State-of-the-art generalisation research in NLP: a taxonomy and review
The ability to generalise well is one of the primary desiderata of natural language
processing (NLP). Yet, what'good generalisation'entails and how it should be evaluated is …
processing (NLP). Yet, what'good generalisation'entails and how it should be evaluated is …
Mitigating popularity bias in recommendation with unbalanced interactions: A gradient perspective
Recommender systems learn from historical user-item interactions to identify preferred items
for target users. These observed interactions are usually unbalanced following a long-tailed …
for target users. These observed interactions are usually unbalanced following a long-tailed …
It's about Time: Rethinking Evaluation on Rumor Detection Benchmarks using Chronological Splits
New events emerge over time influencing the topics of rumors in social media. Current
rumor detection benchmarks use random splits as training, development and test sets which …
rumor detection benchmarks use random splits as training, development and test sets which …
Semi-supervised drifted stream learning with short lookback
In many scenarios, 1) data streams are generated in real time; 2) labeled data are expensive
and only limited labels are available in the beginning; 3) real-world data is not always iid …
and only limited labels are available in the beginning; 3) real-world data is not always iid …
Faithful and consistent graph neural network explanations with rationale alignment
Uncovering rationales behind predictions of graph neural networks (GNNs) has received
increasing attention over recent years. Instance-level GNN explanation aims to discover …
increasing attention over recent years. Instance-level GNN explanation aims to discover …
T-SaS: Toward Shift-aware Dynamic Adaptation for Streaming Data
In many real-world scenarios, distribution shifts exist in the streaming data across time steps.
Many complex sequential data can be effectively divided into distinct regimes that exhibit …
Many complex sequential data can be effectively divided into distinct regimes that exhibit …
Interpretable Imitation Learning with Dynamic Causal Relations
Imitation learning, which learns agent policy by mimicking expert demonstration, has shown
promising results in many applications such as medical treatment regimes and self-driving …
promising results in many applications such as medical treatment regimes and self-driving …
Open-topic false information detection on social networks with contrastive adversarial learning
G Ma, C Hu, L Ge, H Zhang - … of the 2022 Conference on Empirical …, 2022 - aclanthology.org
Current works about false information detection based on conversation graphs on social
networks focus primarily on two research streams from the standpoint of topic distribution: in …
networks focus primarily on two research streams from the standpoint of topic distribution: in …
Dynamic DAG Discovery for Interpretable Imitation Learning
Imitation learning, which learns agent policy by mimicking expert demonstration, has shown
promising results in many applications such as medical treatment regimes and self-driving …
promising results in many applications such as medical treatment regimes and self-driving …
Fusing Multiple Information Sources for Predictive Cardiac Modeling
Z Feng - 2024 - cdr.lib.unc.edu
Echocardiography is typically the first-line imaging study for most cardiac diagnoses due to
its versatility and cost-effectiveness. There is considerable interest in predictive machine …
its versatility and cost-effectiveness. There is considerable interest in predictive machine …