arXiv subjects

Jaspreet Singh

Publications and source records attributed to Jaspreet Singh.

At least 37 records · Page 2Linked to original sources

arXiv2021

An L-class Multirole Observatory and Science Platform for Neptune

A coming resurgence of super heavy-lift launch vehicles has precipitated an immense interest in the future of crewed spaceflight and even future colonisation efforts. While it is true that a bright future awaits this sector, driven by commercial ventures and the reignited interest of old space-faring nations, and the joining of new ones, little of this attention has been reserved for the science-centric applications of these launchers. The Arcanum mission is a proposal to use these vehicles to deliver an L-class observatory into a highly eccentric orbit around Neptune, with a wide-ranging suite of science goals and instrumentation tackling Solar System science, planetary science, Kuiper Belt Objects and exoplanet systems.

astro-ph.IM↗

arXiv2021

Bacterial activity hinders particle sedimentation

Sedimentation in active fluids has come into focus due to the ubiquity of swimming micro-organisms in natural and industrial processes. Here, we investigate sedimentation dynamics of passive particles in a fluid as a function of bacteria E. coli concentration. Results show that the presence of swimming bacteria significantly reduces the speed of the sedimentation front even in the dilute regime, in which the sedimentation speed is expected to be independent of particle concentration. Furthermore, bacteria increase the dispersion of the passive particles, which determines the width of the sedimentation front. For short times, particle sedimentation speed has a linear dependence on bacterial concentration. Mean square displacement data shows, however, that bacterial activity decays over long experimental (sedimentation) times. An advection-diffusion equation coupled to bacteria population dynamics seems to capture concentration profiles relatively well. A single parameter, the ratio of single particle speed to the bacteria flow speed can be used to predict front sedimentation speed.

physics.flu-dyn↗

arXiv2021

Dissonance Between Human and Machine Understanding

Complex machine learning models are deployed in several critical domains including healthcare and autonomous vehicles nowadays, albeit as functional black boxes. Consequently, there has been a recent surge in interpreting decisions of such complex models in order to explain their actions to humans. Models that correspond to human interpretation of a task are more desirable in certain contexts and can help attribute liability, build trust, expose biases and in turn build better models. It is, therefore, crucial to understand how and which models conform to human understanding of tasks. In this paper, we present a large-scale crowdsourcing study that reveals and quantifies the dissonance between human and machine understanding, through the lens of an image classification task. In particular, we seek to answer the following questions: Which (well-performing) complex ML models are closer to humans in their use of features to make accurate predictions? How does task difficulty affect the feature selection capability of machines in comparison to humans? Are humans consistently better at selecting features that make image recognition more accurate? Our findings have important implications on human-machine collaboration, considering that a long term goal in the field of artificial intelligence is to make machines capable of learning and reasoning like humans.

cs.AI↗

arXiv2020

Five-Layers SDP-Based Hierarchical Security Paradigm for Multi-access Edge Computing

The rise in embedded and IoT device usage comes with an increase in LTE usage as well. About 70\% of an estimated 18 billion IoT devices will be using cellular LTE networks for efficient connections. This introduces several challenges such as security, latency, scalability, and quality of service, for which reason Edge Computing or Fog Computing has been introduced. The edge is capable of offloading resources to the edge to reduce workload at the cloud. Several security challenges come with Multi-access Edge Computing (MEC) such as location-based attacks, the man in the middle attacks, and sniffing. This paper proposes a Software-Defined Perimeter (SDP) framework to supplement MEC and provide added security. The SDP is capable of protecting the cloud from the edge by only authorizing authenticated users at the edge to access services in the cloud. The SDP is implemented within a Mobile Edge LTE network. Delay analysis of the implementation is performed, followed by a DoS attack to demonstrate the resilience of the proposed SDP. Further analyses such as CPU usage and Port Scanning were performed to verify the efficiency of the proposed SDP. This analysis is followed by concluding remarks with insight into the future of the SDP in MEC.

cs.NI↗

arXiv2020

Valid Explanations for Learning to Rank Models

Learning-to-rank (LTR) is a class of supervised learning techniques that apply to ranking problems dealing with a large number of features. The popularity and widespread application of LTR models in prioritizing information in a variety of domains makes their scrutability vital in today's landscape of fair and transparent learning systems. However, limited work exists that deals with interpreting the decisions of learning systems that output rankings. In this paper we propose a model agnostic local explanation method that seeks to identify a small subset of input features as explanation to a ranking decision. We introduce new notions of validity and completeness of explanations specifically for rankings, based on the presence or absence of selected features, as a way of measuring goodness. We devise a novel optimization problem to maximize validity directly and propose greedy algorithms as solutions. In extensive quantitative experiments we show that our approach outperforms other model agnostic explanation approaches across pointwise, pairwise and listwise LTR models in validity while not compromising on completeness.

cs.LG↗

arXiv2019

AMUSED: A Multi-Stream Vector Representation Method for Use in Natural Dialogue

The problem of building a coherent and non-monotonous conversational agent with proper discourse and coverage is still an area of open research. Current architectures only take care of semantic and contextual information for a given query and fail to completely account for syntactic and external knowledge which are crucial for generating responses in a chit-chat system. To overcome this problem, we propose an end to end multi-stream deep learning architecture which learns unified embeddings for query-response pairs by leveraging contextual information from memory networks and syntactic information by incorporating Graph Convolution Networks (GCN) over their dependency parse. A stream of this network also utilizes transfer learning by pre-training a bidirectional transformer to extract semantic representation for each input sentence and incorporates external knowledge through the the neighborhood of the entities from a Knowledge Base (KB). We benchmark these embeddings on next sentence prediction task and significantly improve upon the existing techniques. Furthermore, we use AMUSED to represent query and responses along with its context to develop a retrieval based conversational agent which has been validated by expert linguists to have comprehensive engagement with humans.

cs.CL↗

arXiv2019

Toxicity Prediction by Multimodal Deep Learning

Prediction of toxicity levels of chemical compounds is an important issue in Quantitative Structure-Activity Relationship (QSAR) modeling. Although toxicity prediction has achieved significant progress in recent times through deep learning, prediction accuracy levels obtained by even very recent methods are not yet very high. We propose a multimodal deep learning method using multiple heterogeneous neural network types and data representations. We represent chemical compounds by strings, images, and numerical features. We train fully connected, convolutional, and recurrent neural networks and their ensembles. Each data representation or neural network type has its own strengths and weaknesses. Our motivation is to obtain a collective performance that could go beyond individual performance of each data representation or each neural network type. On a standard toxicity benchmark, our proposed method obtains significantly better accuracy levels than that by the state-of-the-art toxicity prediction methods.

cs.LG↗

arXiv2019

A study on the Interpretability of Neural Retrieval Models using DeepSHAP

A recent trend in IR has been the usage of neural networks to learn retrieval models for text based adhoc search. While various approaches and architectures have yielded significantly better performance than traditional retrieval models such as BM25, it is still difficult to understand exactly why a document is relevant to a query. In the ML community several approaches for explaining decisions made by deep neural networks have been proposed -- including DeepSHAP which modifies the DeepLift algorithm to estimate the relative importance (shapley values) of input features for a given decision by comparing the activations in the network for a given image against the activations caused by a reference input. In image classification, the reference input tends to be a plain black image. While DeepSHAP has been well studied for image classification tasks, it remains to be seen how we can adapt it to explain the output of Neural Retrieval Models (NRMs). In particular, what is a good "black" image in the context of IR? In this paper we explored various reference input document construction techniques. Additionally, we compared the explanations generated by DeepSHAP to LIME (a model agnostic approach) and found that the explanations differ considerably. Our study raises concerns regarding the robustness and accuracy of explanations produced for NRMs. With this paper we aim to shed light on interesting problems surrounding interpretability in NRMs and highlight areas of future work.

cs.IR↗

arXiv2018

Asynchronous Training of Word Embeddings for Large Text Corpora

Word embeddings are a powerful approach for analyzing language and have been widely popular in numerous tasks in information retrieval and text mining. Training embeddings over huge corpora is computationally expensive because the input is typically sequentially processed and parameters are synchronously updated. Distributed architectures for asynchronous training that have been proposed either focus on scaling vocabulary sizes and dimensionality or suffer from expensive synchronization latencies. In this paper, we propose a scalable approach to train word embeddings by partitioning the input space instead in order to scale to massive text corpora while not sacrificing the performance of the embeddings. Our training procedure does not involve any parameter synchronization except a final sub-model merge phase that typically executes in a few minutes. Our distributed training scales seamlessly to large corpus sizes and we get comparable and sometimes even up to 45% performance improvement in a variety of NLP benchmarks using models trained by our distributed procedure which requires $1/10$ of the time taken by the baseline approach. Finally we also show that we are robust to missing words in sub-models and are able to effectively reconstruct word representations.

cs.LG↗

arXiv2018

Expedition: A Time-Aware Exploratory Search System Designed for Scholars

Archives are an important source of study for various scholars. Digitization and the web have made archives more accessible and led to the development of several time-aware exploratory search systems. However these systems have been designed for more general users rather than scholars. Scholars have more complex information needs in comparison to general users. They also require support for corpus creation during their exploration process. In this paper we present Expedition - a time-aware exploratory search system that addresses the requirements and information needs of scholars. Expedition possesses a suite of ad-hoc and diversity based retrieval models to address complex information needs; a newspaper-style user interface to allow for larger textual previews and comparisons; entity filters to more naturally refine a result list and an interactive annotated timeline which can be used to better identify periods of importance.

cs.IR↗

arXiv2018

History by Diversity: Helping Historians search News Archives

Longitudinal corpora like newspaper archives are of immense value to historical research, and time as an important factor for historians strongly influences their search behaviour in these archives. While searching for articles published over time, a key preference is to retrieve documents which cover the important aspects from important points in time which is different from standard search behavior. To support this search strategy, we introduce the notion of a Historical Query Intent to explicitly model a historian's search task and define an aspect-time diversification problem over news archives. We present a novel algorithm, HistDiv, that explicitly models the aspects and important time windows based on a historian's information seeking behavior. By incorporating temporal priors based on publication times and temporal expressions, we diversify both on the aspect and temporal dimensions. We test our methods by constructing a test collection based on The New York Times Collection with a workload of 30 queries of historical intent assessed manually. We find that HistDiv outperforms all competitors in subtopic recall with a slight loss in precision. We also present results of a qualitative user study to determine wether this drop in precision is detrimental to user experience. Our results show that users still preferred HistDiv's ranking.

cs.IR↗

arXiv2018

Discovering Entities with Just a Little Help from You

Linking entities like people, organizations, books, music groups and their songs in text to knowledge bases (KBs) is a fundamental task for many downstream search and mining applications. Achieving high disambiguation accuracy crucially depends on a rich and holistic representation of the entities in the KB. For popular entities, such a representation can be easily mined from Wikipedia, and many current entity disambiguation and linking methods make use of this fact. However, Wikipedia does not contain long-tail entities that only few people are interested in, and also at times lags behind until newly emerging entities are added. For such entities, mining a suitable representation in a fully automated fashion is very difficult, resulting in poor linking accuracy. What can automatically be mined, though, is a high-quality representation given the context of a new entity occurring in any text. Due to the lack of knowledge about the entity, no method can retrieve these occurrences automatically with high precision, resulting in a chicken-egg problem. To address this, our approach automatically generates candidate occurrences of entities, prompting the user for feedback to decide if the occurrence refers to the actual entity in question. This feedback gradually improves the knowledge and allows our methods to provide better candidate suggestions to keep the user engaged. We propose novel human-in-the-loop retrieval methods for generating candidates based on gradient interleaving of diversification and textual relevance approaches. We conducted extensive experiments on the FACC dataset, showing that our approaches convincingly outperform carefully selected baselines in both intrinsic and extrinsic measures while keeping users engaged.

cs.IR↗

arXiv2018

Designing Search Tasks for Archive Search

Longitudinal corpora like legal, corporate and newspaper archives are of immense value to a variety of users, and time as an important factor strongly influences their search behavior in these archives. While many systems have been developed to support users temporal information needs, questions remain over how users utilize these advances to satisfy their needs. Analyzing their search behavior will provide us with novel insights into search strategy, guide better interface and system design and highlight new problems for further research. In this paper we propose a set of search tasks, with varying complexity, that IIR researchers can utilize to study user search behavior in archives. We discuss how we created and refined these tasks as the result of a pilot study using a temporal search engine. We not only propose task descriptions but also pre and post-task evaluation mechanisms that can be employed for a large-scale study (crowdsourcing). Our initial findings show the viability of such tasks for investigating search behavior in archives.

cs.IR↗

arXiv2018

Interpreting search result rankings through intent modeling

Given the recent interest in arguably accurate yet non-interpretable neural models, even with textual features, for document ranking we try to answer questions relating to how to interpret rankings. In this paper we take first steps towards a framework for the interpretability of retrieval models with the aim of answering 3 main questions "What is the intent of the query according to the ranker?", "Why is a document ranked higher than another for the query?" and "Why is a document relevant to the query?" Our framework is predicated on the assumption that text based retrieval model behavior can be estimated using query expansions in conjunction with a simpler retrieval model irrespective of the underlying ranker. We conducted experiments with the Clueweb test collection. We show how our approach performs for both simpler models with a closed form notation (which allows us to measure the accuracy of the interpretation) and neural ranking models. Our results indicate that we can indeed interpret more complex models with reasonable accuracy under certain simplifying assumptions. In a case study we also show our framework can be employed to interpret the results of the DRMM neural retrieval model in various scenarios.

cs.IR↗

arXiv2018

EXS: Explainable Search Using Local Model Agnostic Interpretability

Retrieval models in information retrieval are used to rank documents for typically under-specified queries. Today machine learning is used to learn retrieval models from click logs and/or relevance judgments that maximizes an objective correlated with user satisfaction. As these models become increasingly powerful and sophisticated, they also become harder to understand. Consequently, it is hard for to identify artifacts in training, data specific biases and intents from a complex trained model like neural rankers even if trained purely on text features. EXS is a search system designed specifically to provide its users with insight into the following questions: `What is the intent of the query according to the ranker?', `Why is this document ranked higher than another?' and `Why is this document relevant to the query?'. EXS uses a version of a popular posthoc explanation method for classifiers -- LIME, adapted specifically to answer these questions. We show how such a system can effectively help a user understand the results of neural rankers and highlight areas of improvement.

cs.IR↗

arXiv2018

Posthoc Interpretability of Learning to Rank Models using Secondary Training Data

Predictive models are omnipresent in automated and assisted decision making scenarios. But for the most part they are used as black boxes which output a prediction without understanding partially or even completely how different features influence the model prediction avoiding algorithmic transparency. Rankings are ordering over items encoding implicit comparisons typically learned using a family of features using learning-to-rank models. In this paper we focus on how best we can understand the decisions made by a ranker in a post-hoc model agnostic manner. We operate on the notion of interpretability based on explainability of rankings over an interpretable feature space. Furthermore we train a tree based model (inherently interpretable) using labels from the ranker, called secondary training data to provide explanations. Consequently, we attempt to study how well does a subset of features, potentially interpretable, explain the full model under different training sizes and algorithms. We do experiments on the learning to rank datasets with 30k queries and report results that serve show in certain settings we can learn a faithful interpretable ranker.

cs.IR↗

arXiv2018

Elasticity as the basis of allostery in DNA

Allosteric interactions in DNA are crucial for various biological processes. These interactions are quantified by measuring the change in free energy as a function of the distance between the binding sites for two ligands. Here we show that trends in the interaction energy of ligands binding to DNA can be explained within an elastic birod model. The birod model accounts for the deformation of each strand as well as the change in stacking energy due to perturbations in position and orientation of the bases caused by the binding of ligands. The strain fields produced by the ligands decay with distance from the binding site. The interaction energy of two ligands decays exponentially with the distance between them and oscillates with the periodicity of the double helix in quantitative agreement with experimental measurements. The trend in the computed interaction energy is similar to that in the perturbation of groove width produced by the binding of a single ligand which is consistent with molecular simulations. Our analysis provides a new framework to understand allosteric interactions in DNA and can be extended to other rod-like macromolecules whose elasticity plays a role in biological functions.

physics.bio-ph↗

arXiv2018

Allosteric interactions in a birod model of DNA

Allosteric interactions between molecules bound to DNA at distant locations have been known for a long time. The phenomenon has been studied via experiments and numerical simulations, but a comprehensive understanding grounded in a theory of DNA elasticity remains a challenge. Here we quantify allosteric interactions between two entities bound to DNA by using the theory of birods. We recognize that molecules bound to DNA cause local deformations that can be captured in a birod model which consists of two elastic strands interacting via an elastic web representing the base-pairs. We show that the displacement field caused by bound entities decays exponentially with distance from the binding site. We compute the interaction energy between two proteins on DNA as a function of distance between them and find that it decays exponentially while oscillating with the periodicity of the double-helix, in excellent agreement with experiments. The decay length of the interaction energy can be determined in terms of the mechanical properties of the strands and the webbing in our birod model, and it varies with the GC content of the DNA. Our model provides a framework for viewing allosteric interactions in DNA within the ambit of configurational forces of continuum elasticity.

cond-mat.soft↗