Challenges and evolution of Alexa Text-To-Speech<\/strong>
Adam Furmanek, Senior Software Engineer <\/span><\/span> (Amazon)<\/span>\n <\/p>\n

Abstract:<\/strong> It was quite a hike to deliver a first world-class voice assistant, but nowadays it is common to control computers with your voice. What about the future? What else is there in the world of Text-To-Speech? In this talk we are going to see what challenges Alexa TTS is facing now. We\u2019ll go through the history of TTS, technical solutions, and then focus on what future brings. We\u2019ll focus on both technical and business problems we\u2019re solving now, and how these things will affect our lives.
<\/span><\/p>\n

Speaker's bio: <\/strong>Adam Furmanek is a Senior Software Engineer at Alexa. He works on the backend side of Alexa Text-To-Speech. He specializes in machine learning and large scale distributed systems. In his free time, he watches The Office and plays piano.<\/span><\/span>\n <\/p>\n

 <\/p>\n <\/div>\n <\/li>\n

Interactive sequential analysis of a model improves the performance of human decision-making<\/strong>
<\/span>Hubert Baniecki (University of Warsaw<\/span>)<\/span><\/span>\n <\/p>\n

Evaluation of explainable machine learning, especially with human subjects, became mandatory for the trustworthy adoption of predictive models in various applications. This contribution focuses on reporting the results from a user study considering evaluating model explanations in a real-world medical use case; as described in Section 5 of the paper: <\/span>Baniecki, D. Parzych, P. Biecek. The Grammar of Interactive Explanatory Model Analysis, 2022 (https:\/\/arxiv.org\/abs\/2005.00497v4). The contribution's title is mainly supported by Tables 4 & 5. Moreover, we find both: the user study design and the IEMA grammar's theoretical background worth discussing.<\/span><\/span>\n <\/p>\n

 <\/p>\n

Lightweight Conditional Model Extrapolation for Streaming Data under Class Prior Shift (LIMES)<\/span><\/span>\n <\/strong>
Paulina Tomaszewska (Warsaw University of Technology)<\/span><\/span>\n <\/p>\n

Many Machine Learning models don\u2019t work well under large class imbalance. The problem gets even more difficult when the class distribution changes over time. It may happen in non-stationary data streams. <\/span>We address this issue in the proposed method called LIMES which stands for Lightweight Model Extrapolation for Streaming data under Class-Prior Shift. The model works in a continuous manner. It is lightweight as it adds no trainable parameters and almost no memory or computational overhead compared to training a single model. <\/span>The solution is inspired by the MAML network where one model that can be easily adjusted to different scenarios. In the case of MAML, the adaptation is done using few gradient updates, in the case of LIMES, we apply analytical formula derived from the Bayesian rule. The core of the method is bias correction term that allows to shift from the reference class distribution to the target one. At this point, the extrapolation step is also needed in the case when the exact target class distribution is not a priori known. <\/span>We evaluated our method on Twitter data where the goal was to find out the country where the tweet was issued. The results that we got show that LIMES outperforms baselines especially in the most difficult scenarios.<\/span><\/p>\n <\/div>\n <\/li>\n

Introduction and analyzing of Diffusion-based Deep Generative Models<\/strong>
<\/span>Kamil Deja (Warsaw University of Technology<\/span>)<\/span><\/span>\n <\/p>\n

Diffusion-based Deep Generative Models (DDGMs) offer state-of-the-art performance in generative modeling. Their main strength comes from their unique setup in which a model (the backward diffusion process) is trained to reverse the forward diffusion process, which gradually adds noise to the input signal. Although DDGMs are well studied, it is still unclear how the small amount of noise is transformed during the backward diffusion process. In this talk we will introduce the general idea behind Diffusion-based generative models while focusing on denoising and generative capabilities of those models. We observe a fluid transition point that changes the functionality of the backward diffusion process from generating a (corrupted) image from noise to denoising the corrupted image to the final sample. Based on this observation, we postulate to divide a DDGM into two parts: a denoiser and a generator. The denoiser could be parameterized by a denoising auto-encoder, while the generator is a diffusion-based model with its own set of parameters. We experimentally validate our proposition, showing its pros and cons.
<\/span><\/p>\n

 <\/p>\n

Session-aware Graph Neural Network-based Recommendations for Custom Advertisement Segment Generation Focused on Game players (remote)<\/strong>
<\/span>Tomasz Palczewski (Samsung Research America)<\/span><\/span>\n <\/p>\n

Recommendation engines are commonly used across a broad range of verticals. One can find these solutions in e-commerce, advertisement, marketing, news, on TVs, and within streaming service content. They are extremely important to keep a high-level user engagement when users face an overwhelming number of items that can be potentially presented to them. In general, recommendation systems can be divided into two groups - 1) systems built on general interaction information and 2) systems built on sequential interaction data. As the field has progressed, the research has revolved around expanding both groups to include different types of auxiliary information. The sequence-based recommendation systems can be categorized as session-based solutions that rely on the user's actions in the current sessions. The session-aware recommendation systems also leverage user information in the historical sessions. In this paper, we propose a novel Session-awaRe grAph Neural Network-based Recommendation model (called SRA-NN-Rec for brevity) and test it using publicly available datasets as well as present its usefulness in a real-word case for custom advertisement segment generation focused on game players. The key components of SRA-NN-Rec are: 1) a graph neural network that consumes user and session information, 2) a self-attention network to enhance item embeddings based on session data, and 3) an attention network. The experiment results show that the SRA-NN-Rec outperforms the existing baseline models and is an effective model for session-aware recommendations.<\/span><\/p>\n <\/div>\n <\/li>\n

This event will see a discussion on participants\u2019 research topics, their career paths and their views on current ML trends.<\/span><\/p>\n

Panelists: <\/span>Farah Shamout (NYU Abu Dhabi) , Inez Okulska (NASK National Research Institute), Aga Dobrowolska (<\/span>Relation Therapeutics), Daria Szmurlo (QuantumBlack, AI by McKinsey)<\/span> <\/span>\n <\/p>\n <\/div>\n <\/li>\n

Improved Feature Importance Computation for Tree Models Based on the Banzhaf<\/span><\/strong>Value
<\/strong>Piotr Sankowski (IDEAS NCBR, MIM Solutions and University of Warsaw<\/span>)<\/span><\/span>\n <\/p>\n

The Shapley value -- a fundamental game-theoretic solution concept -- has recently become one of the main tools used to explain predictions of tree ensemble models. Another well-known game-theoretic solution concept is the Banzhaf value. Although the Banzhaf value is closely related to the Shapley value, its properties w.r.t. feature attribution have not been understood equally well. This paper shows that, for tree ensemble models, the Banzhaf value offers some crucial advantages over the Shapley value while providing similar feature attributions.<\/span><\/p>\n

In particular, we first give an optimal O(TL+n) time algorithm for computing the Banzhaf value-based attribution of a tree ensemble model's output. Here, T is the number of trees, L is the maximum number of leaves in a tree, and n is the number of features. In comparison, the state-of-the-art Shapley value-based algorithm runs in O(TLD^2+n) time, where D denotes the maximum depth of a tree in the ensemble.<\/span><\/p>\n

Next, we experimentally compare the Banzhaf and Shapley values for tree ensemble models. Both methods deliver essentially the same average importance scores for the studied datasets using two different tree ensemble models (the sklearn implementation of Decision Trees or xgboost implementation of Gradient Boosting Decision Trees). However, our results indicate that, on top of being computable faster, the Banzhaf is more numerically robust than the Shapley value.
<\/span><\/p>\n

 <\/p>\n

Interpretable Deep Learning with Prototypes<\/strong>
<\/span>Bartosz Zieli\u0144ski (<\/span>IDEAS, Jagiellonian University<\/span>)<\/span><\/span>\n <\/p>\n

The broad application of deep learning in fields like medical diagnosis and autonomous driving enforces models to explain the rationale behind their decisions. That is why explainers and self-explainable models are developed to justify neural network predictions. Some of them are inspired by mechanisms used by humans to explain their decisions, like matching image parts with memorized prototypical features that an object can possess. Recently, a self-explainable model called Prototypical Part Network (ProtoPNet) was introduced, employing feature matching learning theory. It focuses on crucial image parts and compares them with reference patterns (prototypical parts) assigned to classes.<\/span><\/p>\n

In this presentation, we will present our papers concerning this topic published on the main track of three recent conferences (SIGKDD 2021, ECML PKDD 2022, and ECCV 2022). They discuss the topic of prototype sharing between classes and their adaptation to the weakly-supervised setting.
<\/span><\/p>\n

 <\/p>\n

Fine-Grained Conditional Computation in Transformers<\/strong>
<\/span>Sebastian Jaszczur (IDEAS NCBR, University of Warsaw<\/span>)<\/span><\/span>\n <\/p>\n

Large Transformer models yield impressive results on many tasks, but are expensive to train, or even fine-tune, and so slow at decoding that the use and study of the largest models becomes out of reach for many researchers and end-users. Conditional computation, or sparsity, may help alleviate those problems.<\/span><\/p>\n

In my work \"Sparse is Enough in Scaling Transformers\", done at Google Research and published at NeurIPS 2021, we showed that sparse layers leveraging fine-grained conditional computation can enable Transformers to scale efficiently and perform unbatched decoding much faster than standard Transformer. Importantly, in contrast to standard Mixture-of-Expert methods, this fine-grained sparsity achieves the speed-up without decreasing the model quality, and with the same number of model parameters.<\/span><\/p>\n

My current work on this topic, done at IDEAS NCBR, focuses on adjusting those conditional computation methods to the training environment, with the goal of speeding up the training process as well as the inference. This can be achieved by a careful redesign of fine-grained conditional computation while using only dense tensor operations, which are efficient on modern accelerators. While this is still an ongoing work, the preliminary results show the promise of improving the training speed of Transformers on existing hardware, without degrading the quality of the model's predictions.<\/span><\/p>\n <\/div>\n <\/li>\n

Experimental Evaluation of Fictitious Self-play Algorithm in Unity Dodgeball Environment<\/strong>
<\/span>Jacek Cyranka (University of Warsaw<\/span>)<\/span><\/span>\n <\/p>\n

We introduce the generalized fictitious co-play algorithm (GFCP) for team video games. Our algorithm constitutes two phases and can be applied on top of any multi-agent RL training procedure in a setting of a simultaneous team game. First, a pool of checkpoints is trained using a vanilla self-play algorithm. Second, further training is carried out via fictitious co-play, i.e., setting one of the agents to inference mode and sampling previously frozen checkpoints. We evaluate our algorithm in the Unity Dodgeball elimination 4vs4 environment. The experiments show the favorable properties of GFCP agents in terms of win rate when matched with weaker checkpoints and previously unseen checkpoints that were not used for the training. On top of that, we evaluate the capability of the GFCP agents to match in a team with human players within a hand-crafted computer game built in the Unity environment.
<\/span><\/p>\n

 <\/p>\n

Fast and Precise: Adjusting Planning Horizon with Adaptive Subgoal Search<\/strong>
<\/span>Micha\u0142 Tyrolski (University of Warsaw<\/span>)<\/span><\/span>\n <\/p>\n

Complex reasoning problems contain states that vary in the computational cost required to determine a good action plan. Taking advantage of this property, we propose Adaptive Subgoal Search (AdaSubS), a search method that adaptively adjusts the planning horizon. To this end, AdaSubS generates diverse sets of subgoals at different distances. A verification mechanism is employed to filter out unreachable subgoals swiftly and thus allowing to focus on feasible further subgoals. In this way, AdaSubS benefits from the efficiency of planning with longer subgoals and the fine control with the shorter ones. We show that AdaSubS significantly surpasses hierarchical planning algorithms on three complex reasoning tasks: Sokoban, the Rubik's Cube, and inequality proving benchmark INT, setting new state-of-the-art on INT.
<\/span><\/p>\n

 <\/p>\n

Reinforcement learning in Datacenters<\/strong>
<\/span>Alessandro Seganti (Equinix<\/span>)<\/span><\/span>\n <\/p>\n

Did you know that datacenters are a highly controlled environment? That inside a datacenter we have thousands of PID controllers that are automating every aspect of the functioning? This together with Equinix expertise, allows our datacenters to operate without flaws (99.9999% uptime record).<\/span><\/p>\n

In our presentation we share our experience in using reinforcement learning in a datacenter. Hopefully by the end of the presentation you will learn what are the challenges and advantages of using reinforcement learning in a real world scenario.<\/span><\/p>\n

During this presentation we will show how data centers are controlled. We will also introduce you to the kind of data we are using and how we are processing it. Then we will explain how we used reinforcement learning to improve the energy efficiency of a simulated datacenter. Finally we will show how our experiments and models have been used in real use cases inside the company.<\/span><\/p>\n <\/div>\n <\/li>\n