. Using the recent MIMIC-III benchmark datasets, we demonstrate that the proposed approach achieves state-of-the-art performance in all tasks, outperforming LSTM models and classical baselines with hand-engineered features.

In automatic speech processing systems, speaker diarization is a crucial front-end component to separate segments from different speakers.Inspired by the recent success of deep neural networks (DNNs) in semantic inferencing, triplet loss-based architectures have been successfully used for this problem.However, existing work utilizes conventional i-vectors as the input representation and builds simple fully connected networks for metric learning, thus not fully leveraging the modeling power of DNN architectures.This paper investigates the importance of learning effective representations from the sequences directly in metric learning pipelines for speaker diarization.More specifically, we propose to employ attention models to learn embeddings and the metric jointly in an end-to-end fashion.Experiments are conducted on the CALLHOME conversational speech corpus.The diarization results demonstrate that, besides providing a unified model, the proposed approach achieves improved performance when compared against existing approaches.

Building highly nonlinear and nonparametric models is central to several state-of-the-art machine learning systems. Kernel methods form an important class of techniques that induce a reproducing kernel Hilbert space (RKHS) for inferring non-linear models through the construction of similarity functions from data. These methods are particularly preferred in cases where the training data sizes are limited and when prior knowledge of the data similarities is available. Despite their usefulness, they are limited by the computational complexity and their inability to support end-to-end learning with a task-specific objective. On the other hand, deep neural networks have become the de facto solution for end-to-end inference in several learning paradigms. In this paper, we explore the idea of using deep architectures to perform kernel machine optimization, for both computational efficiency and end-to-end inferencing. To this end, we develop the deep kernel machine optimization framework, that creates an ensemble of dense embeddings using Nyström kernel approximations and utilizes deep learning to generate task-specific representations through the fusion of the embeddings. Intuitively, the filters of the network are trained to fuse information from an ensemble of linear subspaces in the RKHS. Furthermore, we introduce the kernel dropout regularization to enable improved training convergence. Finally, we extend this framework to the multiple kernel case, by coupling a global fusion layer with pretrained deep kernel machines for each of the constituent kernels. Using case studies with limited training data, and lack of explicit feature sources, we demonstrate the effectiveness of our framework over conventional model inferencing techniques.

Several web-based signal processing simulation packages for education have been developed in a Java environment. Although this environment has provided convenience and accessibility using standard browser technology, it has recently become vulnerable to cyber-attacks and is no longer compatible with secure browsers. In this paper, we describe our efforts to transform our award-winning J-DSP online laboratory by rebuilding it on an HTML5 framework. Along with a new simulation environment, we have redesigned the interface to enable several new functionalities and an entirely new educational experience. These new features include functions that enable real-time interfaces with sensor boards and mobile phones. The Web 4.0 HTML5 technology departs from older Java interfaces and provides an interactive graphical user interface (GUI) enabling seamless connectivity and both software and hardware experiences for students in DSP classes.

Kernel fusion is a popular and effective approach for combining multiple features that characterize different aspects of data. Traditional approaches for Multiple Kernel Learning (MKL) attempt to learn the parameters for combining the kernels through sophisticated optimization procedures. In this paper, we propose an alternative approach that creates dense embeddings for data using the kernel similarities and adopts a deep neural network architecture for fusing the embeddings. In order to improve the effectiveness of this network, we introduce the kernel dropout regularization strategy coupled with the use of an expanded set of composition kernels. Experiment results on a real-world activity recognition dataset show that the proposed architecture is effective in fusing kernels and achieves state-of-the-art performance.

The pervasive use of wearable sensors in activity and health monitoring presents a huge potential for building novel data analysis and prediction frameworks. In particular, approaches that can harness data from a diverse set of low-cost sensors for recognition are needed. Many of the existing approaches rely heavily on elaborate feature engineering to build robust recognition systems, and their performance is often limited by the inaccuracies in the data. In this paper, we develop a novel two-stage recognition system that enables a systematic fusion of complementary information from multiple sensors in a linear graph embedding setting, while employing an ensemble classifier phase that leverages the discriminative power of different feature extraction strategies. Experimental results on a challenging dataset show that our framework greatly improves the recognition performance when compared to using any single sensor.

In complex visual recognition systems, feature fusion has become crucial to discriminate between a large number of classes. In particular, fusing high-level context information with image appearance models can be effective in object/scene recognition. To this end, we develop an auto-context modeling approach under the RKHS (Reproducing Kernel Hilbert Space) setting, wherein a series of supervised learners are used to approximate the context model. By posing the problem of fusing the context and appearance models using multiple kernel learning, we develop a computationally tractable solution to this challenging problem. Furthermore, we propose to use the marginal probabilities from a kernel SVM classifier to construct the auto-context kernel. In addition to providing better regularization to the learning problem, our approach leads to improved recognition performance in comparison to using only the image features.

Understanding global change is important for creating a sustainable environment, and is a key interest of the Earth systems science community. Here we present an educational tutorial that explores the relationship between sea level and global temperature using modern-day records and time-series analysis and the Java-DSP Earth Systems Edition (J-DSP/ESE) application. The objectives of the tutorial are to apply pre-processing steps based on signal type, perform spectral analysis and identify significant frequencies, perform coherency and cross-phase analysis between two records, and arrive at an informed understanding about the relationship between sea level and global temperature change. Preliminary student assessment indicates that students were comfortable using J-DSP/ESE, and quickly understood the signal processing concepts. The analysis reveals correlation between sea level variations and global temperature at inter-annual timescales related to the El Niño climatological phenomenon. In sum, the tutorial improved students' understanding of basic factors that influence global sustainability and habitability.

With the advances in optical technology, the span of a broadband access network using passive optical network (PON) technology can be increased from today's standard of 20 km to 100 km or higher, and thereby serve a lot more users. Such an extended-reach PON is known as SuperPON in the literature, and we call it a long-reach PON (LR-PON). A major challenge in LR-PON is that the propagation delay (for data as well as control signals) between the telecom central office (CO) and the end user is increased by a very significant amount. Now, traditional PON algorithms for scheduling the upstream transmission, such as dynamic bandwidth allocation (DBA) algorithms, may not be sufficient; actually, they may lead to degraded performance because of the long delay of the CO-to- Users "control loop." This challenge motivates us to propose and study a multi-thread polling algorithm to effectively and fairly distribute the upstream bandwidth dynamically. This algorithm exploits the benefits of having multiple polling processes running simultaneously and enabling users to send bandwidth requests before receiving acknowledgement from the CO. We compare the proposed algorithm with traditional DBA, and show its advantage on average packet delay. We then analyze and optimize key parameters of the algorithm, such as initiating and tuning multiple threads, inter-thread scheduling, and fairness among users. Numerical results demonstrate the algorithm's advantage to decrease the average packet delay and improve network throughput under varying offered loads.

With the development of optical technology, the span of a broadband access network using passive optical network (PON) technology can be increased from today's standard of 20 km to 100 km or higher. As a result, we have the long-reach (LR) PON which not only has extended reach, but which can also support a large base of users by employing wavelength-division multiplexing (WDM) for its data transmissions. However, a major challenge in the LR-PON is that the propagation delay (for data as well as control signals) between the telecom central office (CO) and the end user is increased by a very significant amount. Now, traditional PON algorithms for scheduling the upstream transmission, such as dynamic bandwidth allocation (DBA) algorithms, may not be sufficient; actually, they may lead to degraded performance because of the long delay of the "control loop" between the CO and the users. This challenge motivates us to investigate a multi-thread polling algorithm to distribute the upstream bandwidth dynamically in the LR-PON. In this study, we analyze key parameters of the algorithm, such as initiating and tuning multiple threads. We then demonstrate the algorithm's advantage to decrease the average packet delay under varying offered loads.