arXiv subjects

Srikanta Bedathur

Publications and source records attributed to Srikanta Bedathur.

At least 37 records · Page 2Linked to original sources

arXiv2022

Modeling Continuous Time Sequences with Intermittent Observations using Marked Temporal Point Processes

A large fraction of data generated via human activities such as online purchases, health records, spatial mobility etc. can be represented as a sequence of events over a continuous-time. Learning deep learning models over these continuous-time event sequences is a non-trivial task as it involves modeling the ever-increasing event timestamps, inter-event time gaps, event types, and the influences between different events within and across different sequences. In recent years neural enhancements to marked temporal point processes (MTPP) have emerged as a powerful framework to model the underlying generative mechanism of asynchronous events localized in continuous time. However, most existing models and inference methods in the MTPP framework consider only the complete observation scenario i.e. the event sequence being modeled is completely observed with no missing events -- an ideal setting that is rarely applicable in real-world applications. A recent line of work which considers missing events while training MTPP utilizes supervised learning techniques that require additional knowledge of missing or observed label for each event in a sequence, which further restricts its practicability as in several scenarios the details of missing events is not known apriori. In this work, we provide a novel unsupervised model and inference method for learning MTPP in presence of event sequences with missing events. Specifically, we first model the generative processes of observed events and missing events using two MTPP, where the missing events are represented as latent random variables. Then, we devise an unsupervised training method that jointly learns both the MTPP by means of variational inference. Such a formulation can effectively impute the missing data among the observed events and can identify the optimal position of missing events in a sequence.

cs.LG↗

arXiv2022

Plug and Play Counterfactual Text Generation for Model Robustness

Generating counterfactual test-cases is an important backbone for testing NLP models and making them as robust and reliable as traditional software. In generating the test-cases, a desired property is the ability to control the test-case generation in a flexible manner to test for a large variety of failure cases and to explain and repair them in a targeted manner. In this direction, significant progress has been made in the prior works by manually writing rules for generating controlled counterfactuals. However, this approach requires heavy manual supervision and lacks the flexibility to easily introduce new controls. Motivated by the impressive flexibility of the plug-and-play approach of PPLM, we propose bringing the framework of plug-and-play to counterfactual test case generation task. We introduce CASPer, a plug-and-play counterfactual generation framework to generate test cases that satisfy goal attributes on demand. Our plug-and-play model can steer the test case generation process given any attribute model without requiring attribute-specific training of the model. In experiments, we show that CASPer effectively generates counterfactual text that follow the steering provided by an attribute model while also being fluent, diverse and preserving the original content. We also show that the generated counterfactuals from CASPer can be used for augmenting the training data and thereby fixing and making the test model more robust.

cs.CL↗

arXiv2022

TransDrift: Modeling Word-Embedding Drift using Transformer

In modern NLP applications, word embeddings are a crucial backbone that can be readily shared across a number of tasks. However as the text distributions change and word semantics evolve over time, the downstream applications using the embeddings can suffer if the word representations do not conform to the data drift. Thus, maintaining word embeddings to be consistent with the underlying data distribution is a key problem. In this work, we tackle this problem and propose TransDrift, a transformer-based prediction model for word embeddings. Leveraging the flexibility of transformer, our model accurately learns the dynamics of the embedding drift and predicts the future embedding. In experiments, we compare with existing methods and show that our model makes significantly more accurate predictions of the word embedding than the baselines. Crucially, by applying the predicted embeddings as a backbone for downstream classification tasks, we show that our embeddings lead to superior performance compared to the previous methods.

cs.CL↗

arXiv2022

ProActive: Self-Attentive Temporal Point Process Flows for Activity Sequences

Any human activity can be represented as a temporal sequence of actions performed to achieve a certain goal. Unlike machine-made time series, these action sequences are highly disparate as the time taken to finish a similar action might vary between different persons. Therefore, understanding the dynamics of these sequences is essential for many downstream tasks such as activity length prediction, goal prediction, etc. Existing neural approaches that model an activity sequence are either limited to visual data or are task specific, i.e., limited to next action or goal prediction. In this paper, we present ProActive, a neural marked temporal point process (MTPP) framework for modeling the continuous-time distribution of actions in an activity sequence while simultaneously addressing three high-impact problems -- next action prediction, sequence-goal prediction, and end-to-end sequence generation. Specifically, we utilize a self-attention module with temporal normalizing flows to model the influence and the inter-arrival times between actions in a sequence. Moreover, for time-sensitive prediction, we perform an early detection of sequence goal via a constrained margin-based optimization procedure. This in-turn allows ProActive to predict the sequence goal using a limited number of actions. Extensive experiments on sequences derived from three activity recognition datasets show the significant accuracy boost of ProActive over the state-of-the-art in terms of action and goal prediction, and the first-ever application of end-to-end action sequence generation.

cs.CV↗

arXiv2022

TIGGER: Scalable Generative Modelling for Temporal Interaction Graphs

There has been a recent surge in learning generative models for graphs. While impressive progress has been made on static graphs, work on generative modeling of temporal graphs is at a nascent stage with significant scope for improvement. First, existing generative models do not scale with either the time horizon or the number of nodes. Second, existing techniques are transductive in nature and thus do not facilitate knowledge transfer. Finally, due to relying on one-to-one node mapping from source to the generated graph, existing models leak node identity information and do not allow up-scaling/down-scaling the source graph size. In this paper, we bridge these gaps with a novel generative model called TIGGER. TIGGER derives its power through a combination of temporal point processes with auto-regressive modeling enabling both transductive and inductive variants. Through extensive experiments on real datasets, we establish TIGGER generates graphs of superior fidelity, while also being up to 3 orders of magnitude faster than the state-of-the-art.

cs.LG↗

arXiv2022

Learning Temporal Point Processes for Efficient Retrieval of Continuous Time Event Sequences

Recent developments in predictive modeling using marked temporal point processes (MTPP) have enabled an accurate characterization of several real-world applications involving continuous-time event sequences (CTESs). However, the retrieval problem of such sequences remains largely unaddressed in literature. To tackle this, we propose NEUROSEQRET which learns to retrieve and rank a relevant set of continuous-time event sequences for a given query sequence, from a large corpus of sequences. More specifically, NEUROSEQRET first applies a trainable unwarping function on the query sequence, which makes it comparable with corpus sequences, especially when a relevant query-corpus pair has individually different attributes. Next, it feeds the unwarped query sequence and the corpus sequence into MTPP guided neural relevance models. We develop two variants of the relevance model which offer a tradeoff between accuracy and efficiency. We also propose an optimization framework to learn binary sequence embeddings from the relevance scores, suitable for the locality-sensitive hashing leading to a significant speedup in returning top-K results for a given query sequence. Our experiments with several datasets show the significant accuracy boost of NEUROSEQRET beyond several baselines, as well as the efficacy of our hashing mechanism.

cs.IR↗

arXiv2022

Doing More with Less: Overcoming Data Scarcity for POI Recommendation via Cross-Region Transfer

Variability in social app usage across regions results in a high skew of the quantity and the quality of check-in data collected, which in turn is a challenge for effective location recommender systems. In this paper, we present Axolotl (Automated cross Location-network Transfer Learning), a novel method aimed at transferring location preference models learned in a data-rich region to significantly boost the quality of recommendations in a data-scarce region. Axolotl predominantly deploys two channels for information transfer, (1) a meta-learning based procedure learned using location recommendation as well as social predictions, and (2) a lightweight unsupervised cluster-based transfer across users and locations with similar preferences. Both of these work together synergistically to achieve improved accuracy of recommendations in data-scarce regions without any prerequisite of overlapping users and with minimal fine-tuning. We build Axolotl on top of a twin graph-attention neural network model used for capturing the user- and location-conditioned influences in a user-mobility graph for each region. We conduct extensive experiments on 12 user mobility datasets across the U.S., Japan, and Germany, using 3 as source regions and 9 of them (that have much sparsely recorded mobility data) as target regions. Empirically, we show that Axolotl achieves up to 18% better recommendation performance than the existing state-of-the-art methods across all metrics.

cs.LG↗

arXiv2021

VizAI : Selecting Accurate Visualizations of Numerical Data

A good data visualization is not only a distortion-free graphical representation of data but also a way to reveal underlying statistical properties of the data. Despite its common use across various stages of data analysis, selecting a good visualization often is a manual process involving many iterations. Recently there has been interest in reducing this effort by developing models that can recommend visualizations, but they are of limited use since they require large training samples (data and visualization pairs) and focus primarily on the design aspects rather than on assessing the effectiveness of the selected visualization. In this paper, we present VizAI, a generative-discriminative framework that first generates various statistical properties of the data from a number of alternative visualizations of the data. It is linked to a discriminative model that selects the visualization that best matches the true statistics of the data being visualized. VizAI can easily be trained with minimal supervision and adapts to settings with varying degrees of supervision easily. Using crowd-sourced judgements and a large repository of publicly available visualizations, we demonstrate that VizAI outperforms the state of the art methods that learn to recommend visualizations.

cs.HC↗

arXiv2021

Regex Queries over Incomplete Knowledge Bases

We propose the novel task of answering regular expression queries (containing disjunction ($\vee$) and Kleene plus ($+$) operators) over incomplete KBs. The answer set of these queries potentially has a large number of entities, hence previous works for single-hop queries in KBC that model a query as a point in high-dimensional space are not as effective. In response, we develop RotatE-Box -- a novel combination of RotatE and box embeddings. It can model more relational inference patterns compared to existing embedding based models. Furthermore, we define baseline approaches for embedding based KBC models to handle regex operators. We demonstrate performance of RotatE-Box on two new regex-query datasets introduced in this paper, including one where the queries are harvested based on actual user query logs. We find that our final RotatE-Box model significantly outperforms models based on just RotatE and just box embeddings.

cs.CL↗

arXiv2021

Region Invariant Normalizing Flows for Mobility Transfer

There exists a high variability in mobility data volumes across different regions, which deteriorates the performance of spatial recommender systems that rely on region-specific data. In this paper, we propose a novel transfer learning framework called REFORMD, for continuous-time location prediction for regions with sparse checkin data. Specifically, we model user-specific checkin-sequences in a region using a marked temporal point process (MTPP) with normalizing flows to learn the inter-checkin time and geo-distributions. Later, we transfer the model parameters of spatial and temporal flows trained on a data-rich origin region for the next check-in and time prediction in a target region with scarce checkin data. We capture the evolving region-specific checkin dynamics for MTPP and spatial-temporal flows by maximizing the joint likelihood of next checkin with three channels (1) checkin-category prediction, (2) checkin-time prediction, and (3) travel distance prediction. Extensive experiments on different user mobility datasets across the U.S. and Japan show that our model significantly outperforms state-of-the-art methods for modeling continuous-time sequences. Moreover, we also show that REFORMD can be easily adapted for product recommendations i.e., sequences without any spatial component.

cs.LG↗

arXiv2021

Computing and Maintaining Provenance of Query Result Probabilities in Uncertain Knowledge Graphs

Knowledge graphs (KG) that model the relationships between entities as labeled edges (or facts) in a graph are mostly constructed using a suite of automated extractors, thereby inherently leading to uncertainty in the extracted facts. Modeling the uncertainty as probabilistic confidence scores results in a probabilistic knowledge graph. Graph queries over such probabilistic KGs require answer computation along with the computation of those result probabilities, aka, probabilistic inference. We propose a system, HAPPI (How Provenance of Probabilistic Inference), to handle such query processing. Complying with the standard provenance semiring model, we propose a novel commutative semiring to symbolically compute the probability of the result of a query. These provenance-polynomiallike symbolic expressions encode fine-grained information about the probability computation process. We leverage this encoding to efficiently compute as well as maintain the probability of results as the underlying KG changes. Focusing on a popular class of conjunctive basic graph pattern queries on the KG, we compare the performance of HAPPI against a possible-world model of computation and a knowledge compilation tool over two large datasets. We also propose an adaptive system that leverages the strengths of both HAPPI and compilation based techniques. Since existing systems for probabilistic databases mostly focus on query computation, they default to re-computation when facts in the KG are updated. HAPPI, on the other hand, does not just perform probabilistic inference and maintain their provenance, but also provides a mechanism to incrementally maintain them as the KG changes. We extend this maintainability as part of our proposed adaptive system.

cs.DB↗

arXiv2021

FROCC: Fast Random projection-based One-Class Classification

We present Fast Random projection-based One-Class Classification (FROCC), an extremely efficient method for one-class classification. Our method is based on a simple idea of transforming the training data by projecting it onto a set of random unit vectors that are chosen uniformly and independently from the unit sphere, and bounding the regions based on separation of the data. FROCC can be naturally extended with kernels. We theoretically prove that FROCC generalizes well in the sense that it is stable and has low bias. FROCC achieves up to 3.1 percent points better ROC, with 1.2--67.8x speedup in training and test times over a range of state-of-the-art benchmarks including the SVM and the deep learning based models for the OCC task.

cs.LG↗

arXiv2021

BERT Meets Relational DB: Contextual Representations of Relational Databases

In this paper, we address the problem of learning low dimension representation of entities on relational databases consisting of multiple tables. Embeddings help to capture semantics encoded in the database and can be used in a variety of settings like auto-completion of tables, fully-neural query processing of relational joins queries, seamlessly handling missing values, and more. Current work is restricted to working with just single table, or using pretrained embeddings over an external corpus making them unsuitable for use in real-world databases. In this work, we look into ways of using these attention-based model to learn embeddings for entities in the relational database. We are inspired by BERT style pretraining methods and are interested in observing how they can be extended for representation learning on structured databases. We evaluate our approach of the autocompletion of relational databases and achieve improvement over standard baselines.

cs.CL↗

arXiv2021

Tracking entities in technical procedures -- a new dataset and baselines

We introduce TechTrack, a new dataset for tracking entities in technical procedures. The dataset, prepared by annotating open domain articles from WikiHow, consists of 1351 procedures, e.g., "How to connect a printer", identifies more than 1200 unique entities with an average of 4.7 entities per procedure. We evaluate the performance of state-of-the-art models on the entity-tracking task and find that they are well below the human annotation performance. We describe how TechTrack can be used to take forward the research on understanding procedures from temporal texts.

cs.CL↗

arXiv2020

A Survey on Semantic Parsing from the perspective of Compositionality

Different from previous surveys in semantic parsing (Kamath and Das, 2018) and knowledge base question answering(KBQA)(Chakraborty et al., 2019; Zhu et al., 2019; Hoffner et al., 2017) we try to takes a different perspective on the study of semantic parsing. Specifically, we will focus on (a)meaning composition from syntactical structure(Partee, 1975), and (b) the ability of semantic parsers to handle lexical variation given the context of a knowledge base (KB). In the following section after an introduction of the field of semantic parsing and its uses in KBQA, we will describe meaning representation using grammar formalism CCG (Steedman, 1996). We will discuss semantic composition using formal languages in Section 2. In section 3 we will consider systems that uses formal languages e.g. $λ$-calculus (Steedman, 1996), $λ$-DCS (Liang, 2013). Section 4 and 5 consider semantic parser using structured-language for logical form. Section 6 is on different benchmark datasets ComplexQuestions (Bao et al.,2016) and GraphQuestions (Su et al., 2016) that can be used to evaluate semantic parser on their ability to answer complex questions that are highly compositional in nature.

cs.CL↗

arXiv2020

How and Why is An Answer (Still) Correct? Maintaining Provenance in Dynamic Knowledge Graphs

Knowledge graphs (KGs) have increasingly become the backbone of many critical knowledge-centric applications. Most large-scale KGs used in practice are automatically constructed based on an ensemble of extraction techniques applied over diverse data sources. Therefore, it is important to establish the provenance of results for a query to determine how these were computed. Provenance is shown to be useful for assigning confidence scores to the results, for debugging the KG generation itself, and for providing answer explanations. In many such applications, certain queries are registered as standing queries since their answers are needed often. However, KGs keep continuously changing due to reasons such as changes in the source data, improvements to the extraction techniques, refinement/enrichment of information, and so on. This brings us to the issue of efficiently maintaining the provenance polynomials of complex graph pattern queries for dynamic and large KGs instead of having to recompute them from scratch each time the KG is updated. Addressing these issues, we present HUKA which uses provenance polynomials for tracking the derivation of query results over knowledge graphs by encoding the edges involved in generating the answer. More importantly, HUKA also maintains these provenance polynomials in the face of updates---insertions as well as deletions of facts---to the underlying KG. Experimental results over large real-world KGs such as YAGO and DBpedia with various benchmark SPARQL query workloads reveals that HUKA can be almost 50 times faster than existing systems for provenance computation on dynamic KGs.

cs.DB↗

arXiv2020

Modeling Implicit Communities using Spatio-Temporal Point Processes from Geo-tagged Event Traces

The location check-ins of users through various location-based services such as Foursquare, Twitter, and Facebook Places, etc., generate large traces of geo-tagged events. These event-traces often manifest in hidden (possibly overlapping) communities of users with similar interests. Inferring these implicit communities is crucial for forming user profiles for improvements in recommendation and prediction tasks. Given only time-stamped geo-tagged traces of users, can we find out these implicit communities, and characteristics of the underlying influence network? Can we use this network to improve the next location prediction task? In this paper, we focus on the problem of community detection as well as capturing the underlying diffusion process and propose a model COLAB based on Spatio-temporal point processes in continuous time but discrete space of locations that simultaneously models the implicit communities of users based on their check-in activities, without making use of their social network connections. COLAB captures the semantic features of the location, user-to-user influence along with spatial and temporal preferences of users. To learn the latent community of users and model parameters, we propose an algorithm based on stochastic variational inference. To the best of our knowledge, this is the first attempt at jointly modeling the diffusion process with activity-driven implicit communities. We demonstrate COLAB achieves up to 27% improvements in location prediction task over recent deep point-process based methods on geo-tagged event traces collected from Foursquare check-ins.

cs.SI↗

arXiv2020

IterefinE: Iterative KG Refinement Embeddings using Symbolic Knowledge

Knowledge Graphs (KGs) extracted from text sources are often noisy and lead to poor performance in downstream application tasks such as KG-based question answering.While much of the recent activity is focused on addressing the sparsity of KGs by using embeddings for inferring new facts, the issue of cleaning up of noise in KGs through KG refinement task is not as actively studied. Most successful techniques for KG refinement make use of inference rules and reasoning over ontologies. Barring a few exceptions, embeddings do not make use of ontological information, and their performance in KG refinement task is not well understood. In this paper, we present a KG refinement framework called IterefinE which iteratively combines the two techniques - one which uses ontological information and inferences rules, PSL-KGI, and the KG embeddings such as ComplEx and ConvE which do not. As a result, IterefinE is able to exploit not only the ontological information to improve the quality of predictions, but also the power of KG embeddings which (implicitly) perform longer chains of reasoning. The IterefinE framework, operates in a co-training mode and results in explicit type-supervised embedding of the refined KG from PSL-KGI which we call as TypeE-X. Our experiments over a range of KG benchmarks show that the embeddings that we produce are able to reject noisy facts from KG and at the same time infer higher quality new facts resulting in up to 9% improvement of overall weighted F1 score

cs.AI↗