#tmlr — Public Fediverse posts

Now out in #TMLR:

🍇 GRAPES: Learning to Sample Graphs for Scalable Graph Neural Networks 🍇

There's lots of work on sampling subgraphs for GNNs, but relatively little on making this sampling process _adaptive_. That is, learning to select the data from the graph that is relevant for your task.

We introduce an RL-based and a GFLowNet-based sampler and show that the approach performs well on heterophilic graphs.

https://openreview.net/forum?id=QI0l842vSq

#machinelearning #graphs #graph_learning #paper

Now out in #TMLR:

🍇 GRAPES: Learning to Sample Graphs for Scalable Graph Neural Networks 🍇

There's lots of work on sampling subgraphs for GNNs, but relatively little on making this sampling process _adaptive_. That is, learning to select the data from the graph that is relevant for your task.

We introduce an RL-based and a GFLowNet-based sampler and show that the approach performs well on heterophilic graphs.

https://openreview.net/forum?id=QI0l842vSq

#machinelearning #graphs #graph_learning #paper

Our work towards the design of deeper and competitive Forward-Forward Networks has been accepted at #TMLR.
https://openreview.net/forum?id=a7KP5uo0Fp

This was joint work with Inton Tsang (@inton) and Thomas Dooms. Kudos to Thomas as this was work he conducted as part of his CS Master Thesis project @UAntwerpen

#locallearning #FF @IDLabResearch

Our work towards the design of deeper and competitive Forward-Forward Networks has been accepted at #TMLR.
https://openreview.net/forum?id=a7KP5uo0Fp

This was joint work with Inton Tsang (@inton) and Thomas Dooms. Kudos to Thomas as this was work he conducted as part of his CS Master Thesis project @UAntwerpen

#locallearning #FF @IDLabResearch

Our work towards the design of deeper and competitive Forward-Forward Networks has been accepted at #TMLR.
https://openreview.net/forum?id=a7KP5uo0Fp

This was joint work with Inton Tsang (@inton) and Thomas Dooms. Kudos to Thomas as this was work he conducted as part of his CS Master Thesis project @UAntwerpen

#locallearning #FF @IDLabResearch

Our work towards the design of deeper and competitive Forward-Forward Networks has been accepted at #TMLR.
https://openreview.net/forum?id=a7KP5uo0Fp

This was joint work with Inton Tsang (@inton) and Thomas Dooms. Kudos to Thomas as this was work he conducted as part of his CS Master Thesis project @UAntwerpen

#locallearning #FF @IDLabResearch

🎉Last week, amid the #ICML2023 rush, we were informed that our paper (w/ Sonali Parbhoo and Marzyeh Ghassemi): "Risk Sensitive Dead-end Identification in Safety-Critical Offline Reinforcement Learning" was accepted to
#TMLR! 🎉 #ReinforcementLearning #Healthcare

The AutoML conference is happy to announce the partnership with #TMLR. As part of the journal track of #AUTOML23, you can also submit papers accepted at #TMLR. After a lightweight review, you can get an "AutoML certificate" at #TMLR and present your paper at #AUTOML23.

A connection between sparse and low rank matrices. Let S be a sparse similarity matrix, for example the distances of the 3 nearest neighbours in a low dimensional manifold. Can you recover S if you have a low rank (dense) matrix L from in a high dimensional space? This paper provides a geometric interpretation for S = max(0,L). It proposes a decomposition algorithm, that can be modelled as a ReLU neural network layer.

#MachineLearning #SparseDecomposition #LowRank #TMLR
https://openreview.net/forum?id=p8gncJbMit

A connection between sparse and low rank matrices. Let S be a sparse similarity matrix, for example the distances of the 3 nearest neighbours in a low dimensional manifold. Can you recover S if you have a low rank (dense) matrix L from in a high dimensional space? This paper provides a geometric interpretation for S = max(0,L). It proposes a decomposition algorithm, that can be modelled as a ReLU neural network layer.

#MachineLearning #SparseDecomposition #LowRank #TMLR
https://openreview.net/forum?id=p8gncJbMit

A connection between sparse and low rank matrices. Let S be a sparse similarity matrix, for example the distances of the 3 nearest neighbours in a low dimensional manifold. Can you recover S if you have a low rank (dense) matrix L from in a high dimensional space? This paper provides a geometric interpretation for S = max(0,L). It proposes a decomposition algorithm, that can be modelled as a ReLU neural network layer.

#MachineLearning #SparseDecomposition #LowRank #TMLR
https://openreview.net/forum?id=p8gncJbMit

A connection between sparse and low rank matrices. Let S be a sparse similarity matrix, for example the distances of the 3 nearest neighbours in a low dimensional manifold. Can you recover S if you have a low rank (dense) matrix L from in a high dimensional space? This paper provides a geometric interpretation for S = max(0,L). It proposes a decomposition algorithm, that can be modelled as a ReLU neural network layer.

#MachineLearning #SparseDecomposition #LowRank #TMLR
https://openreview.net/forum?id=p8gncJbMit

A connection between sparse and low rank matrices. Let S be a sparse similarity matrix, for example the distances of the 3 nearest neighbours in a low dimensional manifold. Can you recover S if you have a low rank (dense) matrix L from in a high dimensional space? This paper provides a geometric interpretation for S = max(0,L). It proposes a decomposition algorithm, that can be modelled as a ReLU neural network layer.

#MachineLearning #SparseDecomposition #LowRank #TMLR
https://openreview.net/forum?id=p8gncJbMit