Channel Avatar

Farshad Noravesh @UCJNTC3DYzfVpi2tdHY2x60Q@youtube.com

3.3K subscribers - no pronouns :c

I am open to collaborating with researchers on these 6 topic


07:30
Part 92: rethinking message passing for algorithmic alignment on graphs
10:54
Part 56: Leviticus 21-22
11:47
Part 91: maximizing influence with graph neural networks
14:40
Part 90: learning graph representations for influence maximization
12:30
Part 89: transforming pagerank into an infinite depth graph neural network
06:33
Part 88: word-graph2vec: An efficient word embedding approach on word cooccurence graph using ran...
10:16
Part 87: representation learning on heterostructures via heterogeneous anonymous walks
06:26
Part 86: revisiting random walks for learning on graphs
07:57
Part 85 : anonymous walk embeddings
12:12
Part 55: Leviticus 19-20
10:02
Part 84: graph neural networks with maximal independent set based pooling: mitigating...
11:27
Part 83: Liftpool: lifting-based graph pooling for hierarchical graph representation learning
13:31
Part 82: maximum independent set: self training through dynamic programming
07:45
Part 81: beyond GNNs: an efficient architecture for graph problems
14:44
Part 80: role based graph embeddings
08:56
Part 79: self-repellent random walks on general graphs-achieving minimal sampling variances via...
08:25
Part 54: Leviticus 17-18
12:02
Part 78: representation learning on graphs with jumping knowledge networks
10:21
Part 77: infoGCL: information-aware graph contrastive learning
10:51
Part 76: deepwalk: online learning of social representations
07:08
Part 75: higher order organization of complex networks
11:15
Part 74: a broader picture of random walk based graph embedding
06:21
Part 73: neural stochastic models & scalable community based graph learning
14:31
Part 53: Leviticus 15-16
07:35
Part 72: featured graph coarsening with similarity guarantees
11:52
Part 71: probabilistic graph rewiring via virtual nodes
04:56
Part 70: going deeper into permutation sensitive graph neural networks
09:19
Part 69: Non-convolutional graph neural networks
14:45
Part 67: RAW-GNN: random walk aggregation based graph neural network
07:46
Part 66: agent based graph neural networks
21:36
Part 52: Leviticus 13-14
14:34
Part 65: Path integral based convolution and pooling for graph neural networks.
06:30
Part 64: ABDPool: Attention based differentiable Pooling
12:02
Part 63: SSHPool: the separated subgraph based hierarchical pooling
15:30
Part 62: Random walk conformer: learning graph representation from long and short range
09:10
Part 61: The power of recursion in graph neural networks for counting substructures
14:15
Part 60: Learning long range dependencies on graphs via random walks
09:50
Part 51: Leviticus 11-12
13:31
Part 58: sparse structure learning via graph neural networks for inductive document classification
12:13
Part 57: Towards robust graph incremental learning on evolving graphs
10:34
Part 56: PANDA: expanded width-aware message passing beyond rewiring
09:52
Part 55: edge contraction pooling for graph neural networks
10:12
Part 54: graph neural network pooling by edge cut
10:06
Part 53: modularity-based sparse soft graph clustering
09:42
Part 50: Leviticus 9-10
17:30
Part 52: towards dynamic message passing on graphs
13:48
Part 51: GwAC: GNNs with asynchronous communication
10:06
Part 50: fast graph attention networks using effective resistance based graph sparsification
15:58
Part 49: differentiable cluster graph neural network
13:47
Part 48: tackling oversmoothing in GNN via graph sparsification
10:10
Part 47: graph clustering with graph neural networks
14:21
Part 49: Leviticus 7-8
14:59
Part 46: hierarchical graph pooling with structure learning
11:53
Part 45: fast and effective GNN training with linearized random spanning trees
11:09
Part 44: ASAP: adaptive structure aware pooling for learning hierarchical graph representation
08:10
Part 43: edge based graph component pooling
12:58
Part 42: grouping-matrix based graph pooling with adaptive number of clusters
06:16
Part 41: graph U-Nets
11:35
Part 48: Leviticus 5-6
09:11
Part 40: towards sparse hierarchical graph classifiers