Semi-Structured Object Sequence Encoders

by   Rudra Murthy V, et al.

In this paper we explore the task of modeling (semi) structured object sequences; in particular we focus our attention on the problem of developing a structure-aware input representation for such sequences. In such sequences, we assume that each structured object is represented by a set of key-value pairs which encode the attributes of the structured object. Given a universe of keys, a sequence of structured objects can then be viewed as an evolution of the values for each key, over time. We encode and construct a sequential representation using the values for a particular key (Temporal Value Modeling - TVM) and then self-attend over the set of key-conditioned value sequences to a create a representation of the structured object sequence (Key Aggregation - KA). We pre-train and fine-tune the two components independently and present an innovative training schedule that interleaves the training of both modules with shared attention heads. We find that this iterative two part-training results in better performance than a unified network with hierarchical encoding as well as over, other methods that use a record-view representation of the sequence <cit.> or a simple flattened representation of the sequence. We conduct experiments using real-world data to demonstrate the advantage of interleaving TVM-KA on multiple tasks and detailed ablation studies motivating our modeling choices. We find that our approach performs better than flattening sequence objects and also allows us to operate on significantly larger sequences than existing methods.


page 3

page 7


Connecting 3-manifold triangulations with monotonic sequences of bistellar flips

A key result in computational 3-manifold topology is that any two triang...

Temporal Attention-Gated Model for Robust Sequence Classification

Typical techniques for sequence classification are designed for well-seg...

Sequence-based Person Attribute Recognition with Joint CTC-Attention Model

Attribute recognition has become crucial because of its wide application...

Point2Seq: Detecting 3D Objects as Sequences

We present a simple and effective framework, named Point2Seq, for 3D obj...

ST-DETR: Spatio-Temporal Object Traces Attention Detection Transformer

We propose ST-DETR, a Spatio-Temporal Transformer-based architecture for...

HGV4Risk: Hierarchical Global View-guided Sequence Representation Learning for Risk Prediction

Risk prediction, as a typical time series modeling problem, is usually a...

Sequen-C: A Multilevel Overview of Temporal Event Sequences

Building a visual overview of temporal event sequences with an optimal l...

Please sign up or login with your details

Forgot password? Click here to reset