A Lottery Ticket Hypothesis Framework for Low-Complexity Device-Robust Neural Acoustic Scene Classification

We propose a novel neural model compression strategy combining data augmentation, knowledge transfer, pruning, and quantization for device-robust acoustic scene classification (ASC). Specifically, we tackle the ASC task in a low-resource environment leveraging a recently proposed advanced neural network pruning mechanism, namely Lottery Ticket Hypothesis (LTH), to find a sub-network neural model associated with a small amount non-zero model parameters. The effectiveness of LTH for low-complexity acoustic modeling is assessed by investigating various data augmentation and compression schemes, and we report an efficient joint framework for low-complexity multi-device ASC, called Acoustic Lottery. Acoustic Lottery could compress an ASC model over $1/10^{4}$ and attain a superior performance (validation accuracy of 74.01% and Log loss of 0.76) compared to its not compressed seed model. All results reported in this work are based on a joint effort of four groups, namely GT-USTC-UKE-Tencent, aiming to address the "Low-Complexity Acoustic Scene Classification (ASC) with Multiple Devices" in the DCASE 2021 Challenge Task 1a.

Correcting Exposure Bias for Link Recommendation

Link prediction methods are frequently applied in recommender systems, e.g., to suggest citations for academic papers or friends in social networks. However, exposure bias can arise when users are systematically underexposed to certain relevant items. For example, in citation networks, authors might be more likely to encounter papers from their own field and thus cite them preferentially. This bias can propagate through naively trained link predictors, leading to both biased evaluation and high generalization error (as assessed by true relevance). Moreover, this bias can be exacerbated by feedback loops. We propose estimators that leverage known exposure probabilities to mitigate this bias and consequent feedback loops. Next, we provide a loss function for learning the exposure probabilities from data. Finally, experiments on semi-synthetic data based on real-world citation networks, show that our methods reliably identify (truly) relevant citations. Additionally, our methods lead to greater diversity in the recommended papers' fields of study. The code is available at https://github.com/shantanu95/exposure-bias-link-rec.

5G MIMO Data for Machine Learning: Application to Beam-Selection using Deep Learning

The increasing complexity of configuring cellular networks suggests that machine learning (ML) can effectively improve 5G technologies. Deep learning has proven successful in ML tasks such as speech processing and computational vision, with a performance that scales with the amount of available data. The lack of large datasets inhibits the flourish of deep learning applications in wireless communications. This paper presents a methodology that combines a vehicle traffic simulator with a raytracing simulator, to generate channel realizations representing 5G scenarios with mobility of both transceivers and objects. The paper then describes a specific dataset for investigating beams-election techniques on vehicle-to-infrastructure using millimeter waves. Experiments using deep learning in classification, regression and reinforcement learning problems illustrate the use of datasets generated with the proposed methodology

Zero-Shot Recommender Systems

Performance of recommender systems (RS) relies heavily on the amount of training data available. This poses a chicken-and-egg problem for early-stage products, whose amount of data, in turn, relies on the performance of their RS. On the other hand, zero-shot learning promises some degree of generalization from an old dataset to an entirely new dataset. In this paper, we explore the possibility of zero-shot learning in RS. We develop an algorithm, dubbed ZEro-Shot Recommenders (ZESRec), that is trained on an old dataset and generalize to a new one where there are neither overlapping users nor overlapping items, a setting that contrasts typical cross-domain RS that has either overlapping users or items. Different from categorical item indices, i.e., item ID, in previous methods, ZESRec uses items' natural-language descriptions (or description embeddings) as their continuous indices, and therefore naturally generalize to any unseen items. In terms of users, ZESRec builds upon recent advances on sequential RS to represent users using their interactions with items, thereby generalizing to unseen users as well. We study two pairs of real-world RS datasets and demonstrate that ZESRec can successfully enable recommendations in such a zero-shot setting, opening up new opportunities for resolving the chicken-and-egg problem for data-scarce startups or early-stage products.

Variance Reduction in Training Forecasting Models with Subgroup Sampling

In real-world applications of large-scale time series, one often encounters the situation where the temporal patterns of time series, while drifting over time, differ from one another in the same dataset. In this paper, we provably show under such heterogeneity, training a forecasting model with commonly used stochastic optimizers (e.g. SGD) potentially suffers large gradient variance, and thus requires long time training. To alleviate this issue, we propose a sampling strategy named Subgroup Sampling, which mitigates the large variance via sampling over pre-grouped time series. We further introduce SCott, a variance reduced SGD-style optimizer that co-designs subgroup sampling with the control variate method. In theory, we provide the convergence guarantee of SCott on smooth non-convex objectives. Empirically, we evaluate SCott and other baseline optimizers on both synthetic and real-world time series forecasting problems, and show SCott converges faster with respect to both iterations and wall clock time. Additionally, we show two SCott variants that can speed up Adam and Adagrad without compromising generalization of forecasting models.

Deep Learning-based Compressive Beam Alignment in mmWave Vehicular Systems

Millimeter wave vehicular channels exhibit structure that can be exploited for beam alignment with fewer channel measurements compared to exhaustive beam search. With fixed layouts of roadside buildings and regular vehicular moving trajectory, the dominant path directions of channels will likely be among a subset of beam directions instead of distributing randomly over the whole beamspace. In this paper, we propose a deep learning-based technique to design a structured compressed sensing (CS) matrix that is well suited to the underlying channel distribution for mmWave vehicular beam alignment. The proposed approach leverages both sparsity and the particular spatial structure that appears in vehicular channels. We model the compressive channel acquisition by a two-dimensional (2D) convolutional layer followed by dropout. We design fully-connected layers to optimize channel acquisition and beam alignment. We incorporate the low-resolution phase shifter constraint during neural network training by using projected gradient descent for weight updates. Furthermore, we exploit channel spectral structure to optimize the power allocated for different subcarriers. Simulations indicate that our deep learning-based approach achieves better beam alignment than standard CS techniques which use random phase shift-based design. Numerical experiments also show that one single subcarrier is sufficient to provide necessary information for beam alignment.

MolCLR: Molecular Contrastive Learning of Representations via Graph Neural Networks

Molecular machine learning bears promise for efficient molecule property prediction and drug discovery. However, due to the limited labeled data and the giant chemical space, machine learning models trained via supervised learning perform poorly in generalization. This greatly limits the applications of machine learning methods for molecular design and discovery. In this work, we present MolCLR: Molecular Contrastive Learning of Representations via Graph Neural Networks (GNNs), a self-supervised learning framework for large unlabeled molecule datasets. Specifically, we first build a molecular graph, where each node represents an atom and each edge represents a chemical bond. A GNN is then used to encode the molecule graph. We propose three novel molecule graph augmentations: atom masking, bond deletion, and subgraph removal. A contrastive estimator is utilized to maximize the agreement of different graph augmentations from the same molecule. Experiments show that molecule representations learned by MolCLR can be transferred to multiple downstream molecular property prediction tasks. Our method thus achieves state-of-the-art performance on many challenging datasets. We also prove the efficiency of our proposed molecule graph augmentations on supervised molecular classification tasks.

Attention-based Domain Adaptation for Time Series Forecasting

Recent years have witnessed deep neural networks gaining increasing popularity in the field of time series forecasting. A primary reason of their success is their ability to effectively capture complex temporal dynamics across multiple related time series. However, the advantages of these deep forecasters only start to emerge in the presence of a sufficient amount of data. This poses a challenge for typical forecasting problems in practice, where one either has a small number of time series, or limited observations per time series, or both. To cope with the issue of data scarcity, we propose a novel domain adaptation framework, Domain Adaptation Forecaster (DAF), that leverages the statistical strengths from another relevant domain with abundant data samples (source) to improve the performance on the domain of interest with limited data (target). In particular, we propose an attention-based shared module with a domain discriminator across domains as well as private modules for individual domains. This allows us to jointly train the source and target domains by generating domain-invariant latent features while retraining domain-specific features. Extensive experiments on various domains demonstrate that our proposed method outperforms state-of-the-art baselines on synthetic and real-world datasets.

Deep Reinforcement Learning Optimizes Graphene Nanopores for Efficient Desalination

Two-dimensional nanomaterials, such as graphene, have been extensively studied because of their outstanding physical properties. Structure and geometry optimization of nanopores on such materials is beneficial for their performances in real-world engineering applications, like water desalination. However, the optimization process often involves very large number of experiments or simulations which are expensive and time-consuming. In this work, we propose a graphene nanopore optimization framework via the combination of deep reinforcement learning (DRL) and convolutional neural network (CNN) for efficient water desalination. The DRL agent controls the growth of nanopore by determining the atom to be removed at each timestep, while the CNN predicts the performance of nanoporus graphene for water desalination: the water flux and ion rejection at a certain external pressure. With the synchronous feedback from CNN-accelerated desalination performance prediction, our DRL agent can optimize the nanoporous graphene efficiently in an online manner. Molecular dynamics (MD) simulations on promising DRL-designed graphene nanopores show that they have higher water flux while maintaining rival ion rejection rate compared to the normal circular nanopores. Semi-oval shape with rough edges geometry of DRL-designed pores is found to be the key factor for their high water desalination performance. Ultimately, this study shows that DRL can be a powerful tool for material design.