Sourav Das

Luigi Filippo Chiara, Pasquale Coscia, Sourav Das et al.

Human trajectory forecasting is a key component of autonomous vehicles, social-aware robots and advanced video-surveillance applications. This challenging task typically requires knowledge about past motion, the environment and likely destination areas. In this context, multi-modality is a fundamental aspect and its effective modeling can be beneficial to any architecture. Inferring accurate trajectories is nevertheless challenging, due to the inherently uncertain nature of the future. To overcome these difficulties, recent models use different inputs and propose to model human intentions using complex fusion mechanisms. In this respect, we propose a lightweight attention-based recurrent backbone that acts solely on past observed positions. Although this backbone already provides promising results, we demonstrate that its prediction accuracy can be improved considerably when combined with a scene-aware goal-estimation module. To this end, we employ a common goal module, based on a U-Net architecture, which additionally extracts semantic information to predict scene-compliant destinations. We conduct extensive experiments on publicly-available datasets (i.e. SDD, inD, ETH/UCY) and show that our approach performs on par with state-of-the-art techniques while reducing model complexity.

Sourav Das, Anup Kumar Kolya

With the ever-increasing number of digital music and vast music track features through popular online music streaming software and apps, feature recognition using the neural network is being used for experimentation to produce a wide range of results across a variety of experiments recently. Through this work, the authors extract information on such features from a popular open-source music corpus and explored new recognition techniques, by applying unsupervised Hebbian learning techniques on their single-layer neural network using the same dataset. The authors show the detailed empirical findings to simulate how such an algorithm can help a single layer feedforward network in training for music feature learning as patterns. The unsupervised training algorithm enhances their proposed neural network to achieve an accuracy of 90.36% for successful music feature detection. For comparative analysis against similar tasks, authors put their results with the likes of several previous benchmark works. They further discuss the limitations and thorough error analysis of their work. The authors hope to discover and gather new information about this particular classification technique and its performance, and further understand future potential directions and prospects that could improve the art of computational music feature recognition.

Sourav Das, Guglielmo Camporese, Shaokang Cheng et al.

Long-term trajectory forecasting is an important and challenging problem in the fields of computer vision, machine learning, and robotics. One fundamental difficulty stands in the evolution of the trajectory that becomes more and more uncertain and unpredictable as the time horizon grows, subsequently increasing the complexity of the problem. To overcome this issue, in this paper, we propose Di-Long, a new method that employs the distillation of a short-term trajectory model forecaster that guides a student network for long-term trajectory prediction during the training process. Given a total sequence length that comprehends the allowed observation for the student network and the complementary target sequence, we let the student and the teacher solve two different related tasks defined over the same full trajectory: the student observes a short sequence and predicts a long trajectory, whereas the teacher observes a longer sequence and predicts the remaining short target trajectory. The teacher's task is less uncertain, and we use its accurate predictions to guide the student through our knowledge distillation framework, reducing long-term future uncertainty. Our experiments show that our proposed Di-Long method is effective for long-term forecasting and achieves state-of-the-art performance on the Intersection Drone Dataset (inD) and the Stanford Drone Dataset (SDD).

Conor O'Brien, Arvind Thiagarajan, Sourav Das et al.

Online advertising has typically been more personalized than offline advertising, through the use of machine learning models and real-time auctions for ad targeting. One specific task, predicting the likelihood of conversion (i.e.\ the probability a user will purchase the advertised product), is crucial to the advertising ecosystem for both targeting and pricing ads. Currently, these models are often trained by observing individual user behavior, but, increasingly, regulatory and technical constraints are requiring privacy-preserving approaches. For example, major platforms are moving to restrict tracking individual user events across multiple applications, and governments around the world have shown steadily more interest in regulating the use of personal data. Instead of receiving data about individual user behavior, advertisers may receive privacy-preserving feedback, such as the number of installs of an advertised app that resulted from a group of users. In this paper we outline the recent privacy-related changes in the online advertising ecosystem from a machine learning perspective. We provide an overview of the challenges and constraints when learning conversion models in this setting. We introduce a novel approach for training these models that makes use of post-ranking signals. We show using offline experiments on real world data that it outperforms a model relying on opt-in data alone, and significantly reduces model degradation when no individual labels are available. Finally, we discuss future directions for research in this evolving area.

Sourav Das, Nitin Awathare, Ling Ren et al.

Proof-of-Work~(PoW) based blockchains typically allocate only a tiny fraction (e.g., less than 1% for Ethereum) of the average interarrival time~($\mathbb{I}$) between blocks for validating transactions. A trivial increase in validation time~($τ$) introduces the popularly known Verifier's Dilemma, and as we demonstrate, causes more forking and increases unfairness. Large $τ$ also reduces the tolerance for safety against a Byzantine adversary. Solutions that offload validation to a set of non-chain nodes (a.k.a. off-chain approaches) suffer from trust issues that are non-trivial to resolve. In this paper, we present Tuxedo, the first on-chain protocol to theoretically scale $τ/\mathbb{I} \approx 1$ in PoW blockchains. The key innovation in Tuxedo is to separate the consensus on the ordering of transactions from their execution. We achieve this by allowing miners to delay validation of transactions in a block by up to $ζ$ blocks, where $ζ$ is a system parameter. We perform security analysis of Tuxedo considering all possible adversarial strategies in a synchronous network with end-to-end delay $Δ$ and demonstrate that Tuxedo achieves security equivalent to known results for longest chain PoW Nakamoto consensus. Additionally, we also suggest a principled approach for practical choices of parameter $ζ$ as per the application requirement. Our prototype implementation of Tuxedo atop Ethereum demonstrates that it can scale $τ$ without suffering the harmful effects of naive scaling in existing blockchains.