Link prediction tasks focus on predicting possible future connections. Most existing researches measure the likelihood of links by different similarity scores on node pairs and predict links between nodes. However, the similarity-based approaches have some challenges in information loss on nodes and generalization ability on similarity indexes. To address the above issues, we propose a Line Graph Contrastive Learning(LGCL) method to obtain rich information with multiple perspectives. LGCL obtains a subgraph view by h-hop subgraph sampling with target node pairs. After transforming the sampled subgraph into a line graph, the link prediction task is converted into a node classification task, which graph convolution progress can learn edge embeddings from graphs more effectively. Then we design a novel cross-scale contrastive learning framework on the line graph and the subgraph to maximize the mutual information of them, so that fuses the structure and feature information. The experimental results demonstrate that the proposed LGCL outperforms the state-of-the-art methods and has better performance on generalization and robustness.

The common spatial pattern (CSP) approach is known as one of the most popular spatial filtering techniques for EEG classification in motor imagery (MI) based brain-computer interfaces (BCIs). However, it still suffers some drawbacks such as sensitivity to noise, non-stationarity, and limitation to binary classification.Therefore, we propose a novel spatial filtering framework called scaCSP based on the scatter matrices of spatial covariances of EEG signals, which works generally in both binary and multi-class problems whereas CSP can be cast into our framework as a special case when only the range space of the between-class scatter matrix is used in binary cases.We further propose subspace enhanced scaCSP algorithms which easily permit incorporating more discriminative information contained in other range spaces and null spaces of the between-class and within-class scatter matrices in two scenarios: a nullspace components reduction scenario and an additional spatial filter learning scenario.The proposed algorithms are evaluated on two data sets including 4 MI tasks. The classification performance is compared against state-of-the-art competing algorithms: CSP, Tikhonov regularized CSP (TRCSP), stationary CSP (sCSP) and stationary TRCSP (sTRCSP) in the binary problems whilst multi-class extensions of CSP based on pair-wise and one-versus-rest techniques in the multi-class problems. The results show that the proposed framework outperforms all the competing algorithms in terms of average classification accuracy and computational efficiency in both binary and multi-class problems.The proposed scsCSP works as a unified framework for general multi-class problems and is promising for improving the performance of MI-BCIs.

Neyman-Scott processes (NSPs) have been applied across a range of fields to model points or temporal events with a hierarchy of clusters. Markov chain Monte Carlo (MCMC) is typically used for posterior sampling in the model. However, MCMC's mixing time can cause the resulting inference to be slow, and thereby slow down model learning and prediction. We develop the first variational inference (VI) algorithm for NSPs, and give two examples of suitable variational posterior point process distributions. Our method minimizes the inclusive Kullback-Leibler (KL) divergence for VI to obtain the variational parameters. We generate samples from the approximate posterior point processes much faster than MCMC, as we can directly estimate the approximate posterior point processes without any MCMC steps or gradient descent. We include synthetic and real-world data experiments that demonstrate our VI algorithm achieves better prediction performance than MCMC when computational time is limited.

We introduce a new differentially private regression setting we call Private Regression in Multiple Outcomes (PRIMO), inspired the common situation where a data analyst wants to perform a set of $l$ regressions while preserving privacy, where the covariates $X$ are shared across all $l$ regressions, and each regression $i \in [l]$ has a different vector of outcomes $y_i$. While naively applying private linear regression techniques $l$ times leads to a $\sqrt{l}$ multiplicative increase in error over the standard linear regression setting, in Subsection $4.1$ we modify techniques based on sufficient statistics perturbation (SSP) to yield greatly improved dependence on $l$. In Subsection $4.2$ we prove an equivalence to the problem of privately releasing the answers to a special class of low-sensitivity queries we call inner product queries. Via this equivalence, we adapt the geometric projection-based methods from prior work on private query release to the PRIMO setting. Under the assumption the labels $Y$ are public, the projection gives improved results over the Gaussian mechanism when $n < l\sqrt{d}$, with no asymptotic dependence on $l$ in the error. In Subsection $4.3$ we study the complexity of our projection algorithm, and analyze a faster sub-sampling based variant in Subsection $4.4$. Finally in Section $5$ we apply our algorithms to the task of private genomic risk prediction for multiple phenotypes using data from the 1000 Genomes project. We find that for moderately large values of $l$ our techniques drastically improve the accuracy relative to both the naive baseline that uses existing private regression methods and our modified SSP algorithm that doesn't use the projection.

While preserving the privacy of federated learning (FL), differential privacy (DP) inevitably degrades the utility (i.e., accuracy) of FL due to model perturbations caused by DP noise added to model updates. Existing studies have considered exclusively noise with persistent root-mean-square amplitude and overlooked an opportunity of adjusting the amplitudes to alleviate the adverse effects of the noise. This paper presents a new DP perturbation mechanism with a time-varying noise amplitude to protect the privacy of FL and retain the capability of adjusting the learning performance. Specifically, we propose a geometric series form for the noise amplitude and reveal analytically the dependence of the series on the number of global aggregations and the $(\epsilon,\delta)$-DP requirement. We derive an online refinement of the series to prevent FL from premature convergence resulting from excessive perturbation noise. Another important aspect is an upper bound developed for the loss function of a multi-layer perceptron (MLP) trained by FL running the new DP mechanism. Accordingly, the optimal number of global aggregations is obtained, balancing the learning and privacy. Extensive experiments are conducted using MLP, supporting vector machine, and convolutional neural network models on four public datasets. The contribution of the new DP mechanism to the convergence and accuracy of privacy-preserving FL is corroborated, compared to the state-of-the-art Gaussian noise mechanism with a persistent noise amplitude.

A high-dimensional and incomplete (HDI) matrix can describe the complex interactions among numerous nodes in various big data-related applications. A stochastic gradient descent (SGD)-based latent factor analysis (LFA) model is remarkably effective in extracting valuable information from an HDI matrix. However, such a model commonly encounters the problem of slow convergence because a standard SGD algorithm learns a latent factor relying on the stochastic gradient of current instance error only without considering past update information. To address this critical issue, this paper innovatively proposes a Fuzzy PID-incorporated SGD (FPS) algorithm with two-fold ideas: 1) rebuilding the instance learning error by considering the past update information in an efficient way following the principle of PID, and 2) implementing hyper-parameters and gain parameters adaptation following the fuzzy rules. With it, an FPS-incorporated LFA model is further achieved for fast processing an HDI matrix. Empirical studies on six HDI datasets demonstrate that the proposed FPS-incorporated LFA model significantly outperforms the state-of-the-art LFA models in terms of computational efficiency for predicting the missing data of an HDI matrix with competitive accuracy.

Constructing useful representations across a large number of tasks is a key requirement for sample-efficient intelligent systems. A traditional idea in multitask learning (MTL) is building a shared representation across tasks which can then be adapted to new tasks by tuning last layers. A desirable refinement of using a shared one-fits-all representation is to construct task-specific representations. To this end, recent PathNet/muNet architectures represent individual tasks as pathways within a larger supernet. The subnetworks induced by pathways can be viewed as task-specific representations that are composition of modules within supernet's computation graph. This work explores the pathways proposal from the lens of statistical learning: We first develop novel generalization bounds for empirical risk minimization problems learning multiple tasks over multiple paths (Multipath MTL). In conjunction, we formalize the benefits of resulting multipath representation when adapting to new downstream tasks. Our bounds are expressed in terms of Gaussian complexity, lead to tangible guarantees for the class of linear representations, and provide novel insights into the quality and benefits of a multipath representation. When computation graph is a tree, Multipath MTL hierarchically clusters the tasks and builds cluster-specific representations. We provide further discussion and experiments for hierarchical MTL and rigorously identify the conditions under which Multipath MTL is provably superior to traditional MTL approaches with shallow supernets.

Graph Neural networks (GNNs) have recently become a powerful technique for many graph-related tasks including graph classification. Current GNN models apply different graph pooling methods that reduce the number of nodes and edges to learn the higher-order structure of the graph in a hierarchical way. All these methods primarily rely on the one-hop neighborhood. However, they do not consider the higherorder structure of the graph. In this work, we propose a multi-channel Motif-based Graph Pooling method named (MPool) that captures the higher-order graph structure with motif and also local and global graph structure with a combination of selection and clustering-based pooling operation. As the first channel, we develop node selection-based graph pooling by designing a node ranking model considering the motif adjacency of nodes. As the second channel, we develop cluster-based graph pooling by designing a spectral clustering model using motif adjacency. As the final layer, the result of each channel is aggregated into the final graph representation. We perform extensive experiments on eight benchmark datasets and show that our proposed method shows better accuracy than the baseline methods for graph classification tasks.

Disadvantaged communities (DAC), as defined by the Justice40 initiative of the Department of Energy (DOE), USA, identifies census tracts across the USA to determine where benefits of climate and energy investments are or are not currently accruing. The DAC status not only helps in determining the eligibility for future Justice40-related investments but is also critical for exploring ways to achieve equitable distribution of resources. However, designing inclusive and equitable strategies not just requires a good understanding of current demographics, but also a deeper analysis of the transformations that happened in those demographics over the years. In this paper, machine learning (ML) models are trained on publicly available census data from recent years to classify the DAC status at the census tracts level and then the trained model is used to classify DAC status for historical years. A detailed analysis of the feature and model selection along with the evolution of disadvantaged communities between 2013 and 2018 is presented in this study.

The capacity of neural networks like the widely adopted transformer is known to be very high. Evidence is emerging that they learn successfully due to inductive bias in the training routine, typically a variant of gradient descent (GD). To better understand this bias, we study the tendency for transformer parameters to grow in magnitude ($\ell_2$ norm) during training, and its implications for the emergent representations within self attention layers. Empirically, we document norm growth in the training of transformer language models, including T5 during its pretraining. As the parameters grow in magnitude, we prove that the network approximates a discretized network with saturated activation functions. Such "saturated" networks are known to have a reduced capacity compared to the full network family that can be described in terms of formal languages and automata. Our results suggest saturation is a new characterization of an inductive bias implicit in GD of particular interest for NLP. We leverage the emergent discrete structure in a saturated transformer to analyze the role of different attention heads, finding that some focus locally on a small number of positions, while other heads compute global averages, allowing counting. We believe understanding the interplay between these two capabilities may shed further light on the structure of computation within large transformers.