Machine Unlearning has recently been emerging as a paradigm for selectively removing the impact of training datapoints from a network. While existing approaches have focused on unlearning either a small subset of the training data or a single class, in this paper we take a different path and devise a framework that can unlearn all classes of an image classification network in a single untraining round. Our proposed technique learns to modulate the inner components of an image classification network through memory matrices so that, after training, the same network can selectively exhibit an unlearning behavior over any of the classes. By discovering weights which are specific to each of the classes, our approach also recovers a representation of the classes which is explainable by-design. We test the proposed framework, which we name Weight Filtering network (WF-Net), on small-scale and medium-scale image classification datasets, with both CNN and Transformer-based backbones. Our work provides interesting insights in the development of explainable solutions for unlearning and could be easily extended to other vision tasks.

Diffusion models have become a new SOTA generative modeling method in various fields, for which there are multiple survey works that provide an overall survey. With the number of articles on diffusion models increasing exponentially in the past few years, there is an increasing need for surveys of diffusion models on specific fields. In this work, we are committed to conducting a survey on the graph diffusion models. Even though our focus is to cover the progress of diffusion models in graphs, we first briefly summarize how other generative modeling methods are used for graphs. After that, we introduce the mechanism of diffusion models in various forms, which facilitates the discussion on the graph diffusion models. The applications of graph diffusion models mainly fall into the category of AI-generated content (AIGC) in science, for which we mainly focus on how graph diffusion models are utilized for generating molecules and proteins but also cover other cases, including materials design. Moreover, we discuss the issue of evaluating diffusion models in the graph domain and the existing challenges.

Transformer networks have revolutionized NLP representation learning since they were introduced. Though a great effort has been made to explain the representation in transformers, it is widely recognized that our understanding is not sufficient. One important reason is that there lack enough visualization tools for detailed analysis. In this paper, we propose to use dictionary learning to open up these "black boxes" as linear superpositions of transformer factors. Through visualization, we demonstrate the hierarchical semantic structures captured by the transformer factors, e.g., word-level polysemy disambiguation, sentence-level pattern formation, and long-range dependency. While some of these patterns confirm the conventional prior linguistic knowledge, the rest are relatively unexpected, which may provide new insights. We hope this visualization tool can bring further knowledge and a better understanding of how transformer networks work. The code is available at https://github.com/zeyuyun1/TransformerVis

The dynamics of systems of many degrees of freedom evolving on multiple scales are often modeled in terms of stochastic differential equations. Usually the structural form of these equations is unknown and the only manifestation of the system's dynamics are observations at discrete points in time. Despite their widespread use, accurately inferring these systems from sparse-in-time observations remains challenging. Conventional inference methods either focus on the temporal structure of observations, neglecting the geometry of the system's invariant density, or use geometric approximations of the invariant density, which are limited to conservative driving forces. To address these limitations, here, we introduce a novel approach that reconciles these two perspectives. We propose a path augmentation scheme that employs data-driven control to account for the geometry of the invariant system's density. Non-parametric inference on the augmented paths, enables efficient identification of the underlying deterministic forces of systems observed at low sampling rates.

Predicting personality traits based on online posts has emerged as an important task in many fields such as social network analysis. One of the challenges of this task is assembling information from various posts into an overall profile for each user. While many previous solutions simply concatenate the posts into a long document and then encode the document by sequential or hierarchical models, they introduce unwarranted orders for the posts, which may mislead the models. In this paper, we propose a dynamic deep graph convolutional network (D-DGCN) to overcome the above limitation. Specifically, we design a learn-to-connect approach that adopts a dynamic multi-hop structure instead of a deterministic structure, and combine it with a DGCN module to automatically learn the connections between posts. The modules of post encoder, learn-to-connect, and DGCN are jointly trained in an end-to-end manner. Experimental results on the Kaggle and Pandora datasets show the superior performance of D-DGCN to state-of-the-art baselines. Our code is available at https://github.com/djz233/D-DGCN.

Urban anomaly predictions, such as traffic accident prediction and crime prediction, are of vital importance to smart city security and maintenance. Existing methods typically use deep learning to capture the intra-dependencies in spatial and temporal dimensions. However, numerous key challenges remain unsolved, for instance, sparse zero-inflated data due to urban anomalies occurring with low frequency (which can lead to poor performance on real-world datasets), and both intra- and inter-dependencies of abnormal patterns across spatial, temporal, and semantic dimensions. Moreover, a unified approach to predict multiple kinds of anomaly is left to explore. In this paper, we propose STS to jointly capture the intra- and inter-dependencies between the patterns and the influential factors in three dimensions. Further, we use a multi-task prediction module with a customized loss function to solve the zero-inflated issue. To verify the effectiveness of the model, we apply it to two urban anomaly prediction tasks, crime prediction and traffic accident risk prediction, respectively. Experiments on two application scenarios with four real-world datasets demonstrate the superiority of STS, which outperforms state-of-the-art methods in the mean absolute error and the root mean square error by 37.88% and 18.10% on zero-inflated datasets, and, 60.32% and 37.28% on non-zero datasets, respectively.

This paper focuses on optimal unimodal transformation of the score outputs of a univariate learning model under linear loss functions. We demonstrate that the optimal mapping between score values and the target region is a rectangular function. To produce this optimal rectangular fit for the observed samples, we propose a sequential approach that can its estimation with each incoming new sample. Our approach has logarithmic time complexity per iteration and is optimally efficient.

The interactive exploration of large and evolving datasets is challenging as relationships between underlying variables may not be fully understood. There may be hidden trends and patterns in the data that are worthy of further exploration and analysis. We present a system that methodically explores multiple combinations of variables using a searchlight technique and identifies outliers. An iterative k-means clustering algorithm is applied to features derived through a split-apply-combine paradigm used in the database literature. Outliers are identified as singleton or small clusters. This algorithm is swept across the dataset in a searchlight manner. The dimensions that contain outliers are combined in pairs with other dimensions using a susbset scan technique to gain further insight into the outliers. We illustrate this system by anaylzing open health care data released by New York State. We apply our iterative k-means searchlight followed by subset scanning. Several anomalous trends in the data are identified, including cost overruns at specific hospitals, and increases in diagnoses such as suicides. These constitute novel findings in the literature, and are of potential use to regulatory agencies, policy makers and concerned citizens.

Modern neural networks (Krizhevsky et al., 2012; He et al., 2016; Vaswani et al., 2017) are trained using stochastic gradient-based algorithms (Rumelhart et al., 1986; Kingma and Ba, 2014), involving randomized weight initialization, data/batch ordering, and data augmentations. Because of this stochasticity, each independent run of training produces a different network with better or worse performance than average. The difference between such independent runs is often substantial. Picard (2021) finds that for a standard CIFAR-10 (Krizhevsky et al., 2009) training configuration, there exist random seeds which differ by 1.3% in terms of test-set accuracy. In comparison, the gap between the top two methods competing for state-of-the-art on CIFAR-10 has been less than 1% throughout the majority of the benchmark's lifetime

In spite of the progress in music source separation research, the small amount of publicly-available clean source data remains a constant limiting factor for performance. Thus, recent advances in self-supervised learning present a largely-unexplored opportunity for improving separation models by leveraging unlabelled music data. In this paper, we propose a self-supervised learning framework for music source separation inspired by the HuBERT speech representation model. We first investigate the potential impact of the original HuBERT model by inserting an adapted version of it into the well-known Demucs V2 time-domain separation model architecture. We then propose a time-frequency-domain self-supervised model, Pac-HuBERT (for primitive auditory clustering HuBERT), that we later use in combination with a Res-U-Net decoder for source separation. Pac-HuBERT uses primitive auditory features of music as unsupervised clustering labels to initialize the self-supervised pretraining process using the Free Music Archive (FMA) dataset. The resulting framework achieves better source-to-distortion ratio (SDR) performance on the MusDB18 test set than the original Demucs V2 and Res-U-Net models. We further demonstrate that it can boost performance with small amounts of supervised data. Ultimately, our proposed framework is an effective solution to the challenge of limited clean source data for music source separation.