Cancer has long been a main cause of human death, and the discovery of new drugs and the customization of cancer therapy have puzzled people for a long time. In order to facilitate the discovery of new anti-cancer drugs and the customization of treatment strategy, we seek to predict the response of different anti-cancer drugs with variational autoencoders (VAE) and multi-layer perceptron (MLP).Our model takes as input gene expression data of cancer cell lines and anti-cancer drug molecular data, and encode these data with {\sc {GeneVae}} model, which is an ordinary VAE, and rectified junction tree variational autoencoder ({\sc JtVae}) (\cite{jin2018junction}) model, respectively. Encoded features are processes by a Multi-layer Perceptron (MLP) model to produce a final prediction. We reach an average coefficient of determination ($R^{2} = 0.83$) in predicting drug response on breast cancer cell lines and an average $R^{2} > 0.84$ on pan-cancer cell lines. Additionally, we show that our model can generate unseen effective drug compounds for specific cancer cell lines.

Coarse graining enables the investigation of molecular dynamics for larger systems and at longer timescales than is possible at atomic resolution. However, a coarse graining model must be formulated such that the conclusions we draw from it are consistent with the conclusions we would draw from a model at a finer level of detail. It has been proven that a force matching scheme defines a thermodynamically consistent coarse-grained model for an atomistic system in the variational limit. Wang et al. [ACS Cent. Sci. 5, 755 (2019)] demonstrated that the existence of such a variational limit enables the use of a supervised machine learning framework to generate a coarse-grained force field, which can then be used for simulation in the coarse-grained space. Their framework, however, requires the manual input of molecular features upon which to machine learn the force field. In the present contribution, we build upon the advance of Wang et al.and introduce a hybrid architecture for the machine learning of coarse-grained force fields that learns their own features via a subnetwork that leverages continuous filter convolutions on a graph neural network architecture. We demonstrate that this framework succeeds at reproducing the thermodynamics for small biomolecular systems. Since the learned molecular representations are inherently transferable, the architecture presented here sets the stage for the development of machine-learned, coarse-grained force fields that are transferable across molecular systems.

Deep learning methods for graphs achieve remarkable performance on many node-level and graph-level prediction tasks. However, despite the proliferation of the methods and their success, prevailing Graph Neural Networks (GNNs) neglect subgraphs, rendering subgraph prediction tasks challenging to tackle in many impactful applications. Further, subgraph prediction tasks present several unique challenges: subgraphs can have non-trivial internal topology, but also carry a notion of position and external connectivity information relative to the underlying graph in which they exist. Here, we introduce SubGNN, a subgraph neural network to learn disentangled subgraph representations. We propose a novel subgraph routing mechanism that propagates neural messages between the subgraph's components and randomly sampled anchor patches from the underlying graph, yielding highly accurate subgraph representations. SubGNN specifies three channels, each designed to capture a distinct aspect of subgraph topology, and we provide empirical evidence that the channels encode their intended properties. We design a series of new synthetic and real-world subgraph datasets. Empirical results for subgraph classification on eight datasets show that SubGNN achieves considerable performance gains, outperforming strong baseline methods, including node-level and graph-level GNNs, by 19.8% over the strongest baseline. SubGNN performs exceptionally well on challenging biomedical datasets where subgraphs have complex topology and even comprise multiple disconnected components.

We study the effect of mini-batching on the loss landscape of deep neural networks using spiked, field-dependent random matrix theory. We demonstrate that the magnitude of the extremal values of the batch Hessian are larger than those of the empirical Hessian. We also derive similar results for the Generalised Gauss-Newton matrix approximation of the Hessian. As a consequence of our theorems we derive an analytical expressions for the maximal learning rates as a function of batch size, informing practical optimisation schemes for both stochastic gradient descent (linear scaling) and adaptive algorithms such as Adam (square root scaling). Whilst the linear scaling for stochastic gradient descent has been derived under more restrictive conditions, which we generalise, the square root scaling rule for adaptive optimisers is, to our knowledge, completely novel. For stochastic Second-order methods and adaptive methods, we derive that the minimal damping coefficient is proportional to the ratio of the learning rate to batch size.

In recent times, neural networks have become a powerful tool for the analysis of complex and abstract data models. However, their introduction intrinsically increases our uncertainty about which features of the analysis are model-related and which are due to the neural network. This means that predictions by neural networks have biases which cannot be trivially distinguished from being due to the true nature of the creation and observation of data or not. In order to attempt to address such issues we discuss Bayesian neural networks: neural networks where the uncertainty due to the network can be characterised. In particular, we present the Bayesian statistical framework which allows us to categorise uncertainty in terms of the ingrained randomness of observing certain data and the uncertainty from our lack of knowledge about how data can be created and observed. In presenting such techniques we show how errors in prediction by neural networks can be obtained in principle, and provide the two favoured methods for characterising these errors. We will also describe how both of these methods have substantial pitfalls when put into practice, highlighting the need for other statistical techniques to truly be able to do inference when using neural networks.

The ever-growing advances of deep learning in many areas including vision, recommendation systems, natural language processing, etc., have led to the adoption of Deep Neural Networks (DNNs) in production systems. The availability of large datasets and high computational power are the main contributors to these advances. The datasets are usually crowdsourced and may contain sensitive information. This poses serious privacy concerns as this data can be misused or leaked through various vulnerabilities. Even if the cloud provider and the communication link is trusted, there are still threats of inference attacks where an attacker could speculate properties of the data used for training, or find the underlying model architecture and parameters. In this survey, we review the privacy concerns brought by deep learning, and the mitigating techniques introduced to tackle these issues. We also show that there is a gap in the literature regarding test-time inference privacy, and propose possible future research directions.

With recent advancements in language technologies, humansare now interacting with technology through speech. To in-crease the reach of these technologies, we need to build suchsystems in local languages. A major bottleneck here are theunderlying data-intensive parts that make up such systems,including automatic speech recognition (ASR) systems thatrequire large amounts of labelled data. With the aim of aidingdevelopment of dialog systems in low resourced languages,we propose a novel acoustics based intent recognition systemthat uses discovered phonetic units for intent classification.The system is made up of two blocks - the first block gen-erates a transcript of discovered phonetic units for the inputaudio, and the second block which performs intent classifi-cation from the generated phonemic transcripts. Our workpresents results for such a system for two languages families- Indic languages and Romance languages, for two differentintent recognition tasks. We also perform multilingual train-ing of our intent classifier and show improved cross-lingualtransfer and performance on an unknown language with zeroresources in the same language family.

Target-driven visual navigation is a challenging problem that requires a robot to find the goal using only visual inputs. Many researchers have demonstrated promising results using deep reinforcement learning (deep RL) on various robotic platforms, but typical end-to-end learning is known for its poor extrapolation capability to new scenarios. Therefore, learning a navigation policy for a new robot with a new sensor configuration or a new target still remains a challenging problem. In this paper, we introduce a learning algorithm that enables rapid adaptation to new sensor configurations or target objects with a few shots. We design a policy architecture with latent features between perception and inference networks and quickly adapt the perception network via meta-learning while freezing the inference network. Our experiments show that our algorithm adapts the learned navigation policy with only three shots for unseen situations with different sensor configurations or different target colors. We also analyze the proposed algorithm by investigating various hyperparameters.

We demonstrate a deep learning framework which is inherently based in the highly expressive language of relational logic, enabling to, among other things, capture arbitrarily complex graph structures. We show how Graph Neural Networks and similar models can be easily covered in the framework by specifying the underlying propagation rules in the relational logic. The declarative nature of the used language then allows to easily modify and extend the propagation schemes into complex structures, such as the molecular rings which we choose for a short demonstration in this paper.

To prevent the leakage of private information while enabling automated machine intelligence, there is an emerging trend to integrate federated learning and Neural Architecture Search (NAS). Although promising as it may seem, the coupling of difficulties from both two tenets makes the algorithm development quite challenging. In particular, how to efficiently search the optimal neural architecture directly from massive non-iid data of clients in a federated manner remains to be a hard nut to crack. To tackle this challenge, in this paper, by leveraging the advances in proxy-less NAS, we propose a Federated Direct Neural Architecture Search (FDNAS) framework that allows hardware-aware NAS from decentralized non-iid data of clients. To further adapt for various data distributions of clients, inspired by meta-learning, a cluster Federated Direct Neural Architecture Search (CFDNAS) framework is proposed to achieve client-aware NAS, in the sense that each client can learn a tailored deep learning model for its particular data distribution. Extensive experiments on real-world non-iid datasets show state-of-the-art accuracy-efficiency trade-offs for various hardware and data distributions of clients. Our codes will be released publicly upon paper acceptance.