| NAME |
POSTER TITLE |
SPOT |
| Hao WU |
Locally Differentially Private Frequency Estimation |
1 |
| Edwidge Cyffers |
Privacy Amplification by Decentralization |
2 |
| Fangshuo Liao |
On the Convergence of Shallow Neural Network Training with Randomly Masked Neurons |
3 |
| Yang Liu |
FEDGEMS: FEDERATED LEARNING OF LARGER SERVER MODELS VIA SELECTIVE KNOWLEDGE FUSION |
4 |
| Jianyu Wang |
Local Adaptivity in Federated Learning: Convergence and Consistency |
5 |
| Liam Collins |
Exploiting Shared Representations for Personalized Federated Learning |
6 |
| Aritra Mitra |
Linear Convergence in Federated Learning: Tackling Client Heterogeneity and Sparse Gradients |
7 |
| Cameron Wolfe |
GIST: Distributed Training for Large-Scale Graph Convolutional Networks |
8 |
| Edo Roth |
Private Distributed Analytics at Scale |
9 |
| Samuel Horvath |
Fair and Accurate Federated Learning under heterogeneous targets with Ordered Dropout |
10 |
| Hanieh Hashemi |
Byzantine-Robust and Privacy-Preserving Framwork for FedML |
11 |
| Othmane Marfoq |
Federated Multi-Task Learning under a Mixture of Distributions |
12 |
| Mónica Ribero |
Federated Learning Under Time-Varying Communication Constraints and Intermittent Client Availability |
13 |
| Albert Cheu |
SHUFFLE PRIVATE VECTOR SUMS |
14 |
| Carolina Naim |
Private Multi-Group Aggregation |
15 |
| Adam Dziedzic |
Confidential and Private Collaborative Learning |
16 |
| Jonas Geiping |
Robbing the Fed: Directly Obtaining Private Data in Federated Learning with Modified Models |
17 |
| Gavin Brown |
When Is Memorization of Irrelevant Training Data Required for High-Accuracy Learning? |
18 |
| Mohammad Taha Toghani |
Scalable Average Consensus with Compressed Communications |
19 |
| Saeedeh Parsaefard |
Robust Federated Learning by Mixture of Experts |
20 |
| Walid Saad |
Federated Learning and Wireless Networks: A Closer Union |
21 |
| Chen Dun |
ResIST: Layer-wise Decomposition of ResNets for Distributed Training |
22 |
| Mikko A. Heikkilä |
Tight accounting in the shuffle model of differential privacy |
23 |
| Ken Liu |
The Skellam Mechanism for Differentially Private Federated Learning |
24 |
| Yae Jee Cho |
Personalized Federated Learning (FL) for Heterogeneous Clients with Clustered Knowledge Transfer |
25 |
| Abhin Shah |
Optimal Compression of Locally Differentially Private Mechanism |
26 |
| Zheng Xu |
Practical and Private (Deep) Learning Without Sampling or Shuffling |
27 |
| Guari Joshi |
Leveraging Spatial and Temporal Correlations in Sparsified Mean Estimation |
28 |
| Peter Richtarik |
EF21: A New, Simpler, Theoretically Better, and Practically Faster Error Feedback |
29 |
| Jae Hun Ro |
FedJAX: Federated Learning Simulation with JAX |
30 |
| Ankit Singh Rawat |
FedLite: A Scalable Approach for Federated Learning on Resource-constrained Clients |
31 |
Amir Houmansadr
|
Back to the Drawing Board: A Critical Evaluation of Poisining Attacks on Federated Learning |
32 |
| Giulia Fanti |
Reducing the Communication Cost of Federated Learning through Multistage Optimization |
33 |
| Borja De Balle Pigem |
Reconstructing Training Data with Informed Adversaries |
34 |
| Marco Canini |
RELAY: Resource-Efficient Federated Learning |
35 |
| Eugene Bagdasaryan |
Towards Sparse Federated Analytics: Location Heatmaps under Distributed Differential Privacy with Secure Aggregation |
36 |
| Lun Wang |
FED-X2: Secure Federated Hypothesis Test |
37 |
