Model-agnostic counterfactual reasoning for eliminating popularity bias in recommender system
The general aim of the recommender system is to provide personalized suggestions to
users, which is opposed to suggesting popular items. However, the normal training …
users, which is opposed to suggesting popular items. However, the normal training …
Causal attention for interpretable and generalizable graph classification
In graph classification, attention-and pooling-based graph neural networks (GNNs) prevail to
extract the critical features from the input graph and support the prediction. They mostly …
extract the critical features from the input graph and support the prediction. They mostly …
Deconfounded video moment retrieval with causal intervention
We tackle the task of video moment retrieval (VMR), which aims to localize a specific
moment in a video according to a textual query. Existing methods primarily model the …
moment in a video according to a textual query. Existing methods primarily model the …
Deconfounded recommendation for alleviating bias amplification
Recommender systems usually amplify the biases in the data. The model learned from
historical interactions with imbalanced item distribution will amplify the imbalance by over …
historical interactions with imbalanced item distribution will amplify the imbalance by over …
Causerec: Counterfactual user sequence synthesis for sequential recommendation
Learning user representations based on historical behaviors lies at the core of modern
recommender systems. Recent advances in sequential recommenders have convincingly …
recommender systems. Recent advances in sequential recommenders have convincingly …
Causal representation learning for out-of-distribution recommendation
Modern recommender systems learn user representations from historical interactions, which
suffer from the problem of user feature shifts, such as an income increase. Historical …
suffer from the problem of user feature shifts, such as an income increase. Historical …
Exploring causal learning through graph neural networks: an in-depth review
In machine learning, exploring data correlations to predict outcomes is a fundamental task.
Recognizing causal relationships embedded within data is pivotal for a comprehensive …
Recognizing causal relationships embedded within data is pivotal for a comprehensive …
Brave the wind and the waves: Discovering robust and generalizable graph lottery tickets
The training and inference of Graph Neural Networks (GNNs) are costly when scaling up to
large-scale graphs. Graph Lottery Ticket (GLT) has presented the first attempt to accelerate …
large-scale graphs. Graph Lottery Ticket (GLT) has presented the first attempt to accelerate …
User-controllable recommendation against filter bubbles
Recommender systems usually face the issue of filter bubbles: over-recommending
homogeneous items based on user features and historical interactions. Filter bubbles will …
homogeneous items based on user features and historical interactions. Filter bubbles will …
Comprehensive linguistic-visual composition network for image retrieval
Composing text and image for image retrieval (CTI-IR) is a new yet challenging task, for
which the input query is not the conventional image or text but a composition, ie, a reference …
which the input query is not the conventional image or text but a composition, ie, a reference …