Polypharmacy, defined as the use of multiple drugs together, is a standard treatment method, especially for severe and chronic diseases. However, using multiple drugs together may cause interactions between drugs. Drug-drug interaction (DDI) is the activity that occurs when the impact of one drug changes when combined with another. DDIs may obstruct, increase, or decrease the intended effect of either drug or, in the worst-case scenario, create adverse side effects. While it is critical to detect DDIs on time, it is timeconsuming and expensive to identify them in clinical trials due to their short duration and many possible drug pairs to be considered for testing. As a result, computational methods are needed for predicting DDIs. In this paper, we present a novel heterogeneous graph attention model, HAN-DDI to predict drug-drug interactions. We create a heterogeneous network of drugs with different biological entities. Then, we develop a heterogeneous graph attention network to learn DDIs using relations of drugs with other entities. It consists of an attention-based heterogeneous graph node encoder for obtaining drug node representations and a decoder for predicting drug-drug interactions. Further, we utilize comprehensive experiments to evaluate of our model and to compare it with state-of-the-art models. Experimental results show that our proposed method, HAN-DDI, outperforms the baselines significantly and accurately predicts DDIs, even for new drugs.

We present our findings in the gap between theory and practice of using conditional energy-based models (EBM) as an implicit representation for behavior-cloned policies. We also clarify several subtle, and potentially confusing, details in previous work in an attempt to help future research in this area. We point out key differences between unconditional and conditional EBMs, and warn that blindly applying training methods for one to the other could lead to undesirable results that do not generalize well. Finally, we emphasize the importance of the Maximum Mutual Information principle as a necessary condition to achieve good generalization in conditional EBMs as implicit models for regression tasks.

We study the problem of differentially private linear regression where each data point is sampled from a fixed sub-Gaussian style distribution. We propose and analyze a one-pass mini-batch stochastic gradient descent method (DP-AMBSSGD) where points in each iteration are sampled without replacement. Noise is added for DP but the noise standard deviation is estimated online. Compared to existing $(\epsilon, \delta)$-DP techniques which have sub-optimal error bounds, DP-AMBSSGD is able to provide nearly optimal error bounds in terms of key parameters like dimensionality $d$, number of points $N$, and the standard deviation $\sigma$ of the noise in observations. For example, when the $d$-dimensional covariates are sampled i.i.d. from the normal distribution, then the excess error of DP-AMBSSGD due to privacy is $\frac{\sigma^2 d}{N}(1+\frac{d}{\epsilon^2 N})$, i.e., the error is meaningful when number of samples $N= \Omega(d \log d)$ which is the standard operative regime for linear regression. In contrast, error bounds for existing efficient methods in this setting are: $\mathcal{O}\big(\frac{d^3}{\epsilon^2 N^2}\big)$, even for $\sigma=0$. That is, for constant $\epsilon$, the existing techniques require $N=\Omega(d\sqrt{d})$ to provide a non-trivial result.

Security-constrained unit commitment (SCUC) is solved for power system day-ahead generation scheduling, which is a large-scale mixed-integer linear programming problem and is very computationally intensive. Model reduction of SCUC may bring significant time savings. In this work, a novel approach is proposed to effectively utilize machine learning (ML) to reduce the problem size of SCUC. An ML model using logistic regression (LR) algorithm is proposed and trained with historical nodal demand profiles and the respective commitment schedules. The ML outputs are processed and analyzed to reduce variables and constraints in SCUC. The proposed approach is validated on several standard test systems including IEEE 24-bus system, IEEE 73-bus system, IEEE 118-bus system, synthetic South Carolina 500-bus system and Polish 2383-bus system. Simulation results demonstrate that the use of the prediction from the proposed LR model in SCUC model reduction can substantially reduce the computing time while maintaining solution quality.

Stochastic gradient descent (SGD) with momentum is widely used for training modern deep learning architectures. While it is well-understood that using momentum can lead to faster convergence rate in various settings, it has also been observed that momentum yields higher generalization. Prior work argue that momentum stabilizes the SGD noise during training and this leads to higher generalization. In this paper, we adopt another perspective and first empirically show that gradient descent with momentum (GD+M) significantly improves generalization compared to gradient descent (GD) in some deep learning problems. From this observation, we formally study how momentum improves generalization. We devise a binary classification setting where a one-hidden layer (over-parameterized) convolutional neural network trained with GD+M provably generalizes better than the same network trained with GD, when both algorithms are similarly initialized. The key insight in our analysis is that momentum is beneficial in datasets where the examples share some feature but differ in their margin. Contrary to GD that memorizes the small margin data, GD+M still learns the feature in these data thanks to its historical gradients. Lastly, we empirically validate our theoretical findings.

This primer is an attempt to provide a detailed summary of the different facets of lifelong learning. We start with Chapter 2 which provides a high-level overview of lifelong learning systems. In this chapter, we discuss prominent scenarios in lifelong learning (Section 2.4), provide 8 Introduction a high-level organization of different lifelong learning approaches (Section 2.5), enumerate the desiderata for an ideal lifelong learning system (Section 2.6), discuss how lifelong learning is related to other learning paradigms (Section 2.7), describe common metrics used to evaluate lifelong learning systems (Section 2.8). This chapter is more useful for readers who are new to lifelong learning and want to get introduced to the field without focusing on specific approaches or benchmarks. The remaining chapters focus on specific aspects (either learning algorithms or benchmarks) and are more useful for readers who are looking for specific approaches or benchmarks. Chapter 3 focuses on regularization-based approaches that do not assume access to any data from previous tasks. Chapter 4 discusses memory-based approaches that typically use a replay buffer or an episodic memory to save subset of data across different tasks. Chapter 5 focuses on different architecture families (and their instantiations) that have been proposed for training lifelong learning systems. Following these different classes of learning algorithms, we discuss the commonly used evaluation benchmarks and metrics for lifelong learning (Chapter 6) and wrap up with a discussion of future challenges and important research directions in Chapter 7.

Smart wearables have played an integral part in our day to day life. From recording ECG signals to analysing body fat composition, the smart wearables can do it all. The smart devices encompass various sensors which can be employed to derive meaningful information regarding the user's physical and psychological conditions. Our approach focuses on employing such sensors to identify and obtain the variations in the mood of a user at a given instance through the use of supervised machine learning techniques. The study examines the performance of various supervised learning models such as Decision Trees, Random Forests, XGBoost, LightGBM on the dataset. With our proposed model, we obtained a high recognition rate of 92.5% using XGBoost and LightGBM for 9 different emotion classes. By utilizing this, we aim to improvise and suggest methods to aid emotion recognition for better mental health analysis and mood monitoring.

Scientists increasingly rely on Python tools to perform scalable distributed memory array operations using rich, NumPy-like expressions. However, many of these tools rely on dynamic schedulers optimized for abstract task graphs, which often encounter memory and network bandwidth-related bottlenecks due to sub-optimal data and operator placement decisions. Tools built on the message passing interface (MPI), such as ScaLAPACK and SLATE, have better scaling properties, but these solutions require specialized knowledge to use. In this work, we present NumS, an array programming library which optimizes NumPy-like expressions on task-based distributed systems. This is achieved through a novel scheduler called Load Simulated Hierarchical Scheduling (LSHS). LSHS is a local search method which optimizes operator placement by minimizing maximum memory and network load on any given node within a distributed system. Coupled with a heuristic for load balanced data layouts, our approach is capable of attaining communication lower bounds on some common numerical operations, and our empirical study shows that LSHS enhances performance on Ray by decreasing network load by a factor of 2x, requiring 4x less memory, and reducing execution time by 10x on the logistic regression problem. On terabyte-scale data, NumS achieves competitive performance to SLATE on DGEMM, up to 20x speedup over Dask on a key operation for tensor factorization, and a 2x speedup on logistic regression compared to Dask ML and Spark's MLlib.

Welcome to the second part of Humans Learning from Machines. In this series, we discuss the philosophical relevance of some interesting concepts in Artificial Intelligence. In part 1: The Curse of Dimensionality; More is not always better!, we explored how more data can affect learnability in terms of Computational Burden, the Volume of Space, Visualisation and Parameter Estimation. In this part, we discuss how to handle the curse of dimensionality and how we can apply these concepts to improve our well-being. As we wrapped up the first part, When we feel overwhelmed by the infinite dimensions of data surrounding us, we change our perspectives and see things from a different angle to separate noise and relevant information.

Matt Harrison runs MetaSnake, a Python and Data Science consultancy and corporate training shop. In the past, he has worked across the domains of search, build management and testing, business intelligence, and storage. He has presented and taught tutorials at conferences such as Strata, SciPy, SCALE, PyCON, and OSCON as well as local user conferences. The structure and content of his books are based on first-hand experience teaching Python to many individuals.